| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/xattr.h Extended attributes handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <uapi/linux/xattr.h> struct inode; struct dentry; /* * struct xattr_handler: When @name is set, match attributes with exactly that * name. When @prefix is set instead, match attributes with that prefix and * with a non-empty suffix. */ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { const char *name; void *value; size_t value_len; }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct dentry *, const char *); int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); int vfs_removexattr(struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supported_namespace(struct inode *inode, const char *prefix); static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; } struct simple_xattrs { struct list_head head; spinlock_t lock; }; struct simple_xattr { struct list_head list; char *name; size_t size; char value[]; }; /* * initialize the simple_xattrs structure */ static inline void simple_xattrs_init(struct simple_xattrs *xattrs) { INIT_LIST_HEAD(&xattrs->head); spin_lock_init(&xattrs->lock); } /* * free all the xattrs */ static inline void simple_xattrs_free(struct simple_xattrs *xattrs) { struct simple_xattr *xattr, *node; list_for_each_entry_safe(xattr, node, &xattrs->head, list) { kfree(xattr->name); kvfree(xattr); } } struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); #endif /* _LINUX_XATTR_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/major.h> #include <linux/genhd.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> #include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/pfn.h> #include <linux/bio.h> #include <linux/stringify.h> #include <linux/gfp.h> #include <linux/bsg.h> #include <linux/smp.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/scatterlist.h> #include <linux/blkzoned.h> #include <linux/pm.h> struct module; struct scsi_ioctl_command; struct request_queue; struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; struct blk_keyslot_manager; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 /* Doing classic polling */ #define BLK_MQ_POLL_CLASSIC -1 /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ #define BLKCG_MAX_POLS 5 static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; } typedef void (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* elevator knows about this request */ #define RQF_SORTED ((__force req_flags_t)(1 << 0)) /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) /* may not be passed by ioscheduler */ #define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) /* track inflight for MQ */ #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) /* runtime pm request */ #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) /* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* already slept for hybrid poll */ #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) /* * Request state for blk-mq. */ enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; struct list_head queuelist; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct list_head ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. So let the * completion_data share space with the rb_node. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; int error_count; /* for legacy drivers, don't use */ }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. Flush requests are * never put on the IO scheduler. So let the flush fields share * space with the elevator data. */ union { struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; struct list_head list; rq_end_io_fn *saved_end_io; } flush; }; struct gendisk *rq_disk; struct hd_struct *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; #if defined(CONFIG_BLK_DEV_INTEGRITY) unsigned short nr_integrity_segments; #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_ksm_keyslot *crypt_keyslot; #endif unsigned short write_hint; unsigned short ioprio; enum mq_rq_state state; refcount_t ref; unsigned int timeout; unsigned long deadline; union { struct __call_single_data csd; u64 fifo_time; }; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; }; static inline bool blk_op_is_scsi(unsigned int op) { return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT; } static inline bool blk_op_is_private(unsigned int op) { return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } static inline bool blk_rq_is_scsi(struct request *rq) { return blk_op_is_scsi(req_op(rq)); } static inline bool blk_rq_is_private(struct request *rq) { return blk_op_is_private(req_op(rq)); } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); } static inline bool bio_is_passthrough(struct bio *bio) { unsigned op = bio_op(bio); return blk_op_is_scsi(op) || blk_op_is_private(op); } static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; } #include <linux/elevator.h> struct blk_queue_ctx; struct bio_vec; enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ }; enum blk_queue_state { Queue_down, Queue_up, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) /* * Zoned block device models (zoned limit). * * Note: This needs to be ordered from the least to the most severe * restrictions for the inheritance in blk_stack_limits() to work. */ enum blk_zoned_model { BLK_ZONED_NONE = 0, /* Regular block device */ BLK_ZONED_HA, /* Host-aware zoned block device */ BLK_ZONED_HM, /* Host-managed zoned block device */ }; struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; unsigned int max_hw_sectors; unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned int zone_write_granularity; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blkdev_nr_zones(struct gendisk *disk) { return 0; } static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; struct percpu_ref q_usage_counter; struct blk_queue_stats *stats; struct rq_qos *rq_qos; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; unsigned int queue_depth; /* hw dispatch queues */ struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; struct backing_dev_info *backing_dev_info; /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. */ void *queuedata; /* * various queue flags, see QUEUE_* below */ unsigned long queue_flags; /* * Number of contexts that have called blk_set_pm_only(). If this * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from * ioctx. */ int id; /* * queue needs bounce pages for pages above this limit */ gfp_t bounce_gfp; spinlock_t queue_lock; /* * queue kobject */ struct kobject kobj; /* * mq queue kobject */ struct kobject *mq_kobj; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; unsigned int nr_pending; #endif /* * queue settings */ unsigned long nr_requests; /* Max # of requests */ unsigned int dma_pad_mask; unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION /* Inline crypto capabilities */ struct blk_keyslot_manager *ksm; #endif unsigned int rq_timeout; int poll_nsec; struct blk_stat_callback *poll_cb; struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_sbitmap; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); struct blkcg_gq *root_blkg; struct list_head blkg_list; #endif struct queue_limits limits; unsigned int required_elevator_features; #ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones * bits which indicates if a zone is conventional (bit set) or * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones * bits which indicates if a zone is write locked, that is, if a write * request targeting the zone was dispatched. All three fields are * initialized by the low level device driver (e.g. scsi/sd.c). * Stacking drivers (device mappers) may or may not initialize * these fields. * * Reads of this information must be protected with blk_queue_enter() / * blk_queue_exit(). Modifying this information is only allowed while * no requests are being processed. See also blk_mq_freeze_queue() and * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; unsigned int max_open_zones; unsigned int max_active_zones; #endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff */ unsigned int sg_timeout; unsigned int sg_reserved_size; int node; struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif /* * for flush operations */ struct blk_flush_queue *fq; struct list_head requeue_list; spinlock_t requeue_lock; struct delayed_work requeue_work; struct mutex sysfs_lock; struct mutex sysfs_dir_lock; /* * for reusing dead hctx instance in case of updating * nr_hw_queues */ struct list_head unused_hctx_list; spinlock_t unused_hctx_lock; int mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; #endif struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set bio_split; struct dentry *debugfs_dir; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif bool mq_sysfs_init_done; size_t cmd_size; #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_stable_writes(q) \ test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) #else #define blk_queue_rq_alloc_time(q) false #endif #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); static inline bool blk_account_rq(struct request *rq) { return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) #define dma_map_bvec(dev, bv, dir, attrs) \ dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } #ifdef CONFIG_PM static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return q->rpm_status; } #else static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return RPM_ACTIVE; } #endif static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) return q->limits.zoned; return BLK_ZONED_NONE; } static inline bool blk_queue_is_zoned(struct request_queue *q) { switch (blk_queue_zoned_model(q)) { case BLK_ZONED_HA: case BLK_ZONED_HM: return true; default: return false; } } static inline sector_t blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->nr_zones : 0; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return 0; return sector >> ilog2(q->limits.chunk_sectors); } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return false; if (!q->conv_zones_bitmap) return true; return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } static inline void blk_queue_max_open_zones(struct request_queue *q, unsigned int max_open_zones) { q->max_open_zones = max_open_zones; } static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return q->max_open_zones; } static inline void blk_queue_max_active_zones(struct request_queue *q, unsigned int max_active_zones) { q->max_active_zones = max_active_zones; } static inline unsigned int queue_max_active_zones(const struct request_queue *q) { return q->max_active_zones; } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return 0; } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { return false; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { return 0; } static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return 0; } static inline unsigned int queue_max_active_zones(const struct request_queue *q) { return 0; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) return false; if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; if (req_op(rq) == REQ_OP_ZONE_APPEND) return false; if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) return false; return true; } static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { if (bio_page(a) == bio_page(b) && bio_offset(a) == bio_offset(b)) return true; return false; } static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) return q->queue_depth; return q->nr_requests; } extern unsigned long blk_max_low_pfn, blk_max_pfn; /* * standard bounce addresses: * * BLK_BOUNCE_HIGH : bounce all highmem pages * BLK_BOUNCE_ANY : don't bounce anything * BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary */ #if BITS_PER_LONG == 32 #define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT) #else #define BLK_BOUNCE_HIGH -1ULL #endif #define BLK_BOUNCE_ANY (-1ULL) #define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) struct rq_map_data { struct page **pages; int page_order; int nr_entries; unsigned long offset; int null_mapped; int from_user; }; struct req_iterator { struct bvec_iter iter; struct bio *bio; }; /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" #endif #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE extern void rq_flush_dcache_pages(struct request *rq); #else static inline void rq_flush_dcache_pages(struct request *rq) { } #endif extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); blk_qc_t submit_bio_noacct(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); extern int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); extern int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); extern int blk_rq_unmap_user(struct bio *); extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); extern void blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(unsigned int op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; /* this is never NULL */ } /* * The basic unit of block I/O is a sector. It is used in a number of contexts * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 * bytes. Variables of type sector_t represent an offset or size that is a * multiple of 512 bytes. Hence these two constants. */ #ifndef SECTOR_SHIFT #define SECTOR_SHIFT 9 #endif #ifndef SECTOR_SIZE #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) { return rq->bio ? bio_cur_bytes(rq->bio) : 0; } extern unsigned int blk_rq_err_bytes(const struct request *rq); static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } #ifdef CONFIG_BLK_DEV_ZONED /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); } static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } #endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; return q->limits.max_sectors; } /* * Return maximum size of a request at given offset. Only valid for * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset, unsigned int chunk_sectors) { if (!chunk_sectors) { if (q->limits.chunk_sectors) chunk_sectors = q->limits.chunk_sectors; else return q->limits.max_sectors; } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); else chunk_sectors -= sector_div(offset, chunk_sectors); return min(q->limits.max_sectors, chunk_sectors); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); extern void blk_abort_request(struct request *); /* * Access functions for manipulating queue properties */ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); void blk_queue_zone_write_granularity(struct request_queue *q, unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); void blk_queue_update_readahead(struct request_queue *q); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg); static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; return __blk_rq_map_sg(q, rq, sglist, &last_sg); } extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests * into single larger request. As the requests are moved from a per-task list to * the device's request_queue in a batch, this results in improved scalability * as the lock contention for request_queue lock is reduced. * * It is ok not to disable preemption when adding the request to the plug list * or when attempting a merge, because blk_schedule_flush_list() will only flush * the plug list when the task sleeps by itself. For details, please see * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; bool multiple_queues; bool nowait; }; struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; blk_plug_cb_fn callback; void *data; }; extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); static inline void blk_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, false); } static inline void blk_schedule_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, true); } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; return plug && (!list_empty(&plug->mq_list) || !list_empty(&plug->cb_list)); } int blkdev_issue_flush(struct block_device *, gfp_t); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { }; static inline void blk_start_plug(struct blk_plug *plug) { } static inline void blk_finish_plug(struct blk_plug *plug) { } static inline void blk_flush_plug(struct task_struct *task) { } static inline void blk_schedule_flush_plug(struct task_struct *task) { } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { return false; } static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) { return 0; } static inline long nr_blockdev_pages(void) { return 0; } #endif /* CONFIG_BLOCK */ extern void blk_io_schedule(void); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, flags); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) { return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, 0); } extern int blk_verify_command(unsigned char *cmd, fmode_t mode); static inline bool bdev_is_partition(struct block_device *bdev) { return bdev->bd_partno; } enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, BLK_DEF_MAX_SECTORS = 2560, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; } static inline unsigned long queue_virt_boundary(const struct request_queue *q) { return q->limits.virt_boundary_mask; } static inline unsigned int queue_max_sectors(const struct request_queue *q) { return q->limits.max_sectors; } static inline unsigned int queue_max_hw_sectors(const struct request_queue *q) { return q->limits.max_hw_sectors; } static inline unsigned short queue_max_segments(const struct request_queue *q) { return q->limits.max_segments; } static inline unsigned short queue_max_discard_segments(const struct request_queue *q) { return q->limits.max_discard_segments; } static inline unsigned int queue_max_segment_size(const struct request_queue *q) { return q->limits.max_segment_size; } static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) { const struct queue_limits *l = &q->limits; return min(l->max_zone_append_sectors, l->max_sectors); } static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; if (q && q->limits.logical_block_size) retval = q->limits.logical_block_size; return retval; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_physical_block_size(const struct request_queue *q) { return q->limits.physical_block_size; } static inline unsigned int bdev_physical_block_size(struct block_device *bdev) { return queue_physical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_io_min(const struct request_queue *q) { return q->limits.io_min; } static inline unsigned int bdev_io_min(struct block_device *bdev) { return queue_io_min(bdev_get_queue(bdev)); } static inline unsigned int queue_io_opt(const struct request_queue *q) { return q->limits.io_opt; } static inline int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } static inline unsigned int queue_zone_write_granularity(const struct request_queue *q) { return q->limits.zone_write_granularity; } static inline unsigned int bdev_zone_write_granularity(struct block_device *bdev) { return queue_zone_write_granularity(bdev_get_queue(bdev)); } static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) return -1; return q->limits.alignment_offset; } static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) << SECTOR_SHIFT; return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q->limits.misaligned) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_part->start_sect); return q->limits.alignment_offset; } static inline int queue_discard_alignment(const struct request_queue *q) { if (q->limits.discard_misaligned) return -1; return q->limits.discard_alignment; } static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; /* Why are these in bytes, not sectors? */ alignment = lim->discard_alignment >> SECTOR_SHIFT; granularity = lim->discard_granularity >> SECTOR_SHIFT; if (!granularity) return 0; /* Offset of the partition start in 'granularity' sectors */ offset = sector_div(sector, granularity); /* And why do we do this modulus *again* in blkdev_issue_discard()? */ offset = (granularity + alignment - offset) % granularity; /* Turn it back into bytes, gaah */ return offset << SECTOR_SHIFT; } /* * Two cases of handling DISCARD merge: * If max_discard_segments > 1, the driver takes every bio * as a range and send them to controller together. The ranges * needn't to be contiguous. * Otherwise, the bios/requests will be handled as same as * others which should be contiguous. */ static inline bool blk_discard_mergable(struct request *req) { if (req_op(req) == REQ_OP_DISCARD && queue_max_discard_segments(req->q) > 1) return true; return false; } static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_part->start_sect); return q->limits.discard_alignment; } static inline unsigned int bdev_write_same(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_same_sectors; return 0; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_zeroes_sectors; return 0; } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zoned_model(q); return BLK_ZONED_NONE; } static inline bool bdev_is_zoned(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_is_zoned(q); return false; } static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zone_sectors(q); return 0; } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return queue_max_open_zones(q); return 0; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return queue_max_active_zones(q); return 0; } static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; } static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { unsigned int bits = 8; do { bits++; size >>= 1; } while (size > 256); return bits; } static inline unsigned int block_size(struct block_device *bdev) { return 1 << bdev->bd_inode->i_blkbits; } int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") #if defined(CONFIG_BLK_DEV_INTEGRITY) enum blk_integrity_flags { BLK_INTEGRITY_VERIFY = 1 << 0, BLK_INTEGRITY_GENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, }; struct blk_integrity_iter { void *prot_buf; void *data_buf; sector_t seed; unsigned int data_size; unsigned short interval; const char *disk_name; }; typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); typedef void (integrity_prepare_fn) (struct request *); typedef void (integrity_complete_fn) (struct request *, unsigned int); struct blk_integrity_profile { integrity_processing_fn *generate_fn; integrity_processing_fn *verify_fn; integrity_prepare_fn *prepare_fn; integrity_complete_fn *complete_fn; const char *name; }; extern void blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { struct blk_integrity *bi = &disk->queue->integrity; if (!bi->profile) return NULL; return bi; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) { return blk_get_integrity(bdev->bd_disk); } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return q->integrity.profile; } static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { q->limits.max_integrity_segments = segs; } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return q->limits.max_integrity_segments; } /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device * @sectors: Size of the bio in 512-byte sectors * * Description: The block layer calculates everything in 512 byte * sectors but integrity metadata is done in terms of the data integrity * interval size of the storage device. Convert the block layer sectors * to the appropriate number of integrity intervals. */ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } /* * Return the first bvec that contains integrity data. Only drivers that are * limited to a single integrity segment should use this helper. */ static inline struct bio_vec *rq_integrity_vec(struct request *rq) { if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) return NULL; return rq->bio->bi_integrity->bip_vec; } #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; struct block_device; struct gendisk; struct blk_integrity; static inline int blk_integrity_rq(struct request *rq) { return 0; } static inline int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *b) { return 0; } static inline int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *b, struct scatterlist *s) { return 0; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) { return 0; } static inline void blk_integrity_register(struct gendisk *d, struct blk_integrity *b) { } static inline void blk_integrity_unregister(struct gendisk *d) { } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return 0; } static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline struct bio_vec *rq_integrity_vec(struct request *rq) { return NULL; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_BLK_INLINE_ENCRYPTION bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); void blk_ksm_unregister(struct request_queue *q); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) { return true; } static inline void blk_ksm_unregister(struct request_queue *q) { } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ struct block_device_operations { blk_qc_t (*submit_bio) (struct bio *bio); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); char *(*devnode)(struct gendisk *disk, umode_t *mode); struct module *owner; const struct pr_ops *pr_ops; }; #ifdef CONFIG_COMPAT extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL #endif extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); #ifdef CONFIG_BLK_DEV_ZONED bool blk_req_needs_zone_write_lock(struct request *rq); bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); void __blk_req_zone_write_unlock(struct request *rq); static inline void blk_req_zone_write_lock(struct request *rq) { if (blk_req_needs_zone_write_lock(rq)) __blk_req_zone_write_lock(rq); } static inline void blk_req_zone_write_unlock(struct request *rq) { if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) __blk_req_zone_write_unlock(rq); } static inline bool blk_req_zone_is_write_locked(struct request *rq) { return rq->q->seq_zones_wlock && test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) { if (!blk_req_needs_zone_write_lock(rq)) return true; return !blk_req_zone_is_write_locked(rq); } #else static inline bool blk_req_needs_zone_write_lock(struct request *rq) { return false; } static inline void blk_req_zone_write_lock(struct request *rq) { } static inline void blk_req_zone_write_unlock(struct request *rq) { } static inline bool blk_req_zone_is_write_locked(struct request *rq) { return false; } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) { return true; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline void blk_wake_io_task(struct task_struct *waiter) { /* * If we're polling, the task itself is doing the completions. For * that case, we don't need to signal a wakeup, it's enough to just * mark us as RUNNING. */ if (waiter == current) __set_current_state(TASK_RUNNING); else wake_up_process(waiter); } unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, struct bio *bio); void part_end_io_acct(struct hd_struct *part, struct bio *bio, unsigned long start_time); /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for * * Returns the start time that should be passed back to bio_end_io_acct(). */ static inline unsigned long bio_start_io_acct(struct bio *bio) { return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio)); } /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for * @start: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); } int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); const char *bdevname(struct block_device *bdev, char *buffer); struct block_device *lookup_bdev(const char *); void blkdev_show(struct seq_file *seqf, off_t offset); #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK #define BLKDEV_MAJOR_MAX 512 #else #define BLKDEV_MAJOR_MAX 0 #endif struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, void *holder); void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); struct block_device *I_BDEV(struct inode *inode); struct block_device *bdget_part(struct hd_struct *part); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend); int sync_blockdev(struct block_device *bdev); #else static inline void invalidate_bdev(struct block_device *bdev) { } static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend) { return 0; } static inline int sync_blockdev(struct block_device *bdev) { return 0; } #endif int fsync_bdev(struct block_device *bdev); struct super_block *freeze_bdev(struct block_device *bdev); int thaw_bdev(struct block_device *bdev, struct super_block *sb); #endif /* _LINUX_BLKDEV_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov */ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/xarray.h> #include <linux/local_lock.h> /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node struct radix_tree_preload { local_lock_t lock; unsigned nr; /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer * 10 - internal entry * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). * This means that storing a NULL entry in the tree is the same as deleting * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL #define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { return ((unsigned long)ptr & RADIX_TREE_ENTRY_MASK) == RADIX_TREE_INTERNAL_NODE; } /*** radix-tree API starts here ***/ #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) #define RADIX_TREE_MAX_TAGS XA_MAX_MARKS #define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) #define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->xa_head == NULL; } /** * struct radix_tree_iter - radix tree iterator state * * @index: index of current slot * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is * described by a pointer to its first slot and a struct radix_tree_iter * which holds the chunk's position in the tree and its size. For tagged * iteration radix_tree_iter also holds the slots' bit-mask for one chosen * radix tree tag. */ struct radix_tree_iter { unsigned long index; unsigned long next_index; unsigned long tags; struct radix_tree_node *node; }; /** * Radix-tree synchronization * * The radix-tree API requires that users provide all synchronisation (with * specific exceptions, noted below). * * Synchronization of access to the data items being stored in the tree, and * management of their lifetimes must be completely managed by API users. * * For API usage, in general, * - any function _modifying_ the tree or tags (inserting or deleting * items, setting or clearing tags) must exclude other modifications, and * exclude any functions reading the tree. * - any function _reading_ the tree or tags (looking up items or tags, * gang lookups) must exclude modifications to the tree, but may occur * concurrently with other readers. * * The notable exceptions to this rule are the following functions: * __radix_tree_lookup * radix_tree_lookup * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. * * It is still required that the caller manage the synchronization and lifetimes * of the items. So if RCU lock-free lookups are used, typically this would mean * that the items have their own locks, or are amenable to lock-free access; and * that the items are freed by RCU (or only freed after having been deleted from * the radix tree *and* a synchronize_rcu() grace period). * * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * * Note that the value returned by radix_tree_tag_get() may not be relied upon * if only the RCU read lock is held. Functions to set/clear tags and to * delete nodes running concurrently with it may affect its result such that * two consecutive reads in the same locked section may return different * values. If reliability is required, modification functions must also be * excluded from concurrency. * * radix_tree_tagged is able to be called without locking or RCU. */ /** * radix_tree_deref_slot - dereference a slot * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is * held (ie. items cannot be concurrently inserted). * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot(void __rcu **slot) { return rcu_dereference(*slot); } /** * radix_tree_deref_slot_protected - dereference a slot with tree lock held * @slot: slot pointer, returned by radix_tree_lookup_slot * * Similar to radix_tree_deref_slot. The caller does not hold the RCU read * lock but it must hold the tree lock to prevent parallel updates. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot * Returns: 0 if retry is not required, otherwise retry is required * * radix_tree_deref_retry must be used with radix_tree_deref_slot. */ static inline int radix_tree_deref_retry(void *arg) { return unlikely(radix_tree_is_internal_node(arg)); } /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. */ static inline int radix_tree_exception(void *arg) { return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } int radix_tree_insert(struct radix_tree_root *, unsigned long index, void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ }; /** * radix_tree_iter_init - initialize radix tree iterator * * @iter: pointer to iterator state * @start: iteration starting index * Returns: NULL */ static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* * Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it * in the case of a successful tagged chunk lookup. If the lookup was * unsuccessful or non-tagged then nobody cares about ->tags. * * Set index to zero to bypass next_index overflow protection. * See the comment in radix_tree_next_chunk() for details. */ iter->index = 0; iter->next_index = start; return NULL; } /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if there no more left * * This function looks up the next chunk in the radix tree starting from * @iter->next_index. It returns a pointer to the chunk's first slot. * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** * radix_tree_iter_lookup - look up an index in the radix tree * @root: radix tree root * @iter: iterator state * @index: key to look up * * If @index is present in the radix tree, this function returns the slot * containing it and updates @iter to describe the entry. If @index is not * present, it returns NULL. */ static inline void __rcu ** radix_tree_iter_lookup(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned long index) { radix_tree_iter_init(iter, index); return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); } /** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * * If we iterate over a tree protected only by the RCU lock, a race * against deletion or creation may result in seeing a slot for which * radix_tree_deref_retry() returns true. If so, call this function * and continue the iteration. */ static inline __must_check void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; return NULL; } static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { return iter->index + slots; } /** * radix_tree_iter_resume - resume iterating when the chunk may be invalid * @slot: pointer to current slot * @iter: iterator state * Returns: New slot pointer * * If the iterator needs to release then reacquire a lock, the chunk may * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; } /** * radix_tree_next_slot - find next slot in chunk * * @slot: pointer to current slot * @iter: pointer to iterator state * @flags: RADIX_TREE_ITER_*, should be constant * Returns: pointer to next slot, or NULL if there no more left * * This function updates @iter->index in the case of a successful lookup. * For tagged lookup it also eats @iter->tags. * * There are several cases where 'slot' can be passed in as NULL to this * function. These cases result from the use of radix_tree_iter_resume() or * radix_tree_iter_retry(). In these cases we don't end up dereferencing * 'slot' because either: * a) we are doing tagged iteration and iter->tags has been set to 0, or * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; if (unlikely(!iter->tags)) return NULL; if (likely(iter->tags & 1ul)) { iter->index = __radix_tree_iter_add(iter, 1); slot++; goto found; } if (!(flags & RADIX_TREE_ITER_CONTIG)) { unsigned offset = __ffs(iter->tags); iter->tags >>= offset++; iter->index = __radix_tree_iter_add(iter, offset); slot += offset; goto found; } } else { long count = radix_tree_chunk_size(iter); while (--count > 0) { slot++; iter->index = __radix_tree_iter_add(iter, 1); if (likely(*slot)) goto found; if (flags & RADIX_TREE_ITER_CONTIG) { /* forbid switching to the next chunk */ iter->next_index = 0; break; } } } return NULL; found: return slot; } /** * radix_tree_for_each_slot - iterate over non-empty slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_slot(slot, root, iter, start) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) /** * radix_tree_for_each_tagged - iterate over tagged slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * @tag: tag index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_tagged(slot, root, iter, start, tag) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, \ RADIX_TREE_ITER_TAGGED | tag)) ; \ slot = radix_tree_next_slot(slot, iter, \ RADIX_TREE_ITER_TAGGED | tag)) #endif /* _LINUX_RADIX_TREE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Tracing hooks * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This file defines hook entry points called by core code where * user tracing/debugging support might need to do something. These * entry points are called tracehook_*(). Each hook declared below * has a detailed kerneldoc comment giving the context (locking et * al) from which it is called, and the meaning of its return value. * * Each function here typically has only one call site, so it is ok * to have some nontrivial tracehook_*() inlines. In all cases, the * fast path when no tracing is enabled should be very short. * * The purpose of this file and the tracehook_* layer is to consolidate * the interface that the kernel core and arch code uses to enable any * user debugging or tracing facility (such as ptrace). The interfaces * here are carefully documented so that maintainers of core and arch * code do not need to think about the implementation details of the * tracing facilities. Likewise, maintainers of the tracing code do not * need to understand all the calling core or arch code in detail, just * documented circumstances of each call, such as locking conditions. * * If the calling core code changes so that locking is different, then * it is ok to change the interface documented here. The maintainer of * core code changing should notify the maintainers of the tracing code * that they need to work out the change. * * Some tracehook_*() inlines take arguments that the current tracing * implementations might not necessarily use. These function signatures * are chosen to pass in all the information that is on hand in the * caller and might conceivably be relevant to a tracer, so that the * core code won't have to be updated when tracing adds more features. * If a call site changes so that some of those parameters are no longer * already on hand without extra work, then the tracehook_* interface * can change so there is no make-work burden on the core code. The * maintainer of core code changing should notify the maintainers of the * tracing code that they need to work out the change. */ #ifndef _LINUX_TRACEHOOK_H #define _LINUX_TRACEHOOK_H 1 #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/blk-cgroup.h> struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(struct pt_regs *regs, unsigned long message) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; current->ptrace_message = message; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (current->exit_code) { send_sig(current->exit_code, current, 1); current->exit_code = 0; } current->ptrace_message = 0; return fatal_signal_pending(current); } /** * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * tracehook_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %TIF_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); } /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use * * Called by the arch code after a signal handler has been set up. * Register and stack state reflects the user handler about to run. * Signal mask changes have already been made. * * Called without locks, shortly before returning to user mode * (or handling more signals). */ static inline void tracehook_signal_handler(int stepping) { if (stepping) ptrace_notify(SIGTRAP); } /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() * * Calling this arranges that @task will call tracehook_notify_resume() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call tracehook_notify_resume() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { #ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); #endif } /** * tracehook_notify_resume - report when about to return to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void tracehook_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); } /* * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This * is currently used by TWA_SIGNAL based task_work, which requires breaking * wait loops to ensure that task_work is noticed and run. */ static inline void tracehook_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); if (current->task_works) task_work_run(); } /* * Called when we have work to process from exit_to_user_mode_loop() */ static inline void set_notify_signal(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE)) kick_process(task); } #endif /* <linux/tracehook.h> */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(struct page *page) { return atomic_read(&page->_refcount); } static inline int page_count(struct page *page) { return atomic_read(&compound_head(page)->_refcount); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline int page_ref_sub_return(struct page *page, int nr) { int ret = atomic_sub_return(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int page_ref_add_unless(struct page *page, int nr, int u) { int ret = atomic_add_unless(&page->_refcount, nr, u); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_SORT_EXTABLE #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ #endif /* !ARCH_HAS_SORT_EXTABLE */ #ifndef ARCH_HAS_SEARCH_EXTABLE static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 | // SPDX-License-Identifier: GPL-2.0-or-later /* * linux/drivers/net/netconsole.c * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * * This file contains the implementation of an IRQ-safe, crash-safe * kernel console implementation that outputs kernel messages to the * network. * * Modification history: * * 2001-09-17 started by Ingo Molnar. * 2003-08-11 2.6 port by Matt Mackall * simplified options * generic card hooks * works non-modular * 2003-09-07 rewritten with netpoll api */ /**************************************************************** * ****************************************************************/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/console.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/netpoll.h> #include <linux/inet.h> #include <linux/configfs.h> #include <linux/etherdevice.h> MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); #define MAX_PARAM_LENGTH 256 #define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0); MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]"); static bool oops_only = false; module_param(oops_only, bool, 0600); MODULE_PARM_DESC(oops_only, "Only log oops messages"); #ifndef MODULE static int __init option_setup(char *opt) { strlcpy(config, opt, MAX_PARAM_LENGTH); return 1; } __setup("netconsole=", option_setup); #endif /* MODULE */ /* Linked list of all configured targets */ static LIST_HEAD(target_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to * avoid unnecessarily enabling ext message formatting. */ static struct console netconsole_ext; /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. * @item: Links us into the configfs subsystem hierarchy. * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). * We maintain a strict 1:1 correspondence between this and * whether the corresponding netpoll is active or inactive. * Also, other parameters of a target may be modified at * runtime only when it is disabled (enabled == 0). * @np: The netpoll structure for this target. * Contains the other userspace visible parameters: * dev_name (read-write) * local_port (read-write) * remote_port (read-write) * local_ip (read-write) * remote_ip (read-write) * local_mac (read-only) * remote_mac (read-write) */ struct netconsole_target { struct list_head list; #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_item item; #endif bool enabled; bool extended; struct netpoll np; }; #ifdef CONFIG_NETCONSOLE_DYNAMIC static struct configfs_subsystem netconsole_subsys; static DEFINE_MUTEX(dynamic_netconsole_mutex); static int __init dynamic_netconsole_init(void) { config_group_init(&netconsole_subsys.su_group); mutex_init(&netconsole_subsys.su_mutex); return configfs_register_subsystem(&netconsole_subsys); } static void __exit dynamic_netconsole_exit(void) { configfs_unregister_subsystem(&netconsole_subsys); } /* * Targets that were created by parsing the boot/module option string * do not exist in the configfs hierarchy (and have NULL names) and will * never go away, so make these a no-op for them. */ static void netconsole_target_get(struct netconsole_target *nt) { if (config_item_name(&nt->item)) config_item_get(&nt->item); } static void netconsole_target_put(struct netconsole_target *nt) { if (config_item_name(&nt->item)) config_item_put(&nt->item); } #else /* !CONFIG_NETCONSOLE_DYNAMIC */ static int __init dynamic_netconsole_init(void) { return 0; } static void __exit dynamic_netconsole_exit(void) { } /* * No danger of targets going away from under us when dynamic * reconfigurability is off. */ static void netconsole_target_get(struct netconsole_target *nt) { } static void netconsole_target_put(struct netconsole_target *nt) { } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Allocate new target (from boot/module param) and setup netpoll for it */ static struct netconsole_target *alloc_param_target(char *target_config) { int err = -ENOMEM; struct netconsole_target *nt; /* * Allocate and initialize with defaults. * Note that these targets get their config_item fields zeroed-out. */ nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) goto fail; nt->np.name = "netconsole"; strlcpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; eth_broadcast_addr(nt->np.remote_mac); if (*target_config == '+') { nt->extended = true; target_config++; } /* Parse parameters and setup netpoll */ err = netpoll_parse_options(&nt->np, target_config); if (err) goto fail; err = netpoll_setup(&nt->np); if (err) goto fail; nt->enabled = true; return nt; fail: kfree(nt); return ERR_PTR(err); } /* Cleanup netpoll for given target (from boot/module param) and free it */ static void free_param_target(struct netconsole_target *nt) { netpoll_cleanup(&nt->np); kfree(nt); } #ifdef CONFIG_NETCONSOLE_DYNAMIC /* * Our subsystem hierarchy is: * * /sys/kernel/config/netconsole/ * | * <target>/ * | enabled * | dev_name * | local_port * | remote_port * | local_ip * | remote_ip * | local_mac * | remote_mac * | * <target>/... */ static struct netconsole_target *to_target(struct config_item *item) { return item ? container_of(item, struct netconsole_target, item) : NULL; } /* * Attribute operations for netconsole_target. */ static ssize_t enabled_show(struct config_item *item, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->enabled); } static ssize_t extended_show(struct config_item *item, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->extended); } static ssize_t dev_name_show(struct config_item *item, char *buf) { return snprintf(buf, PAGE_SIZE, "%s\n", to_target(item)->np.dev_name); } static ssize_t local_port_show(struct config_item *item, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->np.local_port); } static ssize_t remote_port_show(struct config_item *item, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", to_target(item)->np.remote_port); } static ssize_t local_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return snprintf(buf, PAGE_SIZE, "%pI6c\n", &nt->np.local_ip.in6); else return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.local_ip); } static ssize_t remote_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return snprintf(buf, PAGE_SIZE, "%pI6c\n", &nt->np.remote_ip.in6); else return snprintf(buf, PAGE_SIZE, "%pI4\n", &nt->np.remote_ip); } static ssize_t local_mac_show(struct config_item *item, char *buf) { struct net_device *dev = to_target(item)->np.dev; static const u8 bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; return snprintf(buf, PAGE_SIZE, "%pM\n", dev ? dev->dev_addr : bcast); } static ssize_t remote_mac_show(struct config_item *item, char *buf) { return snprintf(buf, PAGE_SIZE, "%pM\n", to_target(item)->np.remote_mac); } /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. * The user is expected to set the desired parameters first (which * would enable him to dynamically add new netpoll targets for new * network interfaces as and when they come up). */ static ssize_t enabled_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); unsigned long flags; int enabled; int err; mutex_lock(&dynamic_netconsole_mutex); err = kstrtoint(buf, 10, &enabled); if (err < 0) goto out_unlock; err = -EINVAL; if (enabled < 0 || enabled > 1) goto out_unlock; if ((bool)enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); goto out_unlock; } if (enabled) { /* true */ if (nt->extended && !(netconsole_ext.flags & CON_ENABLED)) { netconsole_ext.flags |= CON_ENABLED; register_console(&netconsole_ext); } /* * Skip netpoll_parse_options() -- all the attributes are * already configured via configfs. Just print them out. */ netpoll_print_options(&nt->np); err = netpoll_setup(&nt->np); if (err) goto out_unlock; pr_info("network logging started\n"); } else { /* false */ /* We need to disable the netconsole before cleaning it up * otherwise we might end up in write_msg() with * nt->np.dev == NULL and nt->enabled == true */ spin_lock_irqsave(&target_list_lock, flags); nt->enabled = false; spin_unlock_irqrestore(&target_list_lock, flags); netpoll_cleanup(&nt->np); } nt->enabled = enabled; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return err; } static ssize_t extended_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); int extended; int err; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); err = -EINVAL; goto out_unlock; } err = kstrtoint(buf, 10, &extended); if (err < 0) goto out_unlock; if (extended < 0 || extended > 1) { err = -EINVAL; goto out_unlock; } nt->extended = extended; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return err; } static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); size_t len; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } strlcpy(nt->np.dev_name, buf, IFNAMSIZ); /* Get rid of possible trailing newline from echo(1) */ len = strnlen(nt->np.dev_name, IFNAMSIZ); if (nt->np.dev_name[len - 1] == '\n') nt->np.dev_name[len - 1] = '\0'; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); } static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); int rv = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); goto out_unlock; } rv = kstrtou16(buf, 10, &nt->np.local_port); if (rv < 0) goto out_unlock; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return rv; } static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); int rv = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); goto out_unlock; } rv = kstrtou16(buf, 10, &nt->np.remote_port); if (rv < 0) goto out_unlock; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return rv; } static ssize_t local_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.local_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) { nt->np.local_ip.ip = in_aton(buf); } else goto out_unlock; } mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } static ssize_t remote_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.remote_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) { nt->np.remote_ip.ip = in_aton(buf); } else goto out_unlock; } mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); u8 remote_mac[ETH_ALEN]; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->item)); goto out_unlock; } if (!mac_pton(buf, remote_mac)) goto out_unlock; if (buf[3 * ETH_ALEN - 1] && buf[3 * ETH_ALEN - 1] != '\n') goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } CONFIGFS_ATTR(, enabled); CONFIGFS_ATTR(, extended); CONFIGFS_ATTR(, dev_name); CONFIGFS_ATTR(, local_port); CONFIGFS_ATTR(, remote_port); CONFIGFS_ATTR(, local_ip); CONFIGFS_ATTR(, remote_ip); CONFIGFS_ATTR_RO(, local_mac); CONFIGFS_ATTR(, remote_mac); static struct configfs_attribute *netconsole_target_attrs[] = { &attr_enabled, &attr_extended, &attr_dev_name, &attr_local_port, &attr_remote_port, &attr_local_ip, &attr_remote_ip, &attr_local_mac, &attr_remote_mac, NULL, }; /* * Item operations and type for netconsole_target. */ static void netconsole_target_release(struct config_item *item) { kfree(to_target(item)); } static struct configfs_item_operations netconsole_target_item_ops = { .release = netconsole_target_release, }; static const struct config_item_type netconsole_target_type = { .ct_attrs = netconsole_target_attrs, .ct_item_ops = &netconsole_target_item_ops, .ct_owner = THIS_MODULE, }; /* * Group operations and type for netconsole_subsys. */ static struct config_item *make_netconsole_target(struct config_group *group, const char *name) { unsigned long flags; struct netconsole_target *nt; /* * Allocate and initialize with defaults. * Target is disabled at creation (!enabled). */ nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return ERR_PTR(-ENOMEM); nt->np.name = "netconsole"; strlcpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; eth_broadcast_addr(nt->np.remote_mac); /* Initialize the config_item member */ config_item_init_type_name(&nt->item, name, &netconsole_target_type); /* Adding, but it is disabled */ spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); return &nt->item; } static void drop_netconsole_target(struct config_group *group, struct config_item *item) { unsigned long flags; struct netconsole_target *nt = to_target(item); spin_lock_irqsave(&target_list_lock, flags); list_del(&nt->list); spin_unlock_irqrestore(&target_list_lock, flags); /* * The target may have never been enabled, or was manually disabled * before being removed so netpoll may have already been cleaned up. */ if (nt->enabled) netpoll_cleanup(&nt->np); config_item_put(&nt->item); } static struct configfs_group_operations netconsole_subsys_group_ops = { .make_item = make_netconsole_target, .drop_item = drop_netconsole_target, }; static const struct config_item_type netconsole_subsys_type = { .ct_group_ops = &netconsole_subsys_group_ops, .ct_owner = THIS_MODULE, }; /* The netconsole configfs subsystem */ static struct configfs_subsystem netconsole_subsys = { .su_group = { .cg_item = { .ci_namebuf = "netconsole", .ci_type = &netconsole_subsys_type, }, }, }; #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Handle network interface device notifications */ static int netconsole_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { unsigned long flags; struct netconsole_target *nt; struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER || event == NETDEV_RELEASE || event == NETDEV_JOIN)) goto done; spin_lock_irqsave(&target_list_lock, flags); restart: list_for_each_entry(nt, &target_list, list) { netconsole_target_get(nt); if (nt->np.dev == dev) { switch (event) { case NETDEV_CHANGENAME: strlcpy(nt->np.dev_name, dev->name, IFNAMSIZ); break; case NETDEV_RELEASE: case NETDEV_JOIN: case NETDEV_UNREGISTER: /* rtnl_lock already held * we might sleep in __netpoll_cleanup() */ nt->enabled = false; spin_unlock_irqrestore(&target_list_lock, flags); __netpoll_cleanup(&nt->np); spin_lock_irqsave(&target_list_lock, flags); dev_put(nt->np.dev); nt->np.dev = NULL; stopped = true; netconsole_target_put(nt); goto restart; } } netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); if (stopped) { const char *msg = "had an event"; switch (event) { case NETDEV_UNREGISTER: msg = "unregistered"; break; case NETDEV_RELEASE: msg = "released slaves"; break; case NETDEV_JOIN: msg = "is joining a master device"; break; } pr_info("network logging stopped on interface %s as it %s\n", dev->name, msg); } done: return NOTIFY_DONE; } static struct notifier_block netconsole_netdev_notifier = { .notifier_call = netconsole_netdev_event, }; /** * send_ext_msg_udp - send extended log message to target * @nt: target to send message to * @msg: extended log message to send * @msg_len: length of message * * Transfer extended log @msg to @nt. If @msg is longer than * MAX_PRINT_CHUNK, it'll be split and transmitted in multiple chunks with * ncfrag header field added to identify them. */ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, int msg_len) { static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */ const char *header, *body; int offset = 0; int header_len, body_len; if (msg_len <= MAX_PRINT_CHUNK) { netpoll_send_udp(&nt->np, msg, msg_len); return; } /* need to insert extra header fields, detect header and body */ header = msg; body = memchr(msg, ';', msg_len); if (WARN_ON_ONCE(!body)) return; header_len = body - header; body_len = msg_len - header_len - 1; body++; /* * Transfer multiple chunks with the following extra header. * "ncfrag=<byte-offset>/<total-bytes>" */ memcpy(buf, header, header_len); while (offset < body_len) { int this_header = header_len; int this_chunk; this_header += scnprintf(buf + this_header, sizeof(buf) - this_header, ",ncfrag=%d/%d;", offset, body_len); this_chunk = min(body_len - offset, MAX_PRINT_CHUNK - this_header); if (WARN_ON_ONCE(this_chunk <= 0)) return; memcpy(buf + this_header, body + offset, this_chunk); netpoll_send_udp(&nt->np, buf, this_header + this_chunk); offset += this_chunk; } } static void write_ext_msg(struct console *con, const char *msg, unsigned int len) { struct netconsole_target *nt; unsigned long flags; if ((oops_only && !oops_in_progress) || list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) if (nt->extended && nt->enabled && netif_running(nt->np.dev)) send_ext_msg_udp(nt, msg, len); spin_unlock_irqrestore(&target_list_lock, flags); } static void write_msg(struct console *con, const char *msg, unsigned int len) { int frag, left; unsigned long flags; struct netconsole_target *nt; const char *tmp; if (oops_only && !oops_in_progress) return; /* Avoid taking lock and disabling interrupts unnecessarily */ if (list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!nt->extended && nt->enabled && netif_running(nt->np.dev)) { /* * We nest this inside the for-each-target loop above * so that we're able to get as much logging out to * at least one target if we die inside here, instead * of unnecessarily keeping all targets in lock-step. */ tmp = msg; for (left = len; left;) { frag = min(left, MAX_PRINT_CHUNK); netpoll_send_udp(&nt->np, tmp, frag); tmp += frag; left -= frag; } } } spin_unlock_irqrestore(&target_list_lock, flags); } static struct console netconsole_ext = { .name = "netcon_ext", .flags = CON_EXTENDED, /* starts disabled, registered on first use */ .write = write_ext_msg, }; static struct console netconsole = { .name = "netcon", .flags = CON_ENABLED, .write = write_msg, }; static int __init init_netconsole(void) { int err; struct netconsole_target *nt, *tmp; unsigned long flags; char *target_config; char *input = config; if (strnlen(input, MAX_PARAM_LENGTH)) { while ((target_config = strsep(&input, ";"))) { nt = alloc_param_target(target_config); if (IS_ERR(nt)) { err = PTR_ERR(nt); goto fail; } /* Dump existing printks when we register */ if (nt->extended) netconsole_ext.flags |= CON_PRINTBUFFER | CON_ENABLED; else netconsole.flags |= CON_PRINTBUFFER; spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); } } err = register_netdevice_notifier(&netconsole_netdev_notifier); if (err) goto fail; err = dynamic_netconsole_init(); if (err) goto undonotifier; if (netconsole_ext.flags & CON_ENABLED) register_console(&netconsole_ext); register_console(&netconsole); pr_info("network logging started\n"); return err; undonotifier: unregister_netdevice_notifier(&netconsole_netdev_notifier); fail: pr_err("cleaning up\n"); /* * Remove all targets and destroy them (only targets created * from the boot/module option exist here). Skipping the list * lock is safe here, and netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } return err; } static void __exit cleanup_netconsole(void) { struct netconsole_target *nt, *tmp; unregister_console(&netconsole_ext); unregister_console(&netconsole); dynamic_netconsole_exit(); unregister_netdevice_notifier(&netconsole_netdev_notifier); /* * Targets created via configfs pin references on our module * and would first be rmdir(2)'ed from userspace. We reach * here only when they are already destroyed, and only those * created from the boot/module option are left, so remove and * destroy them. Skipping the list lock is safe here, and * netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } } /* * Use late_initcall to ensure netconsole is * initialized after network device driver if built-in. * * late_initcall() and module_init() are identical if built as module. */ late_initcall(init_netconsole); module_exit(cleanup_netconsole); |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to setting various queue properties from drivers */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/memblock.h> /* for max_pfn/max_low_pfn */ #include <linux/gcd.h> #include <linux/lcm.h> #include <linux/jiffies.h> #include <linux/gfp.h> #include <linux/dma-mapping.h> #include "blk.h" #include "blk-wbt.h" unsigned long blk_max_low_pfn; EXPORT_SYMBOL(blk_max_low_pfn); unsigned long blk_max_pfn; void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) { q->rq_timeout = timeout; } EXPORT_SYMBOL_GPL(blk_queue_rq_timeout); /** * blk_set_default_limits - reset limits to default values * @lim: the queue_limits structure to reset * * Description: * Returns a queue_limit struct to its default state. */ void blk_set_default_limits(struct queue_limits *lim) { lim->max_segments = BLK_MAX_SEGMENTS; lim->max_discard_segments = 1; lim->max_integrity_segments = 0; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->virt_boundary_mask = 0; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; lim->max_dev_sectors = 0; lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; lim->max_write_zeroes_sectors = 0; lim->max_zone_append_sectors = 0; lim->max_discard_sectors = 0; lim->max_hw_discard_sectors = 0; lim->discard_granularity = 0; lim->discard_alignment = 0; lim->discard_misaligned = 0; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; lim->io_opt = 0; lim->misaligned = 0; lim->zoned = BLK_ZONED_NONE; lim->zone_write_granularity = 0; } EXPORT_SYMBOL(blk_set_default_limits); /** * blk_set_stacking_limits - set default limits for stacking devices * @lim: the queue_limits structure to reset * * Description: * Returns a queue_limit struct to its default state. Should be used * by stacking drivers like DM that have no internal limits. */ void blk_set_stacking_limits(struct queue_limits *lim) { blk_set_default_limits(lim); /* Inherit limits from component devices */ lim->max_segments = USHRT_MAX; lim->max_discard_segments = USHRT_MAX; lim->max_hw_sectors = UINT_MAX; lim->max_segment_size = UINT_MAX; lim->max_sectors = UINT_MAX; lim->max_dev_sectors = UINT_MAX; lim->max_write_same_sectors = UINT_MAX; lim->max_write_zeroes_sectors = UINT_MAX; lim->max_zone_append_sectors = UINT_MAX; } EXPORT_SYMBOL(blk_set_stacking_limits); /** * blk_queue_bounce_limit - set bounce buffer limit for queue * @q: the request queue for the device * @max_addr: the maximum address the device can handle * * Description: * Different hardware can have different requirements as to what pages * it can do I/O directly to. A low level driver can call * blk_queue_bounce_limit to have lower memory pages allocated as bounce * buffers for doing I/O to pages residing above @max_addr. **/ void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr) { unsigned long b_pfn = max_addr >> PAGE_SHIFT; int dma = 0; q->bounce_gfp = GFP_NOIO; #if BITS_PER_LONG == 64 /* * Assume anything <= 4GB can be handled by IOMMU. Actually * some IOMMUs can handle everything, but I don't know of a * way to test this here. */ if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT)) dma = 1; q->limits.bounce_pfn = max(max_low_pfn, b_pfn); #else if (b_pfn < blk_max_low_pfn) dma = 1; q->limits.bounce_pfn = b_pfn; #endif if (dma) { init_emergency_isa_pool(); q->bounce_gfp = GFP_NOIO | GFP_DMA; q->limits.bounce_pfn = b_pfn; } } EXPORT_SYMBOL(blk_queue_bounce_limit); /** * blk_queue_max_hw_sectors - set max sectors for a request for this queue * @q: the request queue for the device * @max_hw_sectors: max hardware sectors in the usual 512b unit * * Description: * Enables a low level driver to set a hard upper limit, * max_hw_sectors, on the size of requests. max_hw_sectors is set by * the device driver based upon the capabilities of the I/O * controller. * * max_dev_sectors is a hard limit imposed by the storage device for * READ/WRITE requests. It is set by the disk driver. * * max_sectors is a soft limit imposed by the block layer for * filesystem type requests. This value can be overridden on a * per-device basis in /sys/block/<device>/queue/max_sectors_kb. * The soft limit can not exceed max_hw_sectors. **/ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) { struct queue_limits *limits = &q->limits; unsigned int max_sectors; if ((max_hw_sectors << 9) < PAGE_SIZE) { max_hw_sectors = 1 << (PAGE_SHIFT - 9); printk(KERN_INFO "%s: set to minimum %d\n", __func__, max_hw_sectors); } limits->max_hw_sectors = max_hw_sectors; max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); limits->max_sectors = max_sectors; q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); /** * blk_queue_chunk_sectors - set size of the chunk for this queue * @q: the request queue for the device * @chunk_sectors: chunk sectors in the usual 512b unit * * Description: * If a driver doesn't want IOs to cross a given chunk size, it can set * this limit and prevent merging across chunks. Note that the block layer * must accept a page worth of data at any offset. So if the crossing of * chunks is a hard limitation in the driver, it must still be prepared * to split single page bios. **/ void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors) { q->limits.chunk_sectors = chunk_sectors; } EXPORT_SYMBOL(blk_queue_chunk_sectors); /** * blk_queue_max_discard_sectors - set max sectors for a single discard * @q: the request queue for the device * @max_discard_sectors: maximum number of sectors to discard **/ void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors) { q->limits.max_hw_discard_sectors = max_discard_sectors; q->limits.max_discard_sectors = max_discard_sectors; } EXPORT_SYMBOL(blk_queue_max_discard_sectors); /** * blk_queue_max_write_same_sectors - set max sectors for a single write same * @q: the request queue for the device * @max_write_same_sectors: maximum number of sectors to write per command **/ void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors) { q->limits.max_write_same_sectors = max_write_same_sectors; } EXPORT_SYMBOL(blk_queue_max_write_same_sectors); /** * blk_queue_max_write_zeroes_sectors - set max sectors for a single * write zeroes * @q: the request queue for the device * @max_write_zeroes_sectors: maximum number of sectors to write per command **/ void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_zeroes_sectors) { q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors; } EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors); /** * blk_queue_max_zone_append_sectors - set max sectors for a single zone append * @q: the request queue for the device * @max_zone_append_sectors: maximum number of sectors to write per command **/ void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors) { unsigned int max_sectors; if (WARN_ON(!blk_queue_is_zoned(q))) return; max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors); max_sectors = min(q->limits.chunk_sectors, max_sectors); /* * Signal eventual driver bugs resulting in the max_zone_append sectors limit * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set, * or the max_hw_sectors limit not set. */ WARN_ON(!max_sectors); q->limits.max_zone_append_sectors = max_sectors; } EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors); /** * blk_queue_max_segments - set max hw segments for a request for this queue * @q: the request queue for the device * @max_segments: max number of segments * * Description: * Enables a low level driver to set an upper limit on the number of * hw data segments in a request. **/ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments) { if (!max_segments) { max_segments = 1; printk(KERN_INFO "%s: set to minimum %d\n", __func__, max_segments); } q->limits.max_segments = max_segments; } EXPORT_SYMBOL(blk_queue_max_segments); /** * blk_queue_max_discard_segments - set max segments for discard requests * @q: the request queue for the device * @max_segments: max number of segments * * Description: * Enables a low level driver to set an upper limit on the number of * segments in a discard request. **/ void blk_queue_max_discard_segments(struct request_queue *q, unsigned short max_segments) { q->limits.max_discard_segments = max_segments; } EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments); /** * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg * @q: the request queue for the device * @max_size: max size of segment in bytes * * Description: * Enables a low level driver to set an upper limit on the size of a * coalesced segment **/ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size) { if (max_size < PAGE_SIZE) { max_size = PAGE_SIZE; printk(KERN_INFO "%s: set to minimum %d\n", __func__, max_size); } /* see blk_queue_virt_boundary() for the explanation */ WARN_ON_ONCE(q->limits.virt_boundary_mask); q->limits.max_segment_size = max_size; } EXPORT_SYMBOL(blk_queue_max_segment_size); /** * blk_queue_logical_block_size - set logical block size for the queue * @q: the request queue for the device * @size: the logical block size, in bytes * * Description: * This should be set to the lowest possible block size that the * storage device can address. The default of 512 covers most * hardware. **/ void blk_queue_logical_block_size(struct request_queue *q, unsigned int size) { q->limits.logical_block_size = size; if (q->limits.physical_block_size < size) q->limits.physical_block_size = size; if (q->limits.io_min < q->limits.physical_block_size) q->limits.io_min = q->limits.physical_block_size; } EXPORT_SYMBOL(blk_queue_logical_block_size); /** * blk_queue_physical_block_size - set physical block size for the queue * @q: the request queue for the device * @size: the physical block size, in bytes * * Description: * This should be set to the lowest possible sector size that the * hardware can operate on without reverting to read-modify-write * operations. */ void blk_queue_physical_block_size(struct request_queue *q, unsigned int size) { q->limits.physical_block_size = size; if (q->limits.physical_block_size < q->limits.logical_block_size) q->limits.physical_block_size = q->limits.logical_block_size; if (q->limits.io_min < q->limits.physical_block_size) q->limits.io_min = q->limits.physical_block_size; } EXPORT_SYMBOL(blk_queue_physical_block_size); /** * blk_queue_zone_write_granularity - set zone write granularity for the queue * @q: the request queue for the zoned device * @size: the zone write granularity size, in bytes * * Description: * This should be set to the lowest possible size allowing to write in * sequential zones of a zoned block device. */ void blk_queue_zone_write_granularity(struct request_queue *q, unsigned int size) { if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) return; q->limits.zone_write_granularity = size; if (q->limits.zone_write_granularity < q->limits.logical_block_size) q->limits.zone_write_granularity = q->limits.logical_block_size; } EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity); /** * blk_queue_alignment_offset - set physical block alignment offset * @q: the request queue for the device * @offset: alignment offset in bytes * * Description: * Some devices are naturally misaligned to compensate for things like * the legacy DOS partition table 63-sector offset. Low-level drivers * should call this function for devices whose first sector is not * naturally aligned. */ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) { q->limits.alignment_offset = offset & (q->limits.physical_block_size - 1); q->limits.misaligned = 0; } EXPORT_SYMBOL(blk_queue_alignment_offset); void blk_queue_update_readahead(struct request_queue *q) { /* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. */ q->backing_dev_info->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); q->backing_dev_info->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL_GPL(blk_queue_update_readahead); /** * blk_limits_io_min - set minimum request size for a device * @limits: the queue limits * @min: smallest I/O size in bytes * * Description: * Some devices have an internal block size bigger than the reported * hardware sector size. This function can be used to signal the * smallest I/O the device can perform without incurring a performance * penalty. */ void blk_limits_io_min(struct queue_limits *limits, unsigned int min) { limits->io_min = min; if (limits->io_min < limits->logical_block_size) limits->io_min = limits->logical_block_size; if (limits->io_min < limits->physical_block_size) limits->io_min = limits->physical_block_size; } EXPORT_SYMBOL(blk_limits_io_min); /** * blk_queue_io_min - set minimum request size for the queue * @q: the request queue for the device * @min: smallest I/O size in bytes * * Description: * Storage devices may report a granularity or preferred minimum I/O * size which is the smallest request the device can perform without * incurring a performance penalty. For disk drives this is often the * physical block size. For RAID arrays it is often the stripe chunk * size. A properly aligned multiple of minimum_io_size is the * preferred request size for workloads where a high number of I/O * operations is desired. */ void blk_queue_io_min(struct request_queue *q, unsigned int min) { blk_limits_io_min(&q->limits, min); } EXPORT_SYMBOL(blk_queue_io_min); /** * blk_limits_io_opt - set optimal request size for a device * @limits: the queue limits * @opt: smallest I/O size in bytes * * Description: * Storage devices may report an optimal I/O size, which is the * device's preferred unit for sustained I/O. This is rarely reported * for disk drives. For RAID arrays it is usually the stripe width or * the internal track size. A properly aligned multiple of * optimal_io_size is the preferred request size for workloads where * sustained throughput is desired. */ void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt) { limits->io_opt = opt; } EXPORT_SYMBOL(blk_limits_io_opt); /** * blk_queue_io_opt - set optimal request size for the queue * @q: the request queue for the device * @opt: optimal request size in bytes * * Description: * Storage devices may report an optimal I/O size, which is the * device's preferred unit for sustained I/O. This is rarely reported * for disk drives. For RAID arrays it is usually the stripe width or * the internal track size. A properly aligned multiple of * optimal_io_size is the preferred request size for workloads where * sustained throughput is desired. */ void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { blk_limits_io_opt(&q->limits, opt); q->backing_dev_info->ra_pages = max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); } EXPORT_SYMBOL(blk_queue_io_opt); static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs) { sectors = round_down(sectors, lbs >> SECTOR_SHIFT); if (sectors < PAGE_SIZE >> SECTOR_SHIFT) sectors = PAGE_SIZE >> SECTOR_SHIFT; return sectors; } /** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @b: the underlying queue limits (bottom, component device) * @start: first data sector within component device * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment. * * Returns 0 if the top and bottom queue_limits are compatible. The * top device's block sizes and alignment offsets may be adjusted to * ensure alignment with the bottom device. If no compatible sizes * and alignments exist, -1 is returned and the resulting top * queue_limits will have the misaligned flag set to indicate that * the alignment_offset is undefined. */ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t start) { unsigned int top, bottom, alignment; int ret = 0; t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors); t->max_write_same_sectors = min(t->max_write_same_sectors, b->max_write_same_sectors); t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors, b->max_write_zeroes_sectors); t->max_zone_append_sectors = min(t->max_zone_append_sectors, b->max_zone_append_sectors); t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn); t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask); t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask, b->virt_boundary_mask); t->max_segments = min_not_zero(t->max_segments, b->max_segments); t->max_discard_segments = min_not_zero(t->max_discard_segments, b->max_discard_segments); t->max_integrity_segments = min_not_zero(t->max_integrity_segments, b->max_integrity_segments); t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); t->misaligned |= b->misaligned; alignment = queue_limit_alignment_offset(b, start); /* Bottom device has different alignment. Check that it is * compatible with the current top alignment. */ if (t->alignment_offset != alignment) { top = max(t->physical_block_size, t->io_min) + t->alignment_offset; bottom = max(b->physical_block_size, b->io_min) + alignment; /* Verify that top and bottom intervals line up */ if (max(top, bottom) % min(top, bottom)) { t->misaligned = 1; ret = -1; } } t->logical_block_size = max(t->logical_block_size, b->logical_block_size); t->physical_block_size = max(t->physical_block_size, b->physical_block_size); t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm_not_zero(t->io_opt, b->io_opt); /* Set non-power-of-2 compatible chunk_sectors boundary */ if (b->chunk_sectors) t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors); /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; t->misaligned = 1; ret = -1; } /* Minimum I/O a multiple of the physical block size? */ if (t->io_min & (t->physical_block_size - 1)) { t->io_min = t->physical_block_size; t->misaligned = 1; ret = -1; } /* Optimal I/O a multiple of the physical block size? */ if (t->io_opt & (t->physical_block_size - 1)) { t->io_opt = 0; t->misaligned = 1; ret = -1; } /* chunk_sectors a multiple of the physical block size? */ if (t->chunk_sectors % (t->physical_block_size >> SECTOR_SHIFT)) { t->chunk_sectors = 0; t->misaligned = 1; ret = -1; } t->raid_partial_stripes_expensive = max(t->raid_partial_stripes_expensive, b->raid_partial_stripes_expensive); /* Find lowest common alignment_offset */ t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment) % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { t->misaligned = 1; ret = -1; } t->max_sectors = blk_round_down_sectors(t->max_sectors, t->logical_block_size); t->max_hw_sectors = blk_round_down_sectors(t->max_hw_sectors, t->logical_block_size); t->max_dev_sectors = blk_round_down_sectors(t->max_dev_sectors, t->logical_block_size); /* Discard alignment and granularity */ if (b->discard_granularity) { alignment = queue_limit_discard_alignment(b, start); if (t->discard_granularity != 0 && t->discard_alignment != alignment) { top = t->discard_granularity + t->discard_alignment; bottom = b->discard_granularity + alignment; /* Verify that top and bottom intervals line up */ if ((max(top, bottom) % min(top, bottom)) != 0) t->discard_misaligned = 1; } t->max_discard_sectors = min_not_zero(t->max_discard_sectors, b->max_discard_sectors); t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors, b->max_hw_discard_sectors); t->discard_granularity = max(t->discard_granularity, b->discard_granularity); t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) % t->discard_granularity; } t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); if (!t->zoned) { t->zone_write_granularity = 0; t->max_zone_append_sectors = 0; } return ret; } EXPORT_SYMBOL(blk_stack_limits); /** * disk_stack_limits - adjust queue limits for stacked drivers * @disk: MD/DM gendisk (top) * @bdev: the underlying block device (bottom) * @offset: offset to beginning of data within component device * * Description: * Merges the limits for a top level gendisk and a bottom level * block_device. */ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset) { struct request_queue *t = disk->queue; if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits, get_start_sect(bdev) + (offset >> 9)) < 0) { char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE]; disk_name(disk, 0, top); bdevname(bdev, bottom); printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n", top, bottom); } blk_queue_update_readahead(disk->queue); } EXPORT_SYMBOL(disk_stack_limits); /** * blk_queue_update_dma_pad - update pad mask * @q: the request queue for the device * @mask: pad mask * * Update dma pad mask. * * Appending pad buffer to a request modifies the last entry of a * scatter list such that it includes the pad buffer. **/ void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask) { if (mask > q->dma_pad_mask) q->dma_pad_mask = mask; } EXPORT_SYMBOL(blk_queue_update_dma_pad); /** * blk_queue_segment_boundary - set boundary rules for segment merging * @q: the request queue for the device * @mask: the memory boundary mask **/ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask) { if (mask < PAGE_SIZE - 1) { mask = PAGE_SIZE - 1; printk(KERN_INFO "%s: set to minimum %lx\n", __func__, mask); } q->limits.seg_boundary_mask = mask; } EXPORT_SYMBOL(blk_queue_segment_boundary); /** * blk_queue_virt_boundary - set boundary rules for bio merging * @q: the request queue for the device * @mask: the memory boundary mask **/ void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask) { q->limits.virt_boundary_mask = mask; /* * Devices that require a virtual boundary do not support scatter/gather * I/O natively, but instead require a descriptor list entry for each * page (which might not be idential to the Linux PAGE_SIZE). Because * of that they are not limited by our notion of "segment size". */ if (mask) q->limits.max_segment_size = UINT_MAX; } EXPORT_SYMBOL(blk_queue_virt_boundary); /** * blk_queue_dma_alignment - set dma length and memory alignment * @q: the request queue for the device * @mask: alignment mask * * description: * set required memory and length alignment for direct dma transactions. * this is used when building direct io requests for the queue. * **/ void blk_queue_dma_alignment(struct request_queue *q, int mask) { q->dma_alignment = mask; } EXPORT_SYMBOL(blk_queue_dma_alignment); /** * blk_queue_update_dma_alignment - update dma length and memory alignment * @q: the request queue for the device * @mask: alignment mask * * description: * update required memory and length alignment for direct dma transactions. * If the requested alignment is larger than the current alignment, then * the current queue alignment is updated to the new value, otherwise it * is left alone. The design of this is to allow multiple objects * (driver, device, transport etc) to set their respective * alignments without having them interfere. * **/ void blk_queue_update_dma_alignment(struct request_queue *q, int mask) { BUG_ON(mask > PAGE_SIZE); if (mask > q->dma_alignment) q->dma_alignment = mask; } EXPORT_SYMBOL(blk_queue_update_dma_alignment); /** * blk_set_queue_depth - tell the block layer about the device queue depth * @q: the request queue for the device * @depth: queue depth * */ void blk_set_queue_depth(struct request_queue *q, unsigned int depth) { q->queue_depth = depth; rq_qos_queue_depth_changed(q); } EXPORT_SYMBOL(blk_set_queue_depth); /** * blk_queue_write_cache - configure queue's write cache * @q: the request queue for the device * @wc: write back cache on or off * @fua: device supports FUA writes, if true * * Tell the block layer about the write cache of @q. */ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) { if (wc) blk_queue_flag_set(QUEUE_FLAG_WC, q); else blk_queue_flag_clear(QUEUE_FLAG_WC, q); if (fua) blk_queue_flag_set(QUEUE_FLAG_FUA, q); else blk_queue_flag_clear(QUEUE_FLAG_FUA, q); wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); } EXPORT_SYMBOL_GPL(blk_queue_write_cache); /** * blk_queue_required_elevator_features - Set a queue required elevator features * @q: the request queue for the target device * @features: Required elevator features OR'ed together * * Tell the block layer that for the device controlled through @q, only the * only elevators that can be used are those that implement at least the set of * features specified by @features. */ void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features) { q->required_elevator_features = features; } EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features); /** * blk_queue_can_use_dma_map_merging - configure queue for merging segments. * @q: the request queue for the device * @dev: the device pointer for dma * * Tell the block layer about merging the segments by dma map of @q. */ bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev) { unsigned long boundary = dma_get_merge_boundary(dev); if (!boundary) return false; /* No need to update max_segment_size. see blk_queue_virt_boundary() */ blk_queue_virt_boundary(q, boundary); return true; } EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); /** * blk_queue_set_zoned - configure a disk queue zoned model. * @disk: the gendisk of the queue to configure * @model: the zoned model to set * * Set the zoned model of the request queue of @disk according to @model. * When @model is BLK_ZONED_HM (host managed), this should be called only * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option). * If @model specifies BLK_ZONED_HA (host aware), the effective model used * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions * on the disk. */ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) { struct request_queue *q = disk->queue; switch (model) { case BLK_ZONED_HM: /* * Host managed devices are supported only if * CONFIG_BLK_DEV_ZONED is enabled. */ WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)); break; case BLK_ZONED_HA: /* * Host aware devices can be treated either as regular block * devices (similar to drive managed devices) or as zoned block * devices to take advantage of the zone command set, similarly * to host managed devices. We try the latter if there are no * partitions and zoned block device support is enabled, else * we do nothing special as far as the block layer is concerned. */ if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || disk_has_partitions(disk)) model = BLK_ZONED_NONE; break; case BLK_ZONED_NONE: default: if (WARN_ON_ONCE(model != BLK_ZONED_NONE)) model = BLK_ZONED_NONE; break; } q->limits.zoned = model; if (model != BLK_ZONED_NONE) { /* * Set the zone write granularity to the device logical block * size by default. The driver can change this value if needed. */ blk_queue_zone_write_granularity(q, queue_logical_block_size(q)); } } EXPORT_SYMBOL_GPL(blk_queue_set_zoned); static int __init blk_settings_init(void) { blk_max_low_pfn = max_low_pfn - 1; blk_max_pfn = max_pfn - 1; return 0; } subsys_initcall(blk_settings_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 | // SPDX-License-Identifier: GPL-2.0 #include <linux/capability.h> #include <linux/compat.h> #include <linux/blkdev.h> #include <linux/export.h> #include <linux/gfp.h> #include <linux/blkpg.h> #include <linux/hdreg.h> #include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/blktrace_api.h> #include <linux/pr.h> #include <linux/uaccess.h> #include "blk.h" static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op) { struct blkpg_partition p; sector_t start, length; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) return -EFAULT; if (bdev_is_partition(bdev)) return -EINVAL; if (p.pno <= 0) return -EINVAL; if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(bdev, p.pno); if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start) return -EINVAL; /* Check that the partition is aligned to the block size */ if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) return -EINVAL; start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; /* check for fit in a hd_struct */ if (sizeof(sector_t) < sizeof(long long)) { long pstart = start, plength = length; if (pstart != start || plength != length || pstart < 0 || plength < 0 || p.pno > 65535) return -EINVAL; } switch (op) { case BLKPG_ADD_PARTITION: return bdev_add_partition(bdev, p.pno, start, length); case BLKPG_RESIZE_PARTITION: return bdev_resize_partition(bdev, p.pno, start, length); default: return -EINVAL; } } static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg) { struct blkpg_partition __user *udata; int op; if (get_user(op, &arg->op) || get_user(udata, &arg->data)) return -EFAULT; return blkpg_do_ioctl(bdev, udata, op); } #ifdef CONFIG_COMPAT struct compat_blkpg_ioctl_arg { compat_int_t op; compat_int_t flags; compat_int_t datalen; compat_caddr_t data; }; static int compat_blkpg_ioctl(struct block_device *bdev, struct compat_blkpg_ioctl_arg __user *arg) { compat_caddr_t udata; int op; if (get_user(op, &arg->op) || get_user(udata, &arg->data)) return -EFAULT; return blkpg_do_ioctl(bdev, compat_ptr(udata), op); } #endif static int blkdev_reread_part(struct block_device *bdev, fmode_t mode) { struct block_device *tmp; if (!disk_part_scan_enabled(bdev->bd_disk) || bdev_is_partition(bdev)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (bdev->bd_part_count) return -EBUSY; /* * Reopen the device to revalidate the driver state and force a * partition rescan. */ mode &= ~FMODE_EXCL; set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); tmp = blkdev_get_by_dev(bdev->bd_dev, mode, NULL); if (IS_ERR(tmp)) return PTR_ERR(tmp); blkdev_put(tmp, mode); return 0; } static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, unsigned long arg, unsigned long flags) { uint64_t range[2]; uint64_t start, len; struct request_queue *q = bdev_get_queue(bdev); int err; if (!(mode & FMODE_WRITE)) return -EBADF; if (!blk_queue_discard(q)) return -EOPNOTSUPP; if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; start = range[0]; len = range[1]; if (start & 511) return -EINVAL; if (len & 511) return -EINVAL; if (start + len > i_size_read(bdev->bd_inode)) return -EINVAL; err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) return err; return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, flags); } static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, unsigned long arg) { uint64_t range[2]; uint64_t start, end, len; int err; if (!(mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; start = range[0]; len = range[1]; end = start + len - 1; if (start & 511) return -EINVAL; if (len & 511) return -EINVAL; if (end >= (uint64_t)i_size_read(bdev->bd_inode)) return -EINVAL; if (end < start) return -EINVAL; /* Invalidate the page cache, including dirty pages */ err = truncate_bdev_range(bdev, mode, start, end); if (err) return err; return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); } static int put_ushort(unsigned short __user *argp, unsigned short val) { return put_user(val, argp); } static int put_int(int __user *argp, int val) { return put_user(val, argp); } static int put_uint(unsigned int __user *argp, unsigned int val) { return put_user(val, argp); } static int put_long(long __user *argp, long val) { return put_user(val, argp); } static int put_ulong(unsigned long __user *argp, unsigned long val) { return put_user(val, argp); } static int put_u64(u64 __user *argp, u64 val) { return put_user(val, argp); } #ifdef CONFIG_COMPAT static int compat_put_long(compat_long_t __user *argp, long val) { return put_user(val, argp); } static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) { return put_user(val, argp); } #endif int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; if (disk->fops->ioctl) return disk->fops->ioctl(bdev, mode, cmd, arg); return -ENOTTY; } /* * For the record: _GPL here is only because somebody decided to slap it * on the previous export. Sheer idiocy, since it wasn't copyrightable * at all and could be open-coded without any exports by anybody who cares. */ EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); #ifdef CONFIG_COMPAT /* * This is the equivalent of compat_ptr_ioctl(), to be used by block * drivers that implement only commands that are completely compatible * between 32-bit and 64-bit user space */ int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; if (disk->fops->ioctl) return disk->fops->ioctl(bdev, mode, cmd, (unsigned long)compat_ptr(arg)); return -ENOIOCTLCMD; } EXPORT_SYMBOL(blkdev_compat_ptr_ioctl); #endif static int blkdev_pr_register(struct block_device *bdev, struct pr_registration __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_registration reg; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!ops || !ops->pr_register) return -EOPNOTSUPP; if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (reg.flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags); } static int blkdev_pr_reserve(struct block_device *bdev, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!ops || !ops->pr_reserve) return -EOPNOTSUPP; if (copy_from_user(&rsv, arg, sizeof(rsv))) return -EFAULT; if (rsv.flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags); } static int blkdev_pr_release(struct block_device *bdev, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!ops || !ops->pr_release) return -EOPNOTSUPP; if (copy_from_user(&rsv, arg, sizeof(rsv))) return -EFAULT; if (rsv.flags) return -EOPNOTSUPP; return ops->pr_release(bdev, rsv.key, rsv.type); } static int blkdev_pr_preempt(struct block_device *bdev, struct pr_preempt __user *arg, bool abort) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_preempt p; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!ops || !ops->pr_preempt) return -EOPNOTSUPP; if (copy_from_user(&p, arg, sizeof(p))) return -EFAULT; if (p.flags) return -EOPNOTSUPP; return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort); } static int blkdev_pr_clear(struct block_device *bdev, struct pr_clear __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_clear c; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!ops || !ops->pr_clear) return -EOPNOTSUPP; if (copy_from_user(&c, arg, sizeof(c))) return -EFAULT; if (c.flags) return -EOPNOTSUPP; return ops->pr_clear(bdev, c.key); } /* * Is it an unrecognized ioctl? The correct returns are either * ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a * fallback"). ENOIOCTLCMD gets turned into ENOTTY by the ioctl * code before returning. * * Confused drivers sometimes return EINVAL, which is wrong. It * means "I understood the ioctl command, but the parameters to * it were wrong". * * We should aim to just fix the broken drivers, the EINVAL case * should go away. */ static inline int is_unrecognized_ioctl(int ret) { return ret == -EINVAL || ret == -ENOTTY || ret == -ENOIOCTLCMD; } static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { int ret; if (!capable(CAP_SYS_ADMIN)) return -EACCES; ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); if (!is_unrecognized_ioctl(ret)) return ret; fsync_bdev(bdev); invalidate_bdev(bdev); return 0; } static int blkdev_roset(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { int ret, n; if (!capable(CAP_SYS_ADMIN)) return -EACCES; ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); if (!is_unrecognized_ioctl(ret)) return ret; if (get_user(n, (int __user *)arg)) return -EFAULT; if (bdev->bd_disk->fops->set_read_only) { ret = bdev->bd_disk->fops->set_read_only(bdev, n); if (ret) return ret; } set_device_ro(bdev, n); return 0; } static int blkdev_getgeo(struct block_device *bdev, struct hd_geometry __user *argp) { struct gendisk *disk = bdev->bd_disk; struct hd_geometry geo; int ret; if (!argp) return -EINVAL; if (!disk->fops->getgeo) return -ENOTTY; /* * We need to set the startsect first, the driver may * want to override it. */ memset(&geo, 0, sizeof(geo)); geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(bdev, &geo); if (ret) return ret; if (copy_to_user(argp, &geo, sizeof(geo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_hd_geometry { unsigned char heads; unsigned char sectors; unsigned short cylinders; u32 start; }; static int compat_hdio_getgeo(struct block_device *bdev, struct compat_hd_geometry __user *ugeo) { struct gendisk *disk = bdev->bd_disk; struct hd_geometry geo; int ret; if (!ugeo) return -EINVAL; if (!disk->fops->getgeo) return -ENOTTY; memset(&geo, 0, sizeof(geo)); /* * We need to set the startsect first, the driver may * want to override it. */ geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(bdev, &geo); if (ret) return ret; ret = copy_to_user(ugeo, &geo, 4); ret |= put_user(geo.start, &ugeo->start); if (ret) ret = -EFAULT; return ret; } #endif /* set the logical block size */ static int blkdev_bszset(struct block_device *bdev, fmode_t mode, int __user *argp) { int ret, n; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (!argp) return -EINVAL; if (get_user(n, argp)) return -EFAULT; if (mode & FMODE_EXCL) return set_blocksize(bdev, n); if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev))) return -EBUSY; ret = set_blocksize(bdev, n); blkdev_put(bdev, mode | FMODE_EXCL); return ret; } /* * Common commands that are handled the same way on native and compat * user space. Note the separate arg/argp parameters that are needed * to deal with the compat_ptr() conversion. */ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg, void __user *argp) { unsigned int max_sectors; switch (cmd) { case BLKFLSBUF: return blkdev_flushbuf(bdev, mode, cmd, arg); case BLKROSET: return blkdev_roset(bdev, mode, cmd, arg); case BLKDISCARD: return blk_ioctl_discard(bdev, mode, arg, 0); case BLKSECDISCARD: return blk_ioctl_discard(bdev, mode, arg, BLKDEV_DISCARD_SECURE); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); case BLKREPORTZONE: return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); case BLKRESETZONE: case BLKOPENZONE: case BLKCLOSEZONE: case BLKFINISHZONE: return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg); case BLKGETZONESZ: return put_uint(argp, bdev_zone_sectors(bdev)); case BLKGETNRZONES: return put_uint(argp, blkdev_nr_zones(bdev->bd_disk)); case BLKROGET: return put_int(argp, bdev_read_only(bdev) != 0); case BLKSSZGET: /* get block device logical block size */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKPBSZGET: /* get block device physical block size */ return put_uint(argp, bdev_physical_block_size(bdev)); case BLKIOMIN: return put_uint(argp, bdev_io_min(bdev)); case BLKIOOPT: return put_uint(argp, bdev_io_opt(bdev)); case BLKALIGNOFF: return put_int(argp, bdev_alignment_offset(bdev)); case BLKDISCARDZEROES: return put_uint(argp, 0); case BLKSECTGET: max_sectors = min_t(unsigned int, USHRT_MAX, queue_max_sectors(bdev_get_queue(bdev))); return put_ushort(argp, max_sectors); case BLKROTATIONAL: return put_ushort(argp, !blk_queue_nonrot(bdev_get_queue(bdev))); case BLKRASET: case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) return -EACCES; bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKRRPART: return blkdev_reread_part(bdev, mode); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); case IOC_PR_REGISTER: return blkdev_pr_register(bdev, argp); case IOC_PR_RESERVE: return blkdev_pr_reserve(bdev, argp); case IOC_PR_RELEASE: return blkdev_pr_release(bdev, argp); case IOC_PR_PREEMPT: return blkdev_pr_preempt(bdev, argp, false); case IOC_PR_PREEMPT_ABORT: return blkdev_pr_preempt(bdev, argp, true); case IOC_PR_CLEAR: return blkdev_pr_clear(bdev, argp); default: return -ENOIOCTLCMD; } } /* * Always keep this in sync with compat_blkdev_ioctl() * to handle all incompatible commands in both functions. * * New commands must be compatible and go into blkdev_common_ioctl */ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { int ret; loff_t size; void __user *argp = (void __user *)arg; switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKPG: return blkpg_ioctl(bdev, argp); /* Compat mode returns 32-bit data instead of 'long' */ case BLKRAGET: case BLKFRAGET: if (!argp) return -EINVAL; return put_long(argp, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) return -EFBIG; return put_ulong(argp, size >> 9); /* The data is compatible, but the command number is different */ case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(argp, block_size(bdev)); case BLKBSZSET: return blkdev_bszset(bdev, mode, argp); case BLKGETSIZE64: return put_u64(argp, i_size_read(bdev->bd_inode)); /* Incompatible alignment on i386 */ case BLKTRACESETUP: return blk_trace_ioctl(bdev, cmd, argp); default: break; } ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); if (ret == -ENOIOCTLCMD) return __blkdev_driver_ioctl(bdev, mode, cmd, arg); return ret; } EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */ #ifdef CONFIG_COMPAT #define BLKBSZGET_32 _IOR(0x12, 112, int) #define BLKBSZSET_32 _IOW(0x12, 113, int) #define BLKGETSIZE64_32 _IOR(0x12, 114, int) /* Most of the generic ioctls are handled in the normal fallback path. This assumes the blkdev's low level compat_ioctl always returns ENOIOCTLCMD for unknown ioctls. */ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret; void __user *argp = compat_ptr(arg); struct inode *inode = file->f_mapping->host; struct block_device *bdev = inode->i_bdev; struct gendisk *disk = bdev->bd_disk; fmode_t mode = file->f_mode; loff_t size; /* * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have * to updated it before every ioctl. */ if (file->f_flags & O_NDELAY) mode |= FMODE_NDELAY; else mode &= ~FMODE_NDELAY; switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: return compat_hdio_getgeo(bdev, argp); case BLKPG: return compat_blkpg_ioctl(bdev, argp); /* Compat mode returns 32-bit data instead of 'long' */ case BLKRAGET: case BLKFRAGET: if (!argp) return -EINVAL; return compat_put_long(argp, (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, size >> 9); /* The data is compatible, but the command number is different */ case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKBSZSET_32: return blkdev_bszset(bdev, mode, argp); case BLKGETSIZE64_32: return put_u64(argp, i_size_read(bdev->bd_inode)); /* Incompatible alignment on i386 */ case BLKTRACESETUP32: return blk_trace_ioctl(bdev, cmd, argp); default: break; } ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl) ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg); return ret; } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/backing-dev.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); static u64 bdi_id_cursor; static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> static struct dentry *bdi_debug_root; static void bdi_debug_init(void) { bdi_debug_root = debugfs_create_dir("bdi", NULL); } static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; struct bdi_writeback *wb = &bdi->wb; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long wb_thresh; unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; struct inode *inode; nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode->i_state & I_DIRTY_TIME) nr_dirty_time++; spin_unlock(&wb->list_lock); global_dirty_limits(&background_thresh, &dirty_thresh); wb_thresh = wb_calc_thresh(wb, dirty_thresh); #define K(x) ((x) << (PAGE_SHIFT - 10)) seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", (unsigned long) K(wb_stat(wb, WB_WRITEBACK)), (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)), K(wb_thresh), K(dirty_thresh), K(background_thresh), (unsigned long) K(wb_stat(wb, WB_DIRTIED)), (unsigned long) K(wb_stat(wb, WB_WRITTEN)), (unsigned long) K(wb->write_bandwidth), nr_dirty, nr_io, nr_more_io, nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); #undef K return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } #else static inline void bdi_debug_init(void) { } static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } #endif static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret; ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret; bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); return count; } #define K(pages) ((pages) << (PAGE_SHIFT - 10)) #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *page) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio, bdi->max_ratio) static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *page) { dev_warn_once(dev, "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); return snprintf(page, PAGE_SIZE-1, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_max_ratio.attr, &dev_attr_stable_pages_required.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); static __init int bdi_class_init(void) { bdi_class = class_create(THIS_MODULE, "bdi"); if (IS_ERR(bdi_class)) return PTR_ERR(bdi_class); bdi_class->dev_groups = bdi_dev_groups; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); static int bdi_init(struct backing_dev_info *bdi); static int __init default_bdi_init(void) { int err; bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; err = bdi_init(&noop_backing_dev_info); return err; } subsys_initcall(default_bdi_init); /* * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just * set up a timer which wakes the bdi thread up later. * * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. * * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->dwork, timeout); spin_unlock_bh(&wb->work_lock); } /* * Initial write bandwidth: 100 MB/s */ #define INIT_BW (100 << (20 - PAGE_SHIFT)) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { int i, err; memset(wb, 0, sizeof(*wb)); if (wb != &bdi->wb) bdi_get(bdi); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; wb->write_bandwidth = INIT_BW; wb->avg_write_bandwidth = INIT_BW; spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); wb->dirty_sleep = jiffies; err = fprop_local_init_percpu(&wb->completions, gfp); if (err) goto out_put_bdi; for (i = 0; i < NR_WB_STAT_ITEMS; i++) { err = percpu_counter_init(&wb->stat[i], 0, gfp); if (err) goto out_destroy_stat; } return 0; out_destroy_stat: while (i--) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); out_put_bdi: if (wb != &bdi->wb) bdi_put(bdi); return err; } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); /* * Remove bdi from the global list and shutdown any threads we have running */ static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ spin_lock_bh(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_bh(&wb->work_lock); return; } spin_unlock_bh(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to * be drained no matter what. */ mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); } static void wb_exit(struct bdi_writeback *wb) { int i; WARN_ON(delayed_work_pending(&wb->dwork)); for (i = 0; i < NR_WB_STAT_ITEMS; i++) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); if (wb != &wb->bdi->wb) bdi_put(wb->bdi); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/memcontrol.h> /* * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list. * bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; static void cgwb_free_rcu(struct rcu_head *rcu_head) { struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu); percpu_ref_exit(&wb->refcnt); kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ blkcg_unpin_online(blkcg); fprop_local_destroy_percpu(&wb->memcg_completions); wb_exit(wb); call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) { lockdep_assert_held(&cgwb_lock); WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); percpu_ref_kill(&wb->refcnt); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock); } static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; struct blkcg *blkcg; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; int ret = 0; memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); blkcg = css_to_blkcg(blkcg_css); memcg_cgwb_list = &memcg->cgwb_list; blkcg_cgwb_list = &blkcg->cgwb_list; /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb && wb->blkcg_css != blkcg_css) { cgwb_kill(wb); wb = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); if (wb) goto out_put; /* need to create a new one */ wb = kmalloc(sizeof(*wb), gfp); if (!wb) { ret = -ENOMEM; goto out_put; } ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); if (ret) goto err_wb_exit; ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); if (ret) goto err_ref_exit; wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); /* * The root wb determines the registered state of the whole bdi and * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate * whether they're still online. Don't link @wb if any is dead. * See wb_memcg_offline() and wb_blkcg_offline(). */ ret = -ENODEV; spin_lock_irqsave(&cgwb_lock, flags); if (test_bit(WB_registered, &bdi->wb.state) && blkcg_cgwb_list->next && memcg_cgwb_list->next) { /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); blkcg_pin_online(blkcg); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put; err_fprop_exit: fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); err_wb_exit: wb_exit(wb); err_free: kfree(wb); out_put: css_put(blkcg_css); return ret; } /** * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * * Try to get the wb for @memcg_css on @bdi. The returned wb has its * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on * @memcg_css isn't enough. try_get it before calling this function. * * A wb is keyed by its associated memcg. As blkcg implicitly enables * memcg on the default hierarchy, memcg association is guaranteed to be * more specific (equal or descendant to the associated blkcg) and thus can * identify both the memcg and blkcg associations. * * Because the blkcg associated with a memcg may change as blkcg is enabled * and disabled closer to root in the hierarchy, each wb keeps track of * both the memcg and blkcg associated with it and verifies the blkcg on * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css) { struct bdi_writeback *wb; if (!memcg_css->parent) return &bdi->wb; rcu_read_lock(); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb) { struct cgroup_subsys_state *blkcg_css; /* see whether the blkcg association has changed */ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) wb = NULL; css_put(blkcg_css); } rcu_read_unlock(); return wb; } /** * wb_get_create - get wb for a given memcg, create if necessary * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * @gfp: allocation mask to use * * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to * create one. See wb_get_lookup() for more details. */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; might_sleep_if(gfpflags_allow_blocking(gfp)); if (!memcg_css->parent) return &bdi->wb; do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; } static int cgwb_bdi_init(struct backing_dev_info *bdi) { int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; } return ret; } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); spin_unlock_irq(&cgwb_lock); mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); mutex_unlock(&bdi->cgwb_release_mutex); } /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined * * Also prevents creation of any new wb's associated with @memcg. */ void wb_memcg_offline(struct mem_cgroup *memcg) { struct list_head *memcg_cgwb_list = &memcg->cgwb_list; struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @blkcg: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ void wb_blkcg_offline(struct blkcg *blkcg) { struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) cgwb_kill(wb); blkcg->cgwb_list.next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock); } static int __init cgwb_init(void) { /* * There can be many concurrent release work items overwhelming * system_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); if (!cgwb_release_wq) return -ENOMEM; return 0; } subsys_initcall(cgwb_init); #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) { return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { list_del_rcu(&wb->bdi_node); } #endif /* CONFIG_CGROUP_WRITEBACK */ static int bdi_init(struct backing_dev_info *bdi) { int ret; bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); ret = cgwb_bdi_init(bdi); return ret; } struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; return bdi; } EXPORT_SYMBOL(bdi_alloc); static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) { struct rb_node **p = &bdi_tree.rb_node; struct rb_node *parent = NULL; struct backing_dev_info *bdi; lockdep_assert_held(&bdi_lock); while (*p) { parent = *p; bdi = rb_entry(parent, struct backing_dev_info, rb_node); if (bdi->id > id) p = &(*p)->rb_left; else if (bdi->id < id) p = &(*p)->rb_right; else break; } if (parentp) *parentp = parent; return p; } /** * bdi_get_by_id - lookup and get bdi from its id * @id: bdi id to lookup * * Find bdi matching @id and get it. Returns NULL if the matching bdi * doesn't exist or is already unregistered. */ struct backing_dev_info *bdi_get_by_id(u64 id) { struct backing_dev_info *bdi = NULL; struct rb_node **p; spin_lock_bh(&bdi_lock); p = bdi_lookup_rb_node(id, NULL); if (*p) { bdi = rb_entry(*p, struct backing_dev_info, rb_node); bdi_get(bdi); } spin_unlock_bh(&bdi_lock); return bdi; } int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); bdi->id = ++bdi_id_cursor; p = bdi_lookup_rb_node(bdi->id, &parent); rb_link_node(&bdi->rb_node, parent, p); rb_insert_color(&bdi->rb_node, &bdi_tree); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL(bdi_register); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); } /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); } void bdi_unregister(struct backing_dev_info *bdi) { /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); /* * If this BDI's min ratio has been set, use bdi_set_min_ratio() to * update the global bdi_min_ratio. */ if (bdi->min_ratio) bdi_set_min_ratio(bdi, 0); if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; } if (bdi->owner) { put_device(bdi->owner); bdi->owner = NULL; } } static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); if (test_bit(WB_registered, &bdi->wb.state)) bdi_unregister(bdi); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); } void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } EXPORT_SYMBOL(bdi_put); const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name; } EXPORT_SYMBOL_GPL(bdi_dev_name); static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; static atomic_t nr_wb_congested[2]; void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { wait_queue_head_t *wqh = &congestion_wqh[sync]; enum wb_congested_state bit; bit = sync ? WB_sync_congested : WB_async_congested; if (test_and_clear_bit(bit, &bdi->wb.congested)) atomic_dec(&nr_wb_congested[sync]); smp_mb__after_atomic(); if (waitqueue_active(wqh)) wake_up(wqh); } EXPORT_SYMBOL(clear_bdi_congested); void set_bdi_congested(struct backing_dev_info *bdi, int sync) { enum wb_congested_state bit; bit = sync ? WB_sync_congested : WB_async_congested; if (!test_and_set_bit(bit, &bdi->wb.congested)) atomic_inc(&nr_wb_congested[sync]); } EXPORT_SYMBOL(set_bdi_congested); /** * congestion_wait - wait for a backing_dev to become uncongested * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit * write congestion. If no backing_devs are congested then just wait for the * next write to be completed. */ long congestion_wait(int sync, long timeout) { long ret; unsigned long start = jiffies; DEFINE_WAIT(wait); wait_queue_head_t *wqh = &congestion_wqh[sync]; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = io_schedule_timeout(timeout); finish_wait(wqh, &wait); trace_writeback_congestion_wait(jiffies_to_usecs(timeout), jiffies_to_usecs(jiffies - start)); return ret; } EXPORT_SYMBOL(congestion_wait); /** * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * In the event of a congested backing_dev (any backing_dev) this waits * for up to @timeout jiffies for either a BDI to exit congestion of the * given @sync queue or a write to complete. * * The return value is 0 if the sleep is for the full timeout. Otherwise, * it is the number of jiffies that were still remaining when the function * returned. return_value == timeout implies the function did not sleep. */ long wait_iff_congested(int sync, long timeout) { long ret; unsigned long start = jiffies; DEFINE_WAIT(wait); wait_queue_head_t *wqh = &congestion_wqh[sync]; /* * If there is no congestion, yield if necessary instead * of sleeping on the congestion queue */ if (atomic_read(&nr_wb_congested[sync]) == 0) { cond_resched(); /* In case we scheduled, work out time remaining */ ret = timeout - (jiffies - start); if (ret < 0) ret = 0; goto out; } /* Sleep until uncongested or a write happens */ prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = io_schedule_timeout(timeout); finish_wait(wqh, &wait); out: trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), jiffies_to_usecs(jiffies - start)); return ret; } EXPORT_SYMBOL(wait_iff_congested); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_INVALID, }; extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_getcwd(void); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_getcwd(void) { if (unlikely(audit_context())) __audit_getcwd(); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(unsigned int response) { if (!audit_dummy_context()) __audit_fanotify(response); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_getcwd(void) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(unsigned int response) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Generic socket support routines. Memory allocators, socket lock/release * handler for protocols to use and generic option handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Fixes: * Alan Cox : Numerous verify_area() problems * Alan Cox : Connecting on a connecting socket * now returns an error for tcp. * Alan Cox : sock->protocol is set correctly. * and is not sometimes left as 0. * Alan Cox : connect handles icmp errors on a * connect properly. Unfortunately there * is a restart syscall nasty there. I * can't match BSD without hacking the C * library. Ideas urgently sought! * Alan Cox : Disallow bind() to addresses that are * not ours - especially broadcast ones!! * Alan Cox : Socket 1024 _IS_ ok for users. (fencepost) * Alan Cox : sock_wfree/sock_rfree don't destroy sockets, * instead they leave that for the DESTROY timer. * Alan Cox : Clean up error flag in accept * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. * Alan Cox : Added zapped flag for TCP * Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code * Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb * Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources * Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing. * Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so... * Rick Sladkey : Relaxed UDP rules for matching packets. * C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support * Pauline Middelink : identd support * Alan Cox : Fixed connect() taking signals I think. * Alan Cox : SO_LINGER supported * Alan Cox : Error reporting fixes * Anonymous : inet_create tidied up (sk->reuse setting) * Alan Cox : inet sockets don't set sk->type! * Alan Cox : Split socket option code * Alan Cox : Callbacks * Alan Cox : Nagle flag for Charles & Johannes stuff * Alex : Removed restriction on inet fioctl * Alan Cox : Splitting INET from NET core * Alan Cox : Fixed bogus SO_TYPE handling in getsockopt() * Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code * Alan Cox : Split IP from generic code * Alan Cox : New kfree_skbmem() * Alan Cox : Make SO_DEBUG superuser only. * Alan Cox : Allow anyone to clear SO_DEBUG * (compatibility fix) * Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput. * Alan Cox : Allocator for a socket is settable. * Alan Cox : SO_ERROR includes soft errors. * Alan Cox : Allow NULL arguments on some SO_ opts * Alan Cox : Generic socket allocation to make hooks * easier (suggested by Craig Metz). * Michael Pall : SO_ERROR returns positive errno again * Steve Whitehouse: Added default destructor to free * protocol private data. * Steve Whitehouse: Added various other default routines * common to several socket families. * Chris Evans : Call suser() check last on F_SETOWN * Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER. * Andi Kleen : Add sock_kmalloc()/sock_kfree_s() * Andi Kleen : Fix write_space callback * Chris Evans : Security fixes - signedness again * Arnaldo C. Melo : cleanups, use skb_queue_purge * * To Fix: */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> #include <net/netprio_cgroup.h> #include <linux/sock_diag.h> #include <linux/filter.h> #include <net/sock_reuseport.h> #include <net/bpf_sk_storage.h> #include <trace/events/sock.h> #include <net/tcp.h> #include <net/busy_poll.h> static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); static void sock_inuse_add(struct net *net, int val); /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in the user * namespace @user_ns. */ bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap) { return file_ns_capable(sk->sk_socket->file, user_ns, cap) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user * namespaces. */ bool sk_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, &init_user_ns, cap); } EXPORT_SYMBOL(sk_capable); /** * sk_net_capable - Network namespace socket capability test * @sk: Socket to use a capability on or through * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ bool sk_net_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); } EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have * one slock key per address family and separate keys for internal and * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ #define _sock_locks(x) \ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ x "27" , x "28" , x "AF_CAN" , \ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { _sock_locks("clock-") }; static const char *const af_family_kern_key_strings[AF_MAX+1] = { _sock_locks("k-sk_lock-") }; static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { _sock_locks("k-slock-") }; static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { _sock_locks("elock-") }; /* * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; static struct lock_class_key af_rlock_keys[AF_MAX]; static struct lock_class_key af_wlock_keys[AF_MAX]; static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); int sysctl_tstamp_allow_data __read_mostly = 1; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC * @sk: socket to set it on * * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. * It's the responsibility of the admin to adjust min_free_kbytes * to meet the requirements */ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward * progress of swapping. SOCK_MEMALLOC may be cleared while * it has rmem allocations due to the last swapfile being deactivated * but there is a risk that the socket is unusable due to exceeding * the rmem limits. Reclaim the reserves and obey rmem limits again. */ sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); ret = sk->sk_backlog_rcv(sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; tv.tv_usec = 0; } else { tv.tv_sec = timeo / HZ; tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); } if (old_timeval) { struct __kernel_old_timeval old_tv; old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; return sizeof(old_tv); } *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; tv.tv_sec = tv32.tv_sec; tv.tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; tv.tv_sec = old_tv.tv_sec; tv.tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(tv)) return -EINVAL; if (copy_from_sockptr(&tv, optval, sizeof(tv))) return -EFAULT; } if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; *timeo_p = 0; if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", __func__, current->comm, task_pid_nr(current)); } return 0; } *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); return 0; } static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { case AF_UNSPEC: case AF_UNIX: return false; default: return true; } } static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; if (sock_needs_netstamp(sk) && !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } skb->dev = NULL; skb_set_owner_r(skb, sk); /* we escape from rcu protected region, make sure we dont leak * a norefcounted dst */ skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(__sock_queue_rcv_skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; err = sk_filter(sk, skb); if (err) return err; return __sock_queue_rcv_skb(sk, skb); } EXPORT_SYMBOL(sock_queue_rcv_skb); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } if (nested) bh_lock_sock_nested(sk); else bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* * trylock + unlock semantics: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; } bh_unlock_sock(sk); out: if (refcounted) sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); goto out; } EXPORT_SYMBOL(__sk_receive_skb); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(__sk_dst_check); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(sk_dst_check); static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); /* Sorry... */ ret = -EPERM; if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; sk->sk_bound_dev_if = ifindex; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); ret = 0; out: #endif return ret; } int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) { int ret; if (lock_sk) lock_sock(sk); ret = sock_bindtoindex_locked(sk, ifindex); if (lock_sk) release_sock(sk); return ret; } EXPORT_SYMBOL(sock_bindtoindex); static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; ret = -EINVAL; if (optlen < 0) goto out; /* Bind this socket to a particular device like "eth0", * as specified in the passed interface name. If the * name is "" or the option length is zero the socket * is not bound. */ if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); ret = -EFAULT; if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; if (devname[0] != '\0') { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, devname); if (dev) index = dev->ifindex; rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; } return sock_bindtoindex(sk, index, true); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (sk->sk_bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(struct sock *sk) { if (dev_recursion_level()) return false; if (!sk) return true; /* IPV6_ADDRFORM can change sk->sk_family under us. */ switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_sk(sk)->mc_loop; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; #endif } WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); void sock_set_reuseaddr(struct sock *sk) { lock_sock(sk); sk->sk_reuse = SK_CAN_REUSE; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseaddr); void sock_set_reuseport(struct sock *sk) { lock_sock(sk); sk->sk_reuseport = true; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseport); void sock_no_linger(struct sock *sk) { lock_sock(sk); sk->sk_lingertime = 0; sock_set_flag(sk, SOCK_LINGER); release_sock(sk); } EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); sk->sk_priority = priority; release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) sk->sk_sndtimeo = secs * HZ; else sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) { if (val) { sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns); sock_set_flag(sk, SOCK_RCVTSTAMP); sock_enable_timestamp(sk, SOCK_TIMESTAMP); } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); } } void sock_enable_timestamps(struct sock *sk) { lock_sock(sk); __sock_set_timestamps(sk, true, false, true); release_sock(sk); } EXPORT_SYMBOL(sock_enable_timestamps); void sock_set_keepalive(struct sock *sk) { lock_sock(sk); if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, true); sock_valbool_flag(sk, SOCK_KEEPOPEN, true); release_sock(sk); } EXPORT_SYMBOL(sock_set_keepalive); static void __sock_set_rcvbuf(struct sock *sk, int val) { /* Ensure val * 2 fits into an int, to prevent max_t() from treating it * as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* We double it on the way in to account for "struct sk_buff" etc. * overhead. Applications assume that the SO_RCVBUF setting they make * will allow that much actual data to be received on that socket. * * Applications are unaware that "struct sk_buff" and other overheads * allocate from the receive buffer during socket buffer allocation. * * And after considering the possible alternatives, returning the value * we actually used in getsockopt is the most desirable behavior. */ WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); } void sock_set_rcvbuf(struct sock *sk, int val) { lock_sock(sk); __sock_set_rcvbuf(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { sk->sk_mark = val; sk_dst_reset(sk); } } void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; int valbool; struct linger ling; int ret = 0; /* * Options without arguments */ if (optname == SO_BINDTODEVICE) return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; lock_sock(sk); switch (optname) { case SO_DEBUG: if (val && !capable(CAP_NET_ADMIN)) ret = -EACCES; else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: sk->sk_reuseport = valbool; break; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: case SO_ERROR: ret = -ENOPROTOOPT; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool); break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; case SO_SNDBUFFORCE: if (!capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ if (val < 0) val = 0; goto set_sndbuf; case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: if (!capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ __sock_set_rcvbuf(sk, max(val, 0)); break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; case SO_OOBINLINE: sock_valbool_flag(sk, SOCK_URGINLINE, valbool); break; case SO_NO_CHECK: sk->sk_no_check_tx = valbool; break; case SO_PRIORITY: if ((val >= 0 && val <= 6) || ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; break; case SO_LINGER: if (optlen < sizeof(ling)) { ret = -EINVAL; /* 1003.1g */ break; } if (copy_from_sockptr(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } if (!ling.l_onoff) sock_reset_flag(sk, SOCK_LINGER); else { #if (BITS_PER_LONG == 32) if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; else #endif sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; sock_set_flag(sk, SOCK_LINGER); } break; case SO_BSDCOMPAT: break; case SO_PASSCRED: if (valbool) set_bit(SOCK_PASSCRED, &sock->flags); else clear_bit(SOCK_PASSCRED, &sock->flags); break; case SO_TIMESTAMP_OLD: __sock_set_timestamps(sk, valbool, false, false); break; case SO_TIMESTAMP_NEW: __sock_set_timestamps(sk, valbool, true, false); break; case SO_TIMESTAMPNS_OLD: __sock_set_timestamps(sk, valbool, false, true); break; case SO_TIMESTAMPNS_NEW: __sock_set_timestamps(sk, valbool, true, true); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; break; } if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) { ret = -EINVAL; break; } sk->sk_tskey = tcp_sk(sk)->snd_una; } else { sk->sk_tskey = 0; } } if (val & SOF_TIMESTAMPING_OPT_STATS && !(val & SOF_TIMESTAMPING_OPT_TSONLY)) { ret = -EINVAL; break; } sk->sk_tsflags = val; sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); break; case SO_RCVLOWAT: if (val < 0) val = INT_MAX; if (sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_attach_filter(&fprog, sk); break; } case SO_ATTACH_BPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_attach_bpf(ufd, sk); } break; case SO_ATTACH_REUSEPORT_CBPF: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_reuseport_attach_filter(&fprog, sk); break; } case SO_ATTACH_REUSEPORT_EBPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_reuseport_attach_bpf(ufd, sk); } break; case SO_DETACH_REUSEPORT_BPF: ret = reuseport_detach_prog(sk); break; case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; case SO_LOCK_FILTER: if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) ret = -EPERM; else sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); break; case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); else clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } __sock_set_mark(sk, val); break; case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; case SO_WIFI_STATUS: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; case SO_PEEK_OFF: if (sock->ops->set_peek_off) ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; case SO_SELECT_ERR_QUEUE: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) ret = -EPERM; else { if (val < 0) ret = -EINVAL; else WRITE_ONCE(sk->sk_ll_usec, val); } break; #endif case SO_MAX_PACING_RATE: { unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && copy_from_sockptr(&ulval, optval, sizeof(ulval))) { ret = -EFAULT; break; } if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); /* Pairs with READ_ONCE() from sk_getsockopt() */ WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } case SO_INCOMING_CPU: WRITE_ONCE(sk->sk_incoming_cpu, val); break; case SO_CNX_ADVICE: if (val == 1) dst_negative_advice(sk); break; case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { if (!((sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -ENOTSUPP; } else if (sk->sk_family != PF_RDS) { ret = -ENOTSUPP; } if (!ret) { if (val < 0 || val > 1) ret = -EINVAL; else sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); } break; case SO_TXTIME: if (optlen != sizeof(struct sock_txtime)) { ret = -EINVAL; break; } else if (copy_from_sockptr(&sk_txtime, optval, sizeof(struct sock_txtime))) { ret = -EFAULT; break; } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { ret = -EINVAL; break; } /* CLOCK_MONOTONIC is only used by sch_fq, and this packet * scheduler has enough safe guards. */ if (sk_txtime.clockid != CLOCK_MONOTONIC && !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } sock_valbool_flag(sk, SOCK_TXTIME, true); sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); sk->sk_txtime_report_errors = !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); break; case SO_BINDTOIFINDEX: ret = sock_bindtoindex_locked(sk, val); break; default: ret = -ENOPROTOOPT; break; } release_sock(sk); return ret; } EXPORT_SYMBOL(sock_setsockopt); static const struct cred *sk_get_peer_cred(struct sock *sk) { const struct cred *cred; spin_lock(&sk->sk_peer_lock); cred = get_cred(sk->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); return cred; } static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); ucred->uid = from_kuid_munged(current_ns, cred->euid); ucred->gid = from_kgid_munged(current_ns, cred->egid); } } static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; for (i = 0; i < src->ngroups; i++) { gid_t gid = from_kgid_munged(user_ns, src->gid[i]); if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; } return 0; } static int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct socket *sock = sk->sk_socket; union { int val; u64 val64; unsigned long ulval; struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; } v; int lv = sizeof(int); int len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; memset(&v, 0, sizeof(v)); switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; case SO_DONTROUTE: v.val = sock_flag(sk, SOCK_LOCALROUTE); break; case SO_BROADCAST: v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: v.val = sk->sk_reuse; break; case SO_REUSEPORT: v.val = sk->sk_reuseport; break; case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: v.val = sk->sk_type; break; case SO_PROTOCOL: v.val = sk->sk_protocol; break; case SO_DOMAIN: v.val = sk->sk_family; break; case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; case SO_OOBINLINE: v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: v.val = sk->sk_priority; break; case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = sk->sk_lingertime / HZ; break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; case SO_TIMESTAMPNS_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMP_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPNS_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPING_OLD: v.val = sk->sk_tsflags; break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: v.val = 1; break; case SO_PASSCRED: v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PEERCRED: { struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } case SO_PEERGROUPS: { const struct cred *cred; int ret, n; cred = sk_get_peer_cred(sk); if (!cred) return -ENODATA; n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; goto lenout; } case SO_PEERNAME: { char address[128]; lv = sock->ops->getname(sock, (struct sockaddr *)address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; if (copy_to_sockptr(optval, address, len)) return -EFAULT; goto lenout; } /* Dubious BSD thing... Probably nobody even uses it, but * the UNIX standard wants it for whatever reason... -DaveM */ case SO_ACCEPTCONN: v.val = sk->sk_state == TCP_LISTEN; break; case SO_PASSSEC: v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: return security_socket_getpeersec_stream(sock, optval, optlen, len); case SO_MARK: v.val = sk->sk_mark; break; case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; case SO_WIFI_STATUS: v.val = sock_flag(sk, SOCK_WIFI_STATUS); break; case SO_PEEK_OFF: if (!sock->ops->set_peek_off) return -EOPNOTSUPP; v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; case SO_BINDTODEVICE: return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: len = sk_get_filter(sk, optval, len); if (len < 0) return len; goto lenout; case SO_LOCK_FILTER: v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; case SO_BPF_EXTENSIONS: v.val = bpf_tell_extensions(); break; case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = READ_ONCE(sk->sk_ll_usec); break; #endif case SO_MAX_PACING_RATE: /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ v.val = min_t(unsigned long, ~0U, READ_ONCE(sk->sk_max_pacing_rate)); } break; case SO_INCOMING_CPU: v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: { u32 meminfo[SK_MEMINFO_VARS]; sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; } #ifdef CONFIG_NET_RX_BUSY_POLL case SO_INCOMING_NAPI_ID: v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ if (v.val < MIN_NAPI_ID) v.val = 0; break; #endif case SO_COOKIE: lv = sizeof(u64); if (len < lv) return -EINVAL; v.val64 = sock_gen_cookie(sk); break; case SO_ZEROCOPY: v.val = sock_flag(sk, SOCK_ZEROCOPY); break; case SO_TXTIME: lv = sizeof(v.txtime); v.txtime.clockid = sk->sk_clockid; v.txtime.flags |= sk->sk_txtime_deadline_mode ? SOF_TXTIME_DEADLINE_MODE : 0; v.txtime.flags |= sk->sk_txtime_report_errors ? SOF_TXTIME_REPORT_ERRORS : 0; break; case SO_BINDTOIFINDEX: v.val = sk->sk_bound_dev_if; break; default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). */ return -ENOPROTOOPT; } if (len > lv) len = lv; if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { return sk_getsockopt(sock->sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } /* * Initialize an sk_lock. * * (We also register the sk_lock with the lock validator.) */ static inline void sock_lock_init(struct sock *sk) { sk_owner_clear(sk); if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, af_family_kern_slock_key_strings[sk->sk_family], af_family_kern_slock_keys + sk->sk_family, af_family_kern_key_strings[sk->sk_family], af_family_kern_keys + sk->sk_family); else sock_lock_init_class_and_name( sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], af_family_keys + sk->sk_family); } /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarly, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { struct sock *sk; struct kmem_cache *slab; slab = prot->slab; if (slab != NULL) { sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; if (want_init_on_alloc(priority)) sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { if (security_sk_alloc(sk, family, priority)) goto out_free; if (!try_module_get(prot->owner)) goto out_free_sec; sk_tx_queue_clear(sk); } return sk; out_free_sec: security_sk_free(sk); out_free: if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); return NULL; } static void sk_prot_free(struct proto *prot, struct sock *sk) { struct kmem_cache *slab; struct module *owner; owner = prot->owner; slab = prot->slab; cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); sk_owner_put(sk); if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); module_put(owner); } /** * sk_alloc - All socket objects are allocated here * @net: the applicable net namespace * @family: protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? */ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk; sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family); if (sk) { sk->sk_family = family; /* * See comment in struct sock definition to understand * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { get_net(net); sock_inuse_add(net, 1); } sock_net_set(sk, net); refcount_set(&sk->sk_wmem_alloc, 1); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); sk_tx_queue_clear(sk); } return sk; } EXPORT_SYMBOL(sk_alloc); /* Sockets having SOCK_RCU_FREE will call this function after one RCU * grace period. This is the case for UDP sockets and TCP listeners. */ static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); struct sk_filter *filter; if (sk->sk_destruct) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); #ifdef CONFIG_BPF_SYSCALL bpf_sk_storage_free(sk); #endif if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; } /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); if (rcu_access_pointer(sk->sk_reuseport_cb)) { reuseport_detach_sock(sk); use_call_rcu = true; } if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); } static void __sk_free(struct sock *sk) { if (likely(sk->sk_net_refcnt)) sock_inuse_add(sock_net(sk), -1); if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk))) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); } void sk_free(struct sock *sk) { /* * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); static void sk_init_common(struct sock *sk) { skb_queue_head_init(&sk->sk_receive_queue); skb_queue_head_init(&sk->sk_write_queue); skb_queue_head_init(&sk->sk_error_queue); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_receive_queue.lock, af_rlock_keys + sk->sk_family, af_family_rlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_write_queue.lock, af_wlock_keys + sk->sk_family, af_family_wlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); struct sk_filter *filter; bool is_charged = true; struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (!newsk) goto out; sock_copy(newsk, sk); newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) { get_net(sock_net(newsk)); sock_inuse_add(sock_net(newsk), 1); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ refcount_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); RCU_INIT_POINTER(newsk->sk_filter, filter); rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new * socket if we couldn't charge it in the first place * as otherwise we uncharge the parent's filter. */ if (!is_charged) RCU_INIT_POINTER(newsk->sk_filter, NULL); sk_free_unlock_clone(newsk); newsk = NULL; goto out; } RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); if (bpf_sk_storage_clone(sk, newsk)) { sk_free_unlock_clone(newsk); newsk = NULL; goto out; } /* Clear sk_user_data if parent had the pointer tagged * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&newsk->sk_refcnt, 2); /* Increment the counter in the same struct proto as the master * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that * is the same as sk->sk_prot->socks, as this field was copied * with memcpy). * * This _changes_ the previous behaviour, where * tcp_create_openreq_child always was incrementing the * equivalent to tcp_prot->socks (inet_sock_nr), so this have * to be taken into account in all callers. -acme */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); out: return newsk; } EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_free_unlock_clone(struct sock *sk) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ sk->sk_destruct = NULL; bh_unlock_sock(sk); sk_free(sk); } EXPORT_SYMBOL_GPL(sk_free_unlock_clone); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; sk->sk_route_caps &= ~sk->sk_route_nocaps; if (sk_can_gso(sk)) { if (dst->header_len && !xfrm_dst_offload_ok(dst)) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } sk->sk_gso_max_segs = max_segs; sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); /* * Simple resource managers for sockets. */ /* * Write buffer destructor automatically called from kfree_skb. */ void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { /* * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } /* * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); /* This variant of sock_wfree() is used by TCP, * since it sets SOCK_USE_WRITE_QUEUE. */ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) { skb->destructor = sock_edemux; sock_hold(sk); return; } #endif skb->destructor = sock_wfree; skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation * is enough to guarantee sk_free() wont free this sock until * all in-flight packets are completed */ refcount_add(skb->truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(skb_set_owner_w); static bool can_skb_orphan_partial(const struct sk_buff *skb) { #ifdef CONFIG_TLS_DEVICE /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ if (skb->decrypted) return false; #endif return (skb->destructor == sock_wfree || (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); } /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { if (skb_is_tcp_pure_ack(skb)) return; if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) return; skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); /* * Read buffer destructor automatically called from kfree_skb. */ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; atomic_sub(len, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, len); } EXPORT_SYMBOL(sock_rfree); /* * Buffer destructor for skbs that are not used directly in read or write * path, e.g. for error handler skbs. Automatically called from kfree_skb. */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); } EXPORT_SYMBOL(sock_efree); /* Buffer destructor for prefetch/receive path where reference count may * not be held, e.g. for listen sockets. */ #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { if (sk_is_refcounted(skb->sk)) sock_gen_put(skb->sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; read_unlock(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(__sock_i_ino); unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; local_bh_disable(); ino = __sock_i_ino(sk); local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. */ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; } } return NULL; } EXPORT_SYMBOL(sock_wmalloc); static void sock_ofree(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_omem_alloc); } struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority) { struct sk_buff *skb; /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > READ_ONCE(sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); if (!skb) return NULL; atomic_add(skb->truesize, &sk->sk_omem_alloc); skb->sk = sk; skb->destructor = sock_ofree; return skb; } /* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { int optmem_max = READ_ONCE(sysctl_optmem_max); if ((unsigned int)size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. */ atomic_add(size, &sk->sk_omem_alloc); mem = kmalloc(size, priority); if (mem) return mem; atomic_sub(size, &sk->sk_omem_alloc); } return NULL; } EXPORT_SYMBOL(sock_kmalloc); /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. */ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size, const bool nullify) { if (WARN_ON_ONCE(!mem)) return; if (nullify) kfree_sensitive(mem); else kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } void sock_kfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, false); } EXPORT_SYMBOL(sock_kfree_s); void sock_kzfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, true); } EXPORT_SYMBOL(sock_kzfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (!timeo) break; if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(sk), &wait); return timeo; } /* * Generic send/receive buffer handlers */ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order) { struct sk_buff *skb; long timeo; int err; timeo = sock_sndtimeo(sk, noblock); for (;;) { err = sock_error(sk); if (err != 0) goto failure; err = -EPIPE; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; if (!timeo) goto failure; if (signal_pending(current)) goto interrupted; timeo = sock_wait_for_wmem(sk, timeo); } skb = alloc_skb_with_frags(header_len, data_len, max_page_order, errcode, sk->sk_allocation); if (skb) skb_set_owner_w(skb, sk); return skb; interrupted: err = sock_intr_errno(timeo); failure: *errcode = err; return NULL; } EXPORT_SYMBOL(sock_alloc_send_pskb); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } EXPORT_SYMBOL(sock_alloc_send_skb); int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; switch (cmsg->cmsg_type) { case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; tsflags = *(u32 *)CMSG_DATA(cmsg); if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) return -EINVAL; sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; case SCM_TXTIME: if (!sock_flag(sk, SOCK_TXTIME)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) return -EINVAL; sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); break; /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL(__sock_cmsg_send); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; ret = __sock_cmsg_send(sk, msg, cmsg, sockc); if (ret) return ret; } return 0; } EXPORT_SYMBOL(sock_cmsg_send); static void sk_enter_memory_pressure(struct sock *sk) { if (!sk->sk_prot->enter_memory_pressure) return; sk->sk_prot->enter_memory_pressure(sk); } static void sk_leave_memory_pressure(struct sock *sk) { if (sk->sk_prot->leave_memory_pressure) { sk->sk_prot->leave_memory_pressure(sk); } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; if (memory_pressure && READ_ONCE(*memory_pressure)) WRITE_ONCE(*memory_pressure, 0); } } #define SKB_FRAG_PAGE_ORDER get_order(32768) DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** * skb_page_frag_refill - check that a page_frag contains enough room * @sz: minimum size of the fragment we want to get * @pfrag: pointer to page_frag * @gfp: priority for memory allocation * * Note: While this allocator tries to use high order pages, there is * no guarantee that allocations succeed. Therefore, @sz MUST be * less or equal than PAGE_SIZE. */ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } if (pfrag->offset + sz <= pfrag->size) return true; put_page(pfrag->page); } pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER && !static_branch_unlikely(&net_high_order_alloc_disable_key)) { /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; return true; } } pfrag->page = alloc_page(gfp); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE; return true; } return false; } EXPORT_SYMBOL(skb_page_frag_refill); bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) return true; sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return false; } EXPORT_SYMBOL(sk_page_frag_refill); static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); } void __release_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { struct sk_buff *skb, *next; int nb = 0; while ((skb = sk->sk_backlog.head) != NULL) { sk->sk_backlog.head = sk->sk_backlog.tail = NULL; spin_unlock_bh(&sk->sk_lock.slock); while (1) { next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); skb = next; if (!skb) break; if (!(++nb & 15)) cond_resched(); } spin_lock_bh(&sk->sk_lock.slock); } /* * Doing the zeroing here guarantee we can not loop forever * while a wild producer attempts to flood us. */ sk->sk_backlog.len = 0; } void __sk_flush_backlog(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); __release_sock(sk); spin_unlock_bh(&sk->sk_lock.slock); } /** * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); /** * __sk_mem_raise_allocated - increase memory_allocated * @sk: socket * @size: memory size to allocate * @amt: pages to allocate * @kind: allocation type * * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); bool charged = true; if (mem_cgroup_sockets_enabled && sk->sk_memcg && !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) goto suppress_allocation; /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); /* Over hard limit. */ if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; } else { /* SK_MEM_SEND */ int wmem0 = sk_get_wmem0(sk, prot); if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < wmem0) return 1; } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) { return 1; } } if (sk_has_memory_pressure(sk)) { u64 alloc; if (!sk_under_memory_pressure(sk)) return 1; alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) return 1; } suppress_allocation: if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) { sk_stream_moderate_sndbuf(sk); /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) return 1; } trace_sock_exceed_buf_limit(sk, prot, allocated, kind); sk_memory_allocated_sub(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; } EXPORT_SYMBOL(__sk_mem_raise_allocated); /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated * @sk: socket * @size: memory size to allocate * @kind: allocation type * * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means * rmem allocation. This function assumes that protocols which have * memory_pressure use sk_wmem_queued as write buffer accounting. */ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT; ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT; return ret; } EXPORT_SYMBOL(__sk_mem_schedule); /** * __sk_mem_reduce_allocated - reclaim memory_allocated * @sk: socket * @amount: number of quanta * * Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc */ void __sk_mem_reduce_allocated(struct sock *sk, int amount) { sk_memory_allocated_sub(sk, amount); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } EXPORT_SYMBOL(__sk_mem_reduce_allocated); /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= SK_MEM_QUANTUM_SHIFT; sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when * the protocol does not support a particular function. In certain * cases where it makes no sense for a protocol to have a "do nothing" * function, some default processing is provided. */ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int peer) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_getname); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_shutdown); int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg_locked); int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } EXPORT_SYMBOL(sock_no_mmap); /* * When a file is received (via SCM_RIGHTS, etc), we must bump the * various sock-based usage counts. */ void __receive_sock(struct file *file) { struct socket *sock; int error; /* * The resulting value of "error" is ignored here since we only * need to take action when the file is a socket and testing * "sock" for NULL is sufficient. */ sock = sock_from_file(file, &error); if (sock) { sock_update_netprioidx(&sock->sk->sk_cgrp_data); sock_update_classid(&sock->sk->sk_cgrp_data); } } ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; struct msghdr msg = {.msg_flags = flags}; struct kvec iov; char *kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; res = kernel_sendmsg(sock, &msg, &iov, 1, size); kunmap(page); return res; } EXPORT_SYMBOL(sock_no_sendpage); ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { ssize_t res; struct msghdr msg = {.msg_flags = flags}; struct kvec iov; char *kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size); kunmap(page); return res; } EXPORT_SYMBOL(sock_no_sendpage_locked); /* * Default Socket Callbacks */ static void sock_def_wakeup(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } void sock_def_readable(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) { } void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) if (send_sigurg(&sk->sk_socket->file->f_owner)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) { if (!mod_timer(timer, expires)) sock_hold(sk); } EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { if (del_timer(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) { if (del_timer_sync(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer_sync); void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); if (sock) { sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); } sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) lockdep_set_class_and_name( &sk->sk_callback_lock, af_kern_callback_keys + sk->sk_family, af_family_kern_clock_key_strings[sk->sk_family]); else lockdep_set_class_and_name( &sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; spin_lock_init(&sk->sk_peer_lock); sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; #if BITS_PER_LONG==32 seqlock_init(&sk->sk_stamp_seq); #endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data_uid); void sock_init_data(struct socket *sock, struct sock *sk) { kuid_t uid = sock ? SOCK_INODE(sock)->i_uid : make_kuid(sock_net(sk)->user_ns, 0); sock_init_data_uid(sock, sk, uid); } EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); } EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); /* Warning : release_cb() might need to release sk ownership, * ie call sock_release_ownership(sk) before us. */ if (sk->sk_prot->release_cb) sk->sk_prot->release_cb(sk); sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); /** * lock_sock_fast - fast version of lock_sock * @sk: socket * * This version should be used for very small section, where process wont block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled * * return true if slow path is taken: * * sk_lock.slock unlocked, owned = 1, BH enabled */ bool lock_sock_fast(struct sock *sk) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (!sk->sk_lock.owned) /* * Note : We must disable BH */ return false; __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); local_bh_enable(); return true; } EXPORT_SYMBOL(lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) { struct sock *sk = sock->sk; struct timespec64 ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec64(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); sock_write_timestamp(sk, kt); ts = ktime_to_timespec64(kt); } if (timeval) ts.tv_nsec /= 1000; #ifdef CONFIG_COMPAT_32BIT_TIME if (time32) return put_old_timespec32(&ts, userstamp); #endif #ifdef CONFIG_SPARC64 /* beware of padding in sparc64 timeval */ if (timeval && !in_compat_syscall()) { struct __kernel_old_timeval __user tv = { .tv_sec = ts.tv_sec, .tv_usec = ts.tv_nsec, }; if (copy_to_user(userstamp, &tv, sizeof(tv))) return -EFAULT; return 0; } #endif return put_timespec64(&ts, userstamp); } EXPORT_SYMBOL(sock_gettstamp); void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) { if (!sock_flag(sk, flag)) { unsigned long previous_flags = sk->sk_flags; sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ if (sock_needs_netstamp(sk) && !(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { struct sock_extended_err ee; struct sk_buff *skb; int copied, err; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ ee = SKB_EXT_ERR(skb)->ee; put_cmsg(msg, level, type, sizeof(ee), &ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; out_free_skb: kfree_skb(skb); out: return err; } EXPORT_SYMBOL(sock_recv_errqueue); /* * Get a socket option on an socket. * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume * this means if you specify SO_ERROR (otherwise whats the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_setsockopt); void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); /* * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * * A. Remove from hash tables. */ sk->sk_prot->unhash(sk); /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and * did hash table lookup before we unhashed socket. They will achieve * receive queue and will be purged by socket destructor. * * Also we still have packets pending on receive queue and probably, * our own packets waiting in device queues. sock_destroy will drain * receive queue, but transmitted packets will delay socket destruction * until the last reference will be released. */ sock_orphan(sk); xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); sock_put(sk); } EXPORT_SYMBOL(sk_common_release); void sk_get_meminfo(const struct sock *sk, u32 *mem) { memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { int val[PROTO_INUSE_NR]; }; static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { __this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } EXPORT_SYMBOL_GPL(sock_prot_inuse_add); int sock_prot_inuse_get(struct net *net, struct proto *prot) { int cpu, idx = prot->inuse_idx; int res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx]; return res >= 0 ? res : 0; } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); static void sock_inuse_add(struct net *net, int val) { this_cpu_add(*net->core.sock_inuse, val); } int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) res += *per_cpu_ptr(net->core.sock_inuse, cpu); return res; } EXPORT_SYMBOL_GPL(sock_inuse_get); static int __net_init sock_inuse_init_net(struct net *net) { net->core.prot_inuse = alloc_percpu(struct prot_inuse); if (net->core.prot_inuse == NULL) return -ENOMEM; net->core.sock_inuse = alloc_percpu(int); if (net->core.sock_inuse == NULL) goto out; return 0; out: free_percpu(net->core.prot_inuse); return -ENOMEM; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); free_percpu(net->core.sock_inuse); } static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, }; static __init int net_inuse_init(void) { if (register_pernet_subsys(&net_inuse_ops)) panic("Cannot initialize net inuse counters"); return 0; } core_initcall(net_inuse_init); static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR)) { pr_err("PROTO_INUSE_NR exhausted\n"); return -ENOSPC; } set_bit(prot->inuse_idx, proto_inuse_idx); return 0; } static void release_proto_idx(struct proto *prot) { if (prot->inuse_idx != PROTO_INUSE_NR) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else static inline int assign_proto_idx(struct proto *prot) { return 0; } static inline void release_proto_idx(struct proto *prot) { } static void sock_inuse_add(struct net *net, int val) { } #endif static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) { if (!twsk_prot) return; kfree(twsk_prot->twsk_slab_name); twsk_prot->twsk_slab_name = NULL; kmem_cache_destroy(twsk_prot->twsk_slab); twsk_prot->twsk_slab = NULL; } static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; kmem_cache_destroy(rsk_prot->slab); rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) { struct request_sock_ops *rsk_prot = prot->rsk_prot; if (!rsk_prot) return 0; rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); if (!rsk_prot->slab_name) return -ENOMEM; rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } int proto_register(struct proto *prot, int alloc_slab) { int ret = -ENOBUFS; if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | prot->slab_flags, prot->useroffset, prot->usersize, NULL); if (prot->slab == NULL) { pr_crit("%s: Can't create sock SLAB cache!\n", prot->name); goto out; } if (req_prot_init(prot)) goto out_free_request_sock_slab; if (prot->twsk_prot != NULL) { prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); if (prot->twsk_prot->twsk_slab_name == NULL) goto out_free_request_sock_slab; prot->twsk_prot->twsk_slab = kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) goto out_free_timewait_sock_slab; } } mutex_lock(&proto_list_mutex); ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; out_free_timewait_sock_slab: if (alloc_slab && prot->twsk_prot) tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); kmem_cache_destroy(prot->slab); prot->slab = NULL; } out: return ret; } EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); mutex_unlock(&proto_list_mutex); kmem_cache_destroy(prot->slab); prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); int sock_load_diag_module(int family, int protocol) { if (!protocol) { if (!sock_is_registered(family)) return -ENOENT; return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family); } #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family, protocol); } EXPORT_SYMBOL(sock_load_diag_module); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) { mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &proto_list, pos); } static void proto_seq_stop(struct seq_file *seq, void *v) __releases(proto_list_mutex) { mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } static long sock_prot_memory_allocated(struct proto *proto) { return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; } static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), sock_prot_memory_allocated(proto), sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), proto_method_implemented(proto->close), proto_method_implemented(proto->connect), proto_method_implemented(proto->disconnect), proto_method_implemented(proto->accept), proto_method_implemented(proto->ioctl), proto_method_implemented(proto->init), proto_method_implemented(proto->destroy), proto_method_implemented(proto->shutdown), proto_method_implemented(proto->setsockopt), proto_method_implemented(proto->getsockopt), proto_method_implemented(proto->sendmsg), proto_method_implemented(proto->recvmsg), proto_method_implemented(proto->sendpage), proto_method_implemented(proto->bind), proto_method_implemented(proto->backlog_rcv), proto_method_implemented(proto->hash), proto_method_implemented(proto->unhash), proto_method_implemented(proto->get_port), proto_method_implemented(proto->enter_memory_pressure)); } static int proto_seq_show(struct seq_file *seq, void *v) { if (v == &proto_list) seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s", "protocol", "size", "sockets", "memory", "press", "maxhdr", "slab", "module", "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n"); else proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; } static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, .show = proto_seq_show, }; static __net_init int proto_init_net(struct net *net) { if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static __net_exit void proto_exit_net(struct net *net) { remove_proc_entry("protocols", net->proc_net); } static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, }; static int __init proto_init(void) { return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ #ifdef CONFIG_NET_RX_BUSY_POLL bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; return !skb_queue_empty_lockless(&sk->sk_receive_queue) || sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) { if (!sk->sk_prot->bind_add) return -EOPNOTSUPP; return sk->sk_prot->bind_add(sk, addr, addr_len); } EXPORT_SYMBOL(sock_bind_add); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC_H #define _ASM_X86_ATOMIC_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> #include <asm/barrier.h> /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. */ /** * arch_atomic_read - read atomic variable * @v: pointer of type atomic_t * * Atomically reads the value of @v. */ static __always_inline int arch_atomic_read(const atomic_t *v) { /* * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here, * it's non-inlined function that increases binary size and stack usage. */ return __READ_ONCE((v)->counter); } /** * arch_atomic_set - set atomic variable * @v: pointer of type atomic_t * @i: required value * * Atomically sets the value of @v to @i. */ static __always_inline void arch_atomic_set(atomic_t *v, int i) { __WRITE_ONCE(v->counter, i); } /** * arch_atomic_add - add integer to atomic variable * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v. */ static __always_inline void arch_atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } /** * arch_atomic_sub - subtract integer from atomic variable * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v. */ static __always_inline void arch_atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } /** * arch_atomic_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i); } #define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable * @v: pointer of type atomic_t * * Atomically increments @v by 1. */ static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable * @v: pointer of type atomic_t * * Atomically decrements @v by 1. */ static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test * @v: pointer of type atomic_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e); } #define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test * @v: pointer of type atomic_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e); } #define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i); } #define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns @i + @v */ static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } #define arch_atomic_add_return arch_atomic_add_return /** * arch_atomic_sub_return - subtract integer and return * @v: pointer of type atomic_t * @i: integer value to subtract * * Atomically subtracts @i from @v and returns @v - @i */ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) { return arch_atomic_add_return(-i, v); } #define arch_atomic_sub_return arch_atomic_sub_return static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); } #define arch_atomic_fetch_add arch_atomic_fetch_add static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v) { return xadd(&v->counter, -i); } #define arch_atomic_fetch_sub arch_atomic_fetch_sub static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { return arch_cmpxchg(&v->counter, old, new); } #define arch_atomic_cmpxchg arch_atomic_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { return try_cmpxchg(&v->counter, old, new); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg static __always_inline int arch_atomic_xchg(atomic_t *v, int new) { return arch_xchg(&v->counter, new); } #define arch_atomic_xchg arch_atomic_xchg static __always_inline void arch_atomic_and(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "andl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i)); return val; } #define arch_atomic_fetch_and arch_atomic_fetch_and static __always_inline void arch_atomic_or(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "orl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i)); return val; } #define arch_atomic_fetch_or arch_atomic_fetch_or static __always_inline void arch_atomic_xor(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "xorl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i)); return val; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else # include <asm/atomic64_64.h> #endif #define ARCH_ATOMIC #endif /* _ASM_X86_ATOMIC_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #ifdef CONFIG_MEMCG_KMEM static LIST_HEAD(list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static void list_lru_register(struct list_lru *lru) { mutex_lock(&list_lrus_mutex); list_add(&lru->list, &list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) { struct list_lru_memcg *memcg_lrus; /* * Either lock or RCU protects the array of per cgroup lists * from relocation (see memcg_update_list_lru_node). */ memcg_lrus = rcu_dereference_check(nlru->memcg_lrus, lockdep_is_held(&nlru->lock)); if (memcg_lrus && idx >= 0) return memcg_lrus->lru[idx]; return &nlru->lru; } static inline struct list_lru_one * list_lru_from_kmem(struct list_lru_node *nlru, void *ptr, struct mem_cgroup **memcg_ptr) { struct list_lru_one *l = &nlru->lru; struct mem_cgroup *memcg = NULL; if (!nlru->memcg_lrus) goto out; memcg = mem_cgroup_from_obj(ptr); if (!memcg) goto out; l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); out: if (memcg_ptr) *memcg_ptr = memcg; return l; } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) { return &nlru->lru; } static inline struct list_lru_one * list_lru_from_kmem(struct list_lru_node *nlru, void *ptr, struct mem_cgroup **memcg_ptr) { if (memcg_ptr) *memcg_ptr = NULL; return &nlru->lru; } #endif /* CONFIG_MEMCG_KMEM */ bool list_lru_add(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; struct mem_cgroup *memcg; struct list_lru_one *l; spin_lock(&nlru->lock); if (list_empty(item)) { l = list_lru_from_kmem(nlru, item, &memcg); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) memcg_set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); nlru->nr_items++; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_del(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (!list_empty(item)) { l = list_lru_from_kmem(nlru, item, NULL); list_del_init(item); l->nr_items--; nlru->nr_items--; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_del); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; unsigned long count; rcu_read_lock(); l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); count = READ_ONCE(l->nr_items); rcu_read_unlock(); return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return nlru->nr_items; } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru_node *nlru, int memcg_idx, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; l = list_lru_from_memcg_idx(nlru, memcg_idx); restart: list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, &nlru->lock, cb_arg); switch (ret) { case LRU_REMOVED_RETRY: assert_spin_locked(&nlru->lock); fallthrough; case LRU_REMOVED: isolated++; nlru->nr_items--; /* * If the lru lock has been dropped, our list * traversal is now invalid and so we have to * restart from scratch. */ if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_RETRY: /* * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ assert_spin_locked(&nlru->lock); goto restart; default: BUG(); } } return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock(&nlru->lock); ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); return ret; } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock_irq(&nlru->lock); ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock_irq(&nlru->lock); return ret; } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; int memcg_idx; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { for_each_memcg_cache_index(memcg_idx) { struct list_lru_node *nlru = &lru->node[nid]; spin_lock(&nlru->lock); isolated += __list_lru_walk_one(nlru, memcg_idx, isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); if (*nr_to_walk <= 0) break; } } return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); l->nr_items = 0; } #ifdef CONFIG_MEMCG_KMEM static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus, int begin, int end) { int i; for (i = begin; i < end; i++) kfree(memcg_lrus->lru[i]); } static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus, int begin, int end) { int i; for (i = begin; i < end; i++) { struct list_lru_one *l; l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL); if (!l) goto fail; init_one_lru(l); memcg_lrus->lru[i] = l; } return 0; fail: __memcg_destroy_list_lru_node(memcg_lrus, begin, i); return -ENOMEM; } static int memcg_init_list_lru_node(struct list_lru_node *nlru) { struct list_lru_memcg *memcg_lrus; int size = memcg_nr_cache_ids; memcg_lrus = kvmalloc(sizeof(*memcg_lrus) + size * sizeof(void *), GFP_KERNEL); if (!memcg_lrus) return -ENOMEM; if (__memcg_init_list_lru_node(memcg_lrus, 0, size)) { kvfree(memcg_lrus); return -ENOMEM; } RCU_INIT_POINTER(nlru->memcg_lrus, memcg_lrus); return 0; } static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) { struct list_lru_memcg *memcg_lrus; /* * This is called when shrinker has already been unregistered, * and nobody can use it. So, there is no need to use kvfree_rcu_local(). */ memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true); __memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids); kvfree(memcg_lrus); } static void kvfree_rcu_local(struct rcu_head *head) { struct list_lru_memcg *mlru; mlru = container_of(head, struct list_lru_memcg, rcu); kvfree(mlru); } static int memcg_update_list_lru_node(struct list_lru_node *nlru, int old_size, int new_size) { struct list_lru_memcg *old, *new; BUG_ON(old_size > new_size); old = rcu_dereference_protected(nlru->memcg_lrus, lockdep_is_held(&list_lrus_mutex)); new = kvmalloc(sizeof(*new) + new_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; if (__memcg_init_list_lru_node(new, old_size, new_size)) { kvfree(new); return -ENOMEM; } memcpy(&new->lru, &old->lru, old_size * sizeof(void *)); /* * The locking below allows readers that hold nlru->lock avoid taking * rcu_read_lock (see list_lru_from_memcg_idx). * * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); rcu_assign_pointer(nlru->memcg_lrus, new); spin_unlock_irq(&nlru->lock); call_rcu(&old->rcu, kvfree_rcu_local); return 0; } static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru, int old_size, int new_size) { struct list_lru_memcg *memcg_lrus; memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, lockdep_is_held(&list_lrus_mutex)); /* do not bother shrinking the array back to the old size, because we * cannot handle allocation failures here */ __memcg_destroy_list_lru_node(memcg_lrus, old_size, new_size); } static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { int i; lru->memcg_aware = memcg_aware; if (!memcg_aware) return 0; for_each_node(i) { if (memcg_init_list_lru_node(&lru->node[i])) goto fail; } return 0; fail: for (i = i - 1; i >= 0; i--) { if (!lru->node[i].memcg_lrus) continue; memcg_destroy_list_lru_node(&lru->node[i]); } return -ENOMEM; } static void memcg_destroy_list_lru(struct list_lru *lru) { int i; if (!list_lru_memcg_aware(lru)) return; for_each_node(i) memcg_destroy_list_lru_node(&lru->node[i]); } static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_size) { int i; if (!list_lru_memcg_aware(lru)) return 0; for_each_node(i) { if (memcg_update_list_lru_node(&lru->node[i], old_size, new_size)) goto fail; } return 0; fail: for (i = i - 1; i >= 0; i--) { if (!lru->node[i].memcg_lrus) continue; memcg_cancel_update_list_lru_node(&lru->node[i], old_size, new_size); } return -ENOMEM; } static void memcg_cancel_update_list_lru(struct list_lru *lru, int old_size, int new_size) { int i; if (!list_lru_memcg_aware(lru)) return; for_each_node(i) memcg_cancel_update_list_lru_node(&lru->node[i], old_size, new_size); } int memcg_update_all_list_lrus(int new_size) { int ret = 0; struct list_lru *lru; int old_size = memcg_nr_cache_ids; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &list_lrus, list) { ret = memcg_update_list_lru(lru, old_size, new_size); if (ret) goto fail; } out: mutex_unlock(&list_lrus_mutex); return ret; fail: list_for_each_entry_continue_reverse(lru, &list_lrus, list) memcg_cancel_update_list_lru(lru, old_size, new_size); goto out; } static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, int src_idx, struct mem_cgroup *dst_memcg) { struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); src = list_lru_from_memcg_idx(nlru, src_idx); dst = list_lru_from_memcg_idx(nlru, dst_idx); list_splice_init(&src->list, &dst->list); if (src->nr_items) { dst->nr_items += src->nr_items; memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); src->nr_items = 0; } spin_unlock_irq(&nlru->lock); } static void memcg_drain_list_lru(struct list_lru *lru, int src_idx, struct mem_cgroup *dst_memcg) { int i; if (!list_lru_memcg_aware(lru)) return; for_each_node(i) memcg_drain_list_lru_node(lru, i, src_idx, dst_memcg); } void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg) { struct list_lru *lru; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &list_lrus, list) memcg_drain_list_lru(lru, src_idx, dst_memcg); mutex_unlock(&list_lrus_mutex); } #else static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { return 0; } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG_KMEM */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker) { int i; int err = -ENOMEM; #ifdef CONFIG_MEMCG_KMEM if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; #endif memcg_get_cache_ids(); lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) goto out; for_each_node(i) { spin_lock_init(&lru->node[i].lock); if (key) lockdep_set_class(&lru->node[i].lock, key); init_one_lru(&lru->node[i].lru); } err = memcg_init_list_lru(lru, memcg_aware); if (err) { kfree(lru->node); /* Do this so a list_lru_destroy() doesn't crash: */ lru->node = NULL; goto out; } list_lru_register(lru); out: memcg_put_cache_ids(); return err; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; memcg_get_cache_ids(); list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG_KMEM lru->shrinker_id = -1; #endif memcg_put_cache_ids(); } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fdtable.h> #include <linux/fsnotify_backend.h> int dir_notify_enable __read_mostly = 1; static struct kmem_cache *dnotify_struct_cache __read_mostly; static struct kmem_cache *dnotify_mark_cache __read_mostly; static struct fsnotify_group *dnotify_group __read_mostly; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = &dn->dn_filp->f_owner; send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned long arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } rcu_read_lock(); f = lookup_fd_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, FSNOTIFY_GROUP_NOFS); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); return 0; } module_init(dnotify_init) |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/relay.h * * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com) * * CONFIG_RELAY definitions and declarations */ #ifndef _LINUX_RELAY_H #define _LINUX_RELAY_H #include <linux/types.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/irq_work.h> #include <linux/bug.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/kref.h> #include <linux/percpu.h> /* * Tracks changes to rchan/rchan_buf structs */ #define RELAYFS_CHANNEL_VERSION 7 /* * Per-cpu relay channel buffer */ struct rchan_buf { void *start; /* start of channel buffer */ void *data; /* start of current sub-buffer */ size_t offset; /* current offset into sub-buffer */ size_t subbufs_produced; /* count of sub-buffers produced */ size_t subbufs_consumed; /* count of sub-buffers consumed */ struct rchan *chan; /* associated channel */ wait_queue_head_t read_wait; /* reader wait queue */ struct irq_work wakeup_work; /* reader wakeup */ struct dentry *dentry; /* channel file dentry */ struct kref kref; /* channel buffer refcount */ struct page **page_array; /* array of current buffer pages */ unsigned int page_count; /* number of current buffer pages */ unsigned int finalized; /* buffer has been finalized */ size_t *padding; /* padding counts per sub-buffer */ size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ } ____cacheline_aligned; /* * Relay channel data structure */ struct rchan { u32 version; /* the version of this struct */ size_t subbuf_size; /* sub-buffer size */ size_t n_subbufs; /* number of sub-buffers per buffer */ size_t alloc_size; /* total buffer size allocated */ struct rchan_callbacks *cb; /* client callbacks */ struct kref kref; /* channel refcount */ void *private_data; /* for user-defined data */ size_t last_toobig; /* tried to log event > subbuf size */ struct rchan_buf * __percpu *buf; /* per-cpu channel buffers */ int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ struct dentry *parent; /* parent dentry passed to open */ int has_base_filename; /* has a filename associated? */ char base_filename[NAME_MAX]; /* saved base filename */ }; /* * Relay channel client callbacks */ struct rchan_callbacks { /* * subbuf_start - called on buffer-switch to a new sub-buffer * @buf: the channel buffer containing the new sub-buffer * @subbuf: the start of the new sub-buffer * @prev_subbuf: the start of the previous sub-buffer * @prev_padding: unused space at the end of previous sub-buffer * * The client should return 1 to continue logging, 0 to stop * logging. * * NOTE: subbuf_start will also be invoked when the buffer is * created, so that the first sub-buffer can be initialized * if necessary. In this case, prev_subbuf will be NULL. * * NOTE: the client can reserve bytes at the beginning of the new * sub-buffer by calling subbuf_start_reserve() in this callback. */ int (*subbuf_start) (struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding); /* * buf_mapped - relay buffer mmap notification * @buf: the channel buffer * @filp: relay file pointer * * Called when a relay file is successfully mmapped */ void (*buf_mapped)(struct rchan_buf *buf, struct file *filp); /* * buf_unmapped - relay buffer unmap notification * @buf: the channel buffer * @filp: relay file pointer * * Called when a relay file is successfully unmapped */ void (*buf_unmapped)(struct rchan_buf *buf, struct file *filp); /* * create_buf_file - create file to represent a relay channel buffer * @filename: the name of the file to create * @parent: the parent of the file to create * @mode: the mode of the file to create * @buf: the channel buffer * @is_global: outparam - set non-zero if the buffer should be global * * Called during relay_open(), once for each per-cpu buffer, * to allow the client to create a file to be used to * represent the corresponding channel buffer. If the file is * created outside of relay, the parent must also exist in * that filesystem. * * The callback should return the dentry of the file created * to represent the relay buffer. * * Setting the is_global outparam to a non-zero value will * cause relay_open() to create a single global buffer rather * than the default set of per-cpu buffers. * * See Documentation/filesystems/relay.rst for more info. */ struct dentry *(*create_buf_file)(const char *filename, struct dentry *parent, umode_t mode, struct rchan_buf *buf, int *is_global); /* * remove_buf_file - remove file representing a relay channel buffer * @dentry: the dentry of the file to remove * * Called during relay_close(), once for each per-cpu buffer, * to allow the client to remove a file used to represent a * channel buffer. * * The callback should return 0 if successful, negative if not. */ int (*remove_buf_file)(struct dentry *dentry); }; /* * CONFIG_RELAY kernel API, kernel/relay.c */ struct rchan *relay_open(const char *base_filename, struct dentry *parent, size_t subbuf_size, size_t n_subbufs, struct rchan_callbacks *cb, void *private_data); extern int relay_late_setup_files(struct rchan *chan, const char *base_filename, struct dentry *parent); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); extern void relay_subbufs_consumed(struct rchan *chan, unsigned int cpu, size_t consumed); extern void relay_reset(struct rchan *chan); extern int relay_buf_full(struct rchan_buf *buf); extern size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length); /** * relay_write - write data into the channel * @chan: relay channel * @data: data to be written * @length: number of bytes to write * * Writes data into the current cpu's channel buffer. * * Protects the buffer by disabling interrupts. Use this * if you might be logging from interrupt context. Try * __relay_write() if you know you won't be logging from * interrupt context. */ static inline void relay_write(struct rchan *chan, const void *data, size_t length) { unsigned long flags; struct rchan_buf *buf; local_irq_save(flags); buf = *this_cpu_ptr(chan->buf); if (unlikely(buf->offset + length > chan->subbuf_size)) length = relay_switch_subbuf(buf, length); memcpy(buf->data + buf->offset, data, length); buf->offset += length; local_irq_restore(flags); } /** * __relay_write - write data into the channel * @chan: relay channel * @data: data to be written * @length: number of bytes to write * * Writes data into the current cpu's channel buffer. * * Protects the buffer by disabling preemption. Use * relay_write() if you might be logging from interrupt * context. */ static inline void __relay_write(struct rchan *chan, const void *data, size_t length) { struct rchan_buf *buf; buf = *get_cpu_ptr(chan->buf); if (unlikely(buf->offset + length > buf->chan->subbuf_size)) length = relay_switch_subbuf(buf, length); memcpy(buf->data + buf->offset, data, length); buf->offset += length; put_cpu_ptr(chan->buf); } /** * relay_reserve - reserve slot in channel buffer * @chan: relay channel * @length: number of bytes to reserve * * Returns pointer to reserved slot, NULL if full. * * Reserves a slot in the current cpu's channel buffer. * Does not protect the buffer at all - caller must provide * appropriate synchronization. */ static inline void *relay_reserve(struct rchan *chan, size_t length) { void *reserved = NULL; struct rchan_buf *buf = *get_cpu_ptr(chan->buf); if (unlikely(buf->offset + length > buf->chan->subbuf_size)) { length = relay_switch_subbuf(buf, length); if (!length) goto end; } reserved = buf->data + buf->offset; buf->offset += length; end: put_cpu_ptr(chan->buf); return reserved; } /** * subbuf_start_reserve - reserve bytes at the start of a sub-buffer * @buf: relay channel buffer * @length: number of bytes to reserve * * Helper function used to reserve bytes at the beginning of * a sub-buffer in the subbuf_start() callback. */ static inline void subbuf_start_reserve(struct rchan_buf *buf, size_t length) { BUG_ON(length >= buf->chan->subbuf_size - 1); buf->offset = length; } /* * exported relay file operations, kernel/relay.c */ extern const struct file_operations relay_file_operations; #ifdef CONFIG_RELAY int relay_prepare_cpu(unsigned int cpu); #else #define relay_prepare_cpu NULL #endif #endif /* _LINUX_RELAY_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Block data types and constants. Directly include this file only to * break include dependency loop. */ #ifndef __LINUX_BLK_TYPES_H #define __LINUX_BLK_TYPES_H #include <linux/types.h> #include <linux/bvec.h> #include <linux/ktime.h> struct bio_set; struct bio; struct bio_integrity_payload; struct page; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; struct block_device { dev_t bd_dev; int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; struct mutex bd_mutex; /* open/close mutex */ void * bd_claiming; void * bd_holder; int bd_holders; bool bd_write_holder; #ifdef CONFIG_SYSFS struct list_head bd_holder_disks; #endif struct block_device * bd_contains; u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; /* The counter of freeze processes */ int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; } __randomize_layout; /* * Block error status values. See block/blk-core:blk_errors for the details. * Alpha cannot write a byte atomically, so we need to use 32-bit value. */ #if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) typedef u32 __bitwise blk_status_t; #else typedef u8 __bitwise blk_status_t; #endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) #define BLK_STS_NOSPC ((__force blk_status_t)3) #define BLK_STS_TRANSPORT ((__force blk_status_t)4) #define BLK_STS_TARGET ((__force blk_status_t)5) #define BLK_STS_NEXUS ((__force blk_status_t)6) #define BLK_STS_MEDIUM ((__force blk_status_t)7) #define BLK_STS_PROTECTION ((__force blk_status_t)8) #define BLK_STS_RESOURCE ((__force blk_status_t)9) #define BLK_STS_IOERR ((__force blk_status_t)10) /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) #define BLK_STS_AGAIN ((__force blk_status_t)12) /* * BLK_STS_DEV_RESOURCE is returned from the driver to the block layer if * device related resources are unavailable, but the driver can guarantee * that the queue will be rerun in the future once resources become * available again. This is typically the case for device specific * resources that are consumed for IO. If the driver fails allocating these * resources, we know that inflight (or pending) IO will free these * resource upon completion. * * This is different from BLK_STS_RESOURCE in that it explicitly references * a device specific resource. For resources of wider scope, allocation * failure can happen without having pending IO. This means that we can't * rely on request completions freeing these resources, as IO may not be in * flight. Examples of that are kernel memory allocations, DMA mappings, or * any other system wide resources. */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone * related resources are unavailable, but the driver can guarantee the queue * will be rerun in the future once the resources become available again. * * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references * a zone specific resource and IO to a different zone on the same device could * still be served. Examples of that are zones that are write-locked, but a read * to the same zone could be served. */ #define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ #define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently active. The same command should be successful if resubmitted * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with * * Description: * This classifies block error status into non-retryable errors and ones * that may be successful if retried on a failover path. * * Return: * %false - retrying failover path will not help * %true - may succeed if retried */ static inline bool blk_path_error(blk_status_t error) { switch (error) { case BLK_STS_NOTSUPP: case BLK_STS_NOSPC: case BLK_STS_TARGET: case BLK_STS_NEXUS: case BLK_STS_MEDIUM: case BLK_STS_PROTECTION: return false; } /* Anything else could be a path failure, so should be retried */ return true; } /* * From most significant bit: * 1 bit: reserved for other usage, see below * 12 bits: original size of bio * 51 bits: issue time of bio */ #define BIO_ISSUE_RES_BITS 1 #define BIO_ISSUE_SIZE_BITS 12 #define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS) #define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS) #define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1) #define BIO_ISSUE_SIZE_MASK \ (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT) #define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1)) /* Reserved bit for blk-throtl */ #define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63) struct bio_issue { u64 value; }; static inline u64 __bio_issue_time(u64 time) { return time & BIO_ISSUE_TIME_MASK; } static inline u64 bio_issue_time(struct bio_issue *issue) { return __bio_issue_time(issue->value); } static inline sector_t bio_issue_size(struct bio_issue *issue) { return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT); } static inline void bio_issue_init(struct bio_issue *issue, sector_t size) { size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1; issue->value = ((issue->value & BIO_ISSUE_RES_MASK) | (ktime_get_ns() & BIO_ISSUE_TIME_MASK) | ((u64)size << BIO_ISSUE_SIZE_SHIFT)); } /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { struct bio *bi_next; /* request queue link */ struct gendisk *bi_disk; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. */ unsigned short bi_flags; /* status, etc and bvec pool number */ unsigned short bi_ioprio; unsigned short bi_write_hint; blk_status_t bi_status; u8 bi_partno; atomic_t __bi_remaining; struct bvec_iter bi_iter; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP /* * Represents the association of the css and request_queue for the bio. * If a bio goes direct to device, it will not have a blkg as it will * not have a request_queue associated with it. The reference is put * on release of the bio. */ struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #ifdef CONFIG_BLK_CGROUP_IOCOST u64 bi_iocost_cost; #endif #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *bi_crypt_context; #endif union { #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif }; unsigned short bi_vcnt; /* how many bio_vec's */ /* * Everything starting with bi_max_vecs will be preserved by bio_reset() */ unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ atomic_t __bi_cnt; /* pin count */ struct bio_vec *bi_io_vec; /* the actual vec list */ struct bio_set *bi_pool; /* * We can inline a number of vecs at the end of the bio, to avoid * double allocations for a small number of bio_vecs. This member * MUST obviously be kept at the very end of the bio. */ struct bio_vec bi_inline_vecs[]; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) /* * bio flags */ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ BIO_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_FLAG_LAST }; /* See BVEC_POOL_OFFSET below before adding new flags */ /* * We support 6 different bvec pools, the last one is magic in that it * is backed by a mempool. */ #define BVEC_POOL_NR 6 #define BVEC_POOL_MAX (BVEC_POOL_NR - 1) /* * Top 3 bits of bio flags indicate the pool the bvecs came from. We add * 1 to the actual index so that 0 indicates that there are no bvecs to be * freed. */ #define BVEC_POOL_BITS (3) #define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) #define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) #if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1) # error "BVEC_POOL_BITS is too small" #endif /* * Flags starting here get preserved by bio_reset() - this includes * only BVEC_POOL_IDX() */ #define BIO_RESET_BITS BVEC_POOL_OFFSET typedef __u32 __bitwise blk_mq_req_flags_t; /* * Operations and flags common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. * * The least significant bit of the operation number indicates the data * transfer direction: * * - if the least significant bit is set transfers are TO the device * - if the least significant bit is not set transfers are FROM the device * * If a operation does not transfer data the least significant bit has no * meaning. */ #define REQ_OP_BITS 8 #define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) #define REQ_FLAG_BITS 24 enum req_opf { /* read sectors from the device */ REQ_OP_READ = 0, /* write sectors to the device */ REQ_OP_WRITE = 1, /* flush the volatile write cache */ REQ_OP_FLUSH = 2, /* discard sectors */ REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ REQ_OP_ZONE_OPEN = 11, /* Close a zone */ REQ_OP_ZONE_CLOSE = 13, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = 15, /* reset a zone write pointer */ REQ_OP_ZONE_RESET = 17, /* reset all the zone present on the device */ REQ_OP_ZONE_RESET_ALL = 19, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = 21, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, REQ_OP_SCSI_OUT = 33, /* Driver private requests */ REQ_OP_DRV_IN = 34, REQ_OP_DRV_OUT = 35, REQ_OP_LAST, }; enum req_flag_bits { __REQ_FAILFAST_DEV = /* no driver retries of device errors */ REQ_OP_BITS, __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ __REQ_NOMERGE, /* don't touch this for merging */ __REQ_IDLE, /* anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread * can be trapped waiting for that cgroup. CGROUP_PUNT flag makes * submit_bio() punt the actual issuing to a dedicated per-blkcg * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ __REQ_HIPRI, /* for driver use */ __REQ_DRV, __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; #define REQ_FAILFAST_DEV (1ULL << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT (1ULL << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER (1ULL << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (1ULL << __REQ_SYNC) #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) #define REQ_NOMERGE (1ULL << __REQ_NOMERGE) #define REQ_IDLE (1ULL << __REQ_IDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_HIPRI (1ULL << __REQ_HIPRI) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, STAT_FLUSH, NR_STAT_GROUPS }; #define bio_op(bio) \ ((bio)->bi_opf & REQ_OP_MASK) #define req_op(req) \ ((req)->cmd_flags & REQ_OP_MASK) /* obsolete, don't use in new code */ static inline void bio_set_op_attrs(struct bio *bio, unsigned op, unsigned op_flags) { bio->bi_opf = op | op_flags; } static inline bool op_is_write(unsigned int op) { return (op & 1); } /* * Check if the bio or request is one that needs special treatment in the * flush state machine. */ static inline bool op_is_flush(unsigned int op) { return op & (REQ_FUA | REQ_PREFLUSH); } /* * Reads are always treated as synchronous, as are requests with the FUA or * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. */ static inline bool op_is_sync(unsigned int op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } static inline bool op_is_discard(unsigned int op) { return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } /* * Check if a bio or request operation is a zone management operation. */ static inline bool op_is_zone_mgmt(enum req_opf op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: return true; default: return false; } } static inline int op_stat_group(unsigned int op) { if (op_is_discard(op)) return STAT_DISCARD; return op_is_write(op); } typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) { return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT; } static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) { return cookie & ((1u << BLK_QC_T_SHIFT) - 1); } static inline bool blk_qc_t_is_internal(blk_qc_t cookie) { return (cookie & BLK_QC_T_INTERNAL) != 0; } struct blk_rq_stat { u64 mean; u64 min; u64 max; u32 nr_samples; u64 batch; }; #endif /* __LINUX_BLK_TYPES_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 | // SPDX-License-Identifier: GPL-2.0 /* * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ #define _DEVICE_H_ #include <linux/dev_printk.h> #include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> struct device; struct device_private; struct device_driver; struct driver_private; struct module; struct class; struct subsys_private; struct device_node; struct fwnode_handle; struct iommu_ops; struct iommu_group; struct dev_pin_info; struct dev_iommu; /** * struct subsys_interface - interfaces to device functions * @name: name of the device function * @subsys: subsytem of the devices to attach to * @node: the list of functions registered at the subsystem * @add_dev: device hookup to device function handler * @remove_dev: device hookup to device function handler * * Simple interfaces attached to a subsystem. Multiple interfaces can * attach to a subsystem and its devices. Unlike drivers, they do not * exclusively claim or control devices. Interfaces usually represent * a specific functionality of a subsystem/class of devices. */ struct subsys_interface { const char *name; struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(struct bus_type *subsys, const struct attribute_group **groups); int subsys_virtual_register(struct bus_type *subsys, const struct attribute_group **groups); /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types * like "partitions" and "disks", "mouse" and "event". * This identifies the device type and carries type-specific * information, equivalent to the kobj_type of a kobject. * If "name" is specified, the uevent will contain it in * the DEVTYPE variable. */ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; }; /* interface for exporting device attributes */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); }; struct dev_ext_attribute { struct device_attribute attr; void *var; }; ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); #define DEVICE_ATTR(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_PREALLOC(_name, _mode, _show, _store) #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) #define DEVICE_ATTR_ADMIN_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) #define DEVICE_ATTR_ADMIN_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } #define DEVICE_BOOL_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) int device_create_file(struct device *device, const struct device_attribute *entry); void device_remove_file(struct device *dev, const struct device_attribute *attr); bool device_remove_file_self(struct device *dev, const struct device_attribute *attr); int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); #ifdef CONFIG_DEBUG_DEVRES void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) #else void *devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid) __malloc; static inline void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp) { return devres_alloc_node(release, size, gfp, NUMA_NO_NODE); } #endif void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc; void *devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp) __must_check; __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) __malloc; __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc; static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } void devm_kfree(struct device *dev, const void *p); char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); /* allows to add/remove a custom action to devres stack */ int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); static inline int devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data) { int ret; ret = devm_add_action(dev, action, data); if (ret) action(data); return ret; } /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); void devm_free_percpu(struct device *dev, void __percpu *pdata); struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about * sg limitations. */ unsigned int max_segment_size; unsigned int min_align_mask; unsigned long segment_boundary_mask; }; /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. */ enum device_link_state { DL_STATE_NONE = -1, DL_STATE_DORMANT = 0, DL_STATE_AVAILABLE, DL_STATE_CONSUMER_PROBE, DL_STATE_ACTIVE, DL_STATE_SUPPLIER_UNBIND, }; /* * Device link flags. * * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. * @DL_DEV_PROBING: A driver is probing. * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. * @DL_DEV_UNBINDING: The driver is unbinding from the device. */ enum dl_dev_state { DL_DEV_NO_DRIVER = 0, DL_DEV_PROBING, DL_DEV_DRIVER_BOUND, DL_DEV_UNBINDING, }; /** * enum device_removable - Whether the device is removable. The criteria for a * device to be classified as removable is determined by its subsystem or bus. * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this * device (default). * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. * @DEVICE_FIXED: Device is not removable by the user. * @DEVICE_REMOVABLE: Device is removable by the user. */ enum device_removable { DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ DEVICE_REMOVABLE_UNKNOWN, DEVICE_FIXED, DEVICE_REMOVABLE, }; /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. * @defer_hook: Hook to global list of devices that have deferred sync_state or * deferred fw_devlink. * @need_for_probe: If needs_suppliers is on a list, this indicates if the * suppliers are needed for probe or not. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head needs_suppliers; struct list_head defer_hook; bool need_for_probe; enum dl_dev_state status; }; /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host * controller. If parent is NULL, the device, is a top-level device, * which is not usually what you want. * @p: Holds the private data of the driver core portions of the device. * See the comment of the struct device_private for detail. * @kobj: A top-level, abstract class from which other classes are derived. * @init_name: Initial name of the device. * @type: The type of device. * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. * @lockdep_mutex: An optional debug lock that a subsystem can use as a * peer lock to gain localized lockdep coverage of the device_lock. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. * Example: For devices on custom boards, as typical of embedded * and SOC based hardware, Linux often uses platform_data to point * to board-specific structures describing devices and how they * are wired. That can include what ports are available, chip * variants, which GPIO pins act in what additional roles, and so * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. * @devt: For creating the sysfs "dev". * @id: device instance * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. * @knode_class: The node used to add the device to the class list. * @class: The class of the device. * @groups: Optional attribute groups. * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. * @state_synced: The hardware state of this device has been synced to match * the software state of this device by calling the driver/bus * sync_state() callback. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information * that the device model core needs to model the system. Most subsystems, * however, track additional information about the devices they host. As a * result, it is rare for devices to be represented by bare device structures; * instead, that structure, like kobject structures, is usually embedded within * a higher-level representation of the device. */ struct device { struct kobject kobj; struct device *parent; struct device_private *p; const char *init_name; /* initial name of the device */ const struct device_type *type; struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ #ifdef CONFIG_PROVE_LOCKING struct mutex lockdep_mutex; #endif struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_ENERGY_MODEL struct em_perf_domain *em_pd; #endif #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN struct irq_domain *msi_domain; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ #ifdef CONFIG_DMA_DECLARE_COHERENT struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #endif #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct dev_iommu *iommu; enum device_removable removable; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; bool state_synced:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif }; /** * struct device_link - Device link representation. * @supplier: The device on the supplier end of the link. * @s_node: Hook to the supplier device's list of links to consumers. * @consumer: The device on the consumer end of the link. * @c_node: Hook to the consumer device's list of links to suppliers. * @link_dev: device used to expose link details in sysfs * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { struct device *supplier; struct list_head s_node; struct device *consumer; struct list_head c_node; struct device link_dev; enum device_link_state status; u32 flags; refcount_t rpm_active; struct kref kref; struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; static inline struct device *kobj_to_dev(struct kobject *kobj) { return container_of(kobj, struct device, kobj); } /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU * @dev: Device to perform the check on */ static inline bool device_iommu_mapped(struct device *dev) { return (dev->iommu_group != NULL); } /* Get the wakeup routines, which depend on struct device */ #include <linux/pm_wakeup.h> static inline const char *dev_name(const struct device *dev) { /* Use the init name until the kobject becomes available */ if (dev->init_name) return dev->init_name; return kobject_name(&dev->kobj); } /** * dev_bus_name - Return a device's bus/class name, if at all possible * @dev: struct device to get the bus/class name of * * Will return the name of the bus/class the device is attached to. If it is * not attached to a bus/class, an empty string will be returned. */ static inline const char *dev_bus_name(const struct device *dev) { return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); } __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { return dev->numa_node; } static inline void set_dev_node(struct device *dev, int node) { dev->numa_node = node; } #else static inline int dev_to_node(struct device *dev) { return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { } #endif static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN return dev->msi_domain; #else return NULL; #endif } static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN dev->msi_domain = d; #endif } static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; } static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } static inline struct pm_subsys_data *dev_to_psd(struct device *dev) { return dev ? dev->power.subsys_data : NULL; } static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; } static inline void dev_set_uevent_suppress(struct device *dev, int val) { dev->kobj.uevent_suppress = val; } static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; } static inline void device_enable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = false; } static inline bool device_async_suspend_enabled(struct device *dev) { return !!dev->power.async_suspend; } static inline bool device_pm_not_required(struct device *dev) { return dev->power.no_pm; } static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; #ifdef CONFIG_PM dev->power.no_callbacks = true; #endif } static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.syscore = val; #endif } static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) { dev->power.driver_flags = flags; } static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) { return !!(dev->power.driver_flags & flags); } static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); } static inline int device_lock_interruptible(struct device *dev) { return mutex_lock_interruptible(&dev->mutex); } static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { mutex_unlock(&dev->mutex); } static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); } static inline struct device_node *dev_of_node(struct device *dev) { if (!IS_ENABLED(CONFIG_OF) || !dev) return NULL; return dev->of_node; } static inline bool dev_has_sync_state(struct device *dev) { if (!dev) return false; if (dev->driver && dev->driver->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_set_removable(struct device *dev, enum device_removable removable) { dev->removable = removable; } static inline bool dev_is_removable(struct device *dev) { return dev->removable == DEVICE_REMOVABLE; } static inline bool dev_removable_is_valid(struct device *dev) { return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; } /* * High level routines for use by the bus drivers */ int __must_check device_register(struct device *dev); void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, const char *name); struct device *device_find_any_child(struct device *parent); int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); int device_is_dependent(struct device *dev, void *target); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); static inline int dev_num_vf(struct device *dev) { if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev); return 0; } /* * Root device objects for grouping under /sys/devices */ struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { return dev->platform_data; } /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); int __must_check driver_attach(struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * device_create(struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_add_groups(dev, groups); } static inline void device_remove_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_remove_groups(dev, groups); } int __must_check devm_device_add_groups(struct device *dev, const struct attribute_group **groups); void devm_device_remove_groups(struct device *dev, const struct attribute_group **groups); int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); void devm_device_remove_group(struct device *dev, const struct attribute_group *grp); /* * Platform "fixup" functions - allow the platform to have their say * about devices and actions that the general device layer doesn't * know about. */ /* Notify platform of device discovery */ extern int (*platform_notify)(struct device *dev); extern int (*platform_notify_remove)(struct device *dev); /* * get_device - atomically increment the reference count for the device. * */ struct device *get_device(struct device *dev); void put_device(struct device *dev); DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); void device_link_wait_removal(void); extern __printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") #ifdef CONFIG_SYSFS_DEPRECATED extern long sysfs_deprecated; #else #define sysfs_deprecated 0 #endif #endif /* _DEVICE_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 | // SPDX-License-Identifier: GPL-2.0 /* * This is a maximally equidistributed combined Tausworthe generator * based on code from GNU Scientific Library 1.5 (30 Jun 2004) * * lfsr113 version: * * x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n) * * s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n << 6) ^ s1_n) >> 13)) * s2_{n+1} = (((s2_n & 4294967288) << 2) ^ (((s2_n << 2) ^ s2_n) >> 27)) * s3_{n+1} = (((s3_n & 4294967280) << 7) ^ (((s3_n << 13) ^ s3_n) >> 21)) * s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n << 3) ^ s4_n) >> 12)) * * The period of this generator is about 2^113 (see erratum paper). * * From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe * Generators", Mathematics of Computation, 65, 213 (1996), 203--213: * http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps * ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps * * There is an erratum in the paper "Tables of Maximally Equidistributed * Combined LFSR Generators", Mathematics of Computation, 68, 225 (1999), * 261--269: http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps * * ... the k_j most significant bits of z_j must be non-zero, * for each j. (Note: this restriction also applies to the * computer code given in [4], but was mistakenly not mentioned * in that paper.) * * This affects the seeding procedure by imposing the requirement * s1 > 1, s2 > 7, s3 > 15, s4 > 127. */ #include <linux/types.h> #include <linux/percpu.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/notifier.h> #include <asm/unaligned.h> /** * prandom_u32_state - seeded pseudo-random number generator. * @state: pointer to state structure holding seeded state. * * This is used for pseudo-randomness with no outside seeding. * For more random results, use prandom_u32(). */ u32 prandom_u32_state(struct rnd_state *state) { #define TAUSWORTHE(s, a, b, c, d) ((s & c) << d) ^ (((s << a) ^ s) >> b) state->s1 = TAUSWORTHE(state->s1, 6U, 13U, 4294967294U, 18U); state->s2 = TAUSWORTHE(state->s2, 2U, 27U, 4294967288U, 2U); state->s3 = TAUSWORTHE(state->s3, 13U, 21U, 4294967280U, 7U); state->s4 = TAUSWORTHE(state->s4, 3U, 12U, 4294967168U, 13U); return (state->s1 ^ state->s2 ^ state->s3 ^ state->s4); } EXPORT_SYMBOL(prandom_u32_state); /** * prandom_bytes_state - get the requested number of pseudo-random bytes * * @state: pointer to state structure holding seeded state. * @buf: where to copy the pseudo-random bytes to * @bytes: the requested number of bytes * * This is used for pseudo-randomness with no outside seeding. * For more random results, use prandom_bytes(). */ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes) { u8 *ptr = buf; while (bytes >= sizeof(u32)) { put_unaligned(prandom_u32_state(state), (u32 *) ptr); ptr += sizeof(u32); bytes -= sizeof(u32); } if (bytes > 0) { u32 rem = prandom_u32_state(state); do { *ptr++ = (u8) rem; bytes--; rem >>= BITS_PER_BYTE; } while (bytes > 0); } } EXPORT_SYMBOL(prandom_bytes_state); static void prandom_warmup(struct rnd_state *state) { /* Calling RNG ten times to satisfy recurrence condition */ prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); } void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) { int i; for_each_possible_cpu(i) { struct rnd_state *state = per_cpu_ptr(pcpu_state, i); u32 seeds[4]; get_random_bytes(&seeds, sizeof(seeds)); state->s1 = __seed(seeds[0], 2U); state->s2 = __seed(seeds[1], 8U); state->s3 = __seed(seeds[2], 16U); state->s4 = __seed(seeds[3], 128U); prandom_warmup(state); } } EXPORT_SYMBOL(prandom_seed_full_state); #ifdef CONFIG_RANDOM32_SELFTEST static struct prandom_test1 { u32 seed; u32 result; } test1[] = { { 1U, 3484351685U }, { 2U, 2623130059U }, { 3U, 3125133893U }, { 4U, 984847254U }, }; static struct prandom_test2 { u32 seed; u32 iteration; u32 result; } test2[] = { /* Test cases against taus113 from GSL library. */ { 931557656U, 959U, 2975593782U }, { 1339693295U, 876U, 3887776532U }, { 1545556285U, 961U, 1615538833U }, { 601730776U, 723U, 1776162651U }, { 1027516047U, 687U, 511983079U }, { 416526298U, 700U, 916156552U }, { 1395522032U, 652U, 2222063676U }, { 366221443U, 617U, 2992857763U }, { 1539836965U, 714U, 3783265725U }, { 556206671U, 994U, 799626459U }, { 684907218U, 799U, 367789491U }, { 2121230701U, 931U, 2115467001U }, { 1668516451U, 644U, 3620590685U }, { 768046066U, 883U, 2034077390U }, { 1989159136U, 833U, 1195767305U }, { 536585145U, 996U, 3577259204U }, { 1008129373U, 642U, 1478080776U }, { 1740775604U, 939U, 1264980372U }, { 1967883163U, 508U, 10734624U }, { 1923019697U, 730U, 3821419629U }, { 442079932U, 560U, 3440032343U }, { 1961302714U, 845U, 841962572U }, { 2030205964U, 962U, 1325144227U }, { 1160407529U, 507U, 240940858U }, { 635482502U, 779U, 4200489746U }, { 1252788931U, 699U, 867195434U }, { 1961817131U, 719U, 668237657U }, { 1071468216U, 983U, 917876630U }, { 1281848367U, 932U, 1003100039U }, { 582537119U, 780U, 1127273778U }, { 1973672777U, 853U, 1071368872U }, { 1896756996U, 762U, 1127851055U }, { 847917054U, 500U, 1717499075U }, { 1240520510U, 951U, 2849576657U }, { 1685071682U, 567U, 1961810396U }, { 1516232129U, 557U, 3173877U }, { 1208118903U, 612U, 1613145022U }, { 1817269927U, 693U, 4279122573U }, { 1510091701U, 717U, 638191229U }, { 365916850U, 807U, 600424314U }, { 399324359U, 702U, 1803598116U }, { 1318480274U, 779U, 2074237022U }, { 697758115U, 840U, 1483639402U }, { 1696507773U, 840U, 577415447U }, { 2081979121U, 981U, 3041486449U }, { 955646687U, 742U, 3846494357U }, { 1250683506U, 749U, 836419859U }, { 595003102U, 534U, 366794109U }, { 47485338U, 558U, 3521120834U }, { 619433479U, 610U, 3991783875U }, { 704096520U, 518U, 4139493852U }, { 1712224984U, 606U, 2393312003U }, { 1318233152U, 922U, 3880361134U }, { 855572992U, 761U, 1472974787U }, { 64721421U, 703U, 683860550U }, { 678931758U, 840U, 380616043U }, { 692711973U, 778U, 1382361947U }, { 677703619U, 530U, 2826914161U }, { 92393223U, 586U, 1522128471U }, { 1222592920U, 743U, 3466726667U }, { 358288986U, 695U, 1091956998U }, { 1935056945U, 958U, 514864477U }, { 735675993U, 990U, 1294239989U }, { 1560089402U, 897U, 2238551287U }, { 70616361U, 829U, 22483098U }, { 368234700U, 731U, 2913875084U }, { 20221190U, 879U, 1564152970U }, { 539444654U, 682U, 1835141259U }, { 1314987297U, 840U, 1801114136U }, { 2019295544U, 645U, 3286438930U }, { 469023838U, 716U, 1637918202U }, { 1843754496U, 653U, 2562092152U }, { 400672036U, 809U, 4264212785U }, { 404722249U, 965U, 2704116999U }, { 600702209U, 758U, 584979986U }, { 519953954U, 667U, 2574436237U }, { 1658071126U, 694U, 2214569490U }, { 420480037U, 749U, 3430010866U }, { 690103647U, 969U, 3700758083U }, { 1029424799U, 937U, 3787746841U }, { 2012608669U, 506U, 3362628973U }, { 1535432887U, 998U, 42610943U }, { 1330635533U, 857U, 3040806504U }, { 1223800550U, 539U, 3954229517U }, { 1322411537U, 680U, 3223250324U }, { 1877847898U, 945U, 2915147143U }, { 1646356099U, 874U, 965988280U }, { 805687536U, 744U, 4032277920U }, { 1948093210U, 633U, 1346597684U }, { 392609744U, 783U, 1636083295U }, { 690241304U, 770U, 1201031298U }, { 1360302965U, 696U, 1665394461U }, { 1220090946U, 780U, 1316922812U }, { 447092251U, 500U, 3438743375U }, { 1613868791U, 592U, 828546883U }, { 523430951U, 548U, 2552392304U }, { 726692899U, 810U, 1656872867U }, { 1364340021U, 836U, 3710513486U }, { 1986257729U, 931U, 935013962U }, { 407983964U, 921U, 728767059U }, }; static u32 __extract_hwseed(void) { unsigned int val = 0; (void)(arch_get_random_seed_int(&val) || arch_get_random_int(&val)); return val; } static void prandom_seed_early(struct rnd_state *state, u32 seed, bool mix_with_hwseed) { #define LCG(x) ((x) * 69069U) /* super-duper LCG */ #define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0) state->s1 = __seed(HWSEED() ^ LCG(seed), 2U); state->s2 = __seed(HWSEED() ^ LCG(state->s1), 8U); state->s3 = __seed(HWSEED() ^ LCG(state->s2), 16U); state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U); } static int __init prandom_state_selftest(void) { int i, j, errors = 0, runs = 0; bool error = false; for (i = 0; i < ARRAY_SIZE(test1); i++) { struct rnd_state state; prandom_seed_early(&state, test1[i].seed, false); prandom_warmup(&state); if (test1[i].result != prandom_u32_state(&state)) error = true; } if (error) pr_warn("prandom: seed boundary self test failed\n"); else pr_info("prandom: seed boundary self test passed\n"); for (i = 0; i < ARRAY_SIZE(test2); i++) { struct rnd_state state; prandom_seed_early(&state, test2[i].seed, false); prandom_warmup(&state); for (j = 0; j < test2[i].iteration - 1; j++) prandom_u32_state(&state); if (test2[i].result != prandom_u32_state(&state)) errors++; runs++; cond_resched(); } if (errors) pr_warn("prandom: %d/%d self tests failed\n", errors, runs); else pr_info("prandom: %d self tests passed\n", runs); return 0; } core_initcall(prandom_state_selftest); #endif /* * The prandom_u32() implementation is now completely separate from the * prandom_state() functions, which are retained (for now) for compatibility. * * Because of (ab)use in the networking code for choosing random TCP/UDP port * numbers, which open DoS possibilities if guessable, we want something * stronger than a standard PRNG. But the performance requirements of * the network code do not allow robust crypto for this application. * * So this is a homebrew Junior Spaceman implementation, based on the * lowest-latency trustworthy crypto primitive available, SipHash. * (The authors of SipHash have not been consulted about this abuse of * their work.) * * Standard SipHash-2-4 uses 2n+4 rounds to hash n words of input to * one word of output. This abbreviated version uses 2 rounds per word * of output. */ struct siprand_state { unsigned long v0; unsigned long v1; unsigned long v2; unsigned long v3; }; static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy; DEFINE_PER_CPU(unsigned long, net_rand_noise); EXPORT_PER_CPU_SYMBOL(net_rand_noise); /* * This is the core CPRNG function. As "pseudorandom", this is not used * for truly valuable things, just intended to be a PITA to guess. * For maximum speed, we do just two SipHash rounds per word. This is * the same rate as 4 rounds per 64 bits that SipHash normally uses, * so hopefully it's reasonably secure. * * There are two changes from the official SipHash finalization: * - We omit some constants XORed with v2 in the SipHash spec as irrelevant; * they are there only to make the output rounds distinct from the input * rounds, and this application has no input rounds. * - Rather than returning v0^v1^v2^v3, return v1+v3. * If you look at the SipHash round, the last operation on v3 is * "v3 ^= v0", so "v0 ^ v3" just undoes that, a waste of time. * Likewise "v1 ^= v2". (The rotate of v2 makes a difference, but * it still cancels out half of the bits in v2 for no benefit.) * Second, since the last combining operation was xor, continue the * pattern of alternating xor/add for a tiny bit of extra non-linearity. */ static inline u32 siprand_u32(struct siprand_state *s) { unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3; unsigned long n = raw_cpu_read(net_rand_noise); v3 ^= n; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= n; s->v0 = v0; s->v1 = v1; s->v2 = v2; s->v3 = v3; return v1 + v3; } /** * prandom_u32 - pseudo random number generator * * A 32 bit pseudo-random number is generated using a fast * algorithm suitable for simulation. This algorithm is NOT * considered safe for cryptographic use. */ u32 prandom_u32(void) { struct siprand_state *state = get_cpu_ptr(&net_rand_state); u32 res = siprand_u32(state); put_cpu_ptr(&net_rand_state); return res; } EXPORT_SYMBOL(prandom_u32); /** * prandom_bytes - get the requested number of pseudo-random bytes * @buf: where to copy the pseudo-random bytes to * @bytes: the requested number of bytes */ void prandom_bytes(void *buf, size_t bytes) { struct siprand_state *state = get_cpu_ptr(&net_rand_state); u8 *ptr = buf; while (bytes >= sizeof(u32)) { put_unaligned(siprand_u32(state), (u32 *)ptr); ptr += sizeof(u32); bytes -= sizeof(u32); } if (bytes > 0) { u32 rem = siprand_u32(state); do { *ptr++ = (u8)rem; rem >>= BITS_PER_BYTE; } while (--bytes > 0); } put_cpu_ptr(&net_rand_state); } EXPORT_SYMBOL(prandom_bytes); /** * prandom_seed - add entropy to pseudo random number generator * @entropy: entropy value * * Add some additional seed material to the prandom pool. * The "entropy" is actually our IP address (the only caller is * the network code), not for unpredictability, but to ensure that * different machines are initialized differently. */ void prandom_seed(u32 entropy) { int i; add_device_randomness(&entropy, sizeof(entropy)); for_each_possible_cpu(i) { struct siprand_state *state = per_cpu_ptr(&net_rand_state, i); unsigned long v0 = state->v0, v1 = state->v1; unsigned long v2 = state->v2, v3 = state->v3; do { v3 ^= entropy; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= entropy; } while (unlikely(!v0 || !v1 || !v2 || !v3)); WRITE_ONCE(state->v0, v0); WRITE_ONCE(state->v1, v1); WRITE_ONCE(state->v2, v2); WRITE_ONCE(state->v3, v3); } } EXPORT_SYMBOL(prandom_seed); /* * Generate some initially weak seeding values to allow * the prandom_u32() engine to be started. */ static int __init prandom_init_early(void) { int i; unsigned long v0, v1, v2, v3; if (!arch_get_random_long(&v0)) v0 = jiffies; if (!arch_get_random_long(&v1)) v1 = random_get_entropy(); v2 = v0 ^ PRND_K0; v3 = v1 ^ PRND_K1; for_each_possible_cpu(i) { struct siprand_state *state; v3 ^= i; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= i; state = per_cpu_ptr(&net_rand_state, i); state->v0 = v0; state->v1 = v1; state->v2 = v2; state->v3 = v3; } return 0; } core_initcall(prandom_init_early); /* Stronger reseeding when available, and periodically thereafter. */ static void prandom_reseed(struct timer_list *unused); static DEFINE_TIMER(seed_timer, prandom_reseed); static void prandom_reseed(struct timer_list *unused) { unsigned long expires; int i; /* * Reinitialize each CPU's PRNG with 128 bits of key. * No locking on the CPUs, but then somewhat random results are, * well, expected. */ for_each_possible_cpu(i) { struct siprand_state *state; unsigned long v0 = get_random_long(), v2 = v0 ^ PRND_K0; unsigned long v1 = get_random_long(), v3 = v1 ^ PRND_K1; #if BITS_PER_LONG == 32 int j; /* * On 32-bit machines, hash in two extra words to * approximate 128-bit key length. Not that the hash * has that much security, but this prevents a trivial * 64-bit brute force. */ for (j = 0; j < 2; j++) { unsigned long m = get_random_long(); v3 ^= m; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= m; } #endif /* * Probably impossible in practice, but there is a * theoretical risk that a race between this reseeding * and the target CPU writing its state back could * create the all-zero SipHash fixed point. * * To ensure that never happens, ensure the state * we write contains no zero words. */ state = per_cpu_ptr(&net_rand_state, i); WRITE_ONCE(state->v0, v0 ? v0 : -1ul); WRITE_ONCE(state->v1, v1 ? v1 : -1ul); WRITE_ONCE(state->v2, v2 ? v2 : -1ul); WRITE_ONCE(state->v3, v3 ? v3 : -1ul); } /* reseed every ~60 seconds, in [40 .. 80) interval with slack */ expires = round_jiffies(jiffies + 40 * HZ + prandom_u32_max(40 * HZ)); mod_timer(&seed_timer, expires); } /* * The random ready callback can be called from almost any interrupt. * To avoid worrying about whether it's safe to delay that interrupt * long enough to seed all CPUs, just schedule an immediate timer event. */ static int prandom_timer_start(struct notifier_block *nb, unsigned long action, void *data) { mod_timer(&seed_timer, jiffies); return 0; } #ifdef CONFIG_RANDOM32_SELFTEST /* Principle: True 32-bit random numbers will all have 16 differing bits on * average. For each 32-bit number, there are 601M numbers differing by 16 * bits, and 89% of the numbers differ by at least 12 bits. Note that more * than 16 differing bits also implies a correlation with inverted bits. Thus * we take 1024 random numbers and compare each of them to the other ones, * counting the deviation of correlated bits to 16. Constants report 32, * counters 32-log2(TEST_SIZE), and pure randoms, around 6 or lower. With the * u32 total, TEST_SIZE may be as large as 4096 samples. */ #define TEST_SIZE 1024 static int __init prandom32_state_selftest(void) { unsigned int x, y, bits, samples; u32 xor, flip; u32 total; u32 *data; data = kmalloc(sizeof(*data) * TEST_SIZE, GFP_KERNEL); if (!data) return 0; for (samples = 0; samples < TEST_SIZE; samples++) data[samples] = prandom_u32(); flip = total = 0; for (x = 0; x < samples; x++) { for (y = 0; y < samples; y++) { if (x == y) continue; xor = data[x] ^ data[y]; flip |= xor; bits = hweight32(xor); total += (bits - 16) * (bits - 16); } } /* We'll return the average deviation as 2*sqrt(corr/samples), which * is also sqrt(4*corr/samples) which provides a better resolution. */ bits = int_sqrt(total / (samples * (samples - 1)) * 4); if (bits > 6) pr_warn("prandom32: self test failed (at least %u bits" " correlated, fixed_mask=%#x fixed_value=%#x\n", bits, ~flip, data[0] & ~flip); else pr_info("prandom32: self test passed (less than %u bits" " correlated)\n", bits+1); kfree(data); return 0; } core_initcall(prandom32_state_selftest); #endif /* CONFIG_RANDOM32_SELFTEST */ /* * Start periodic full reseeding as soon as strong * random numbers are available. */ static int __init prandom_init_late(void) { static struct notifier_block random_ready = { .notifier_call = prandom_timer_start }; int ret = register_random_ready_notifier(&random_ready); if (ret == -EALREADY) { prandom_timer_start(&random_ready, 0, NULL); ret = 0; } return ret; } late_initcall(prandom_init_late); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CTYPE_H #define _LINUX_CTYPE_H /* * NOTE! This ctype does not handle EOF like the standard C * library is required to. */ #define _U 0x01 /* upper */ #define _L 0x02 /* lower */ #define _D 0x04 /* digit */ #define _C 0x08 /* cntrl */ #define _P 0x10 /* punct */ #define _S 0x20 /* white space (space/lf/tab) */ #define _X 0x40 /* hex digit */ #define _SP 0x80 /* hard space (0x20) */ extern const unsigned char _ctype[]; #define __ismask(x) (_ctype[(int)(unsigned char)(x)]) #define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0) #define isalpha(c) ((__ismask(c)&(_U|_L)) != 0) #define iscntrl(c) ((__ismask(c)&(_C)) != 0) static inline int isdigit(int c) { return '0' <= c && c <= '9'; } #define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0) #define islower(c) ((__ismask(c)&(_L)) != 0) #define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0) #define ispunct(c) ((__ismask(c)&(_P)) != 0) /* Note: isspace() must return false for %NUL-terminator */ #define isspace(c) ((__ismask(c)&(_S)) != 0) #define isupper(c) ((__ismask(c)&(_U)) != 0) #define isxdigit(c) ((__ismask(c)&(_D|_X)) != 0) #define isascii(c) (((unsigned char)(c))<=0x7f) #define toascii(c) (((unsigned char)(c))&0x7f) static inline unsigned char __tolower(unsigned char c) { if (isupper(c)) c -= 'A'-'a'; return c; } static inline unsigned char __toupper(unsigned char c) { if (islower(c)) c -= 'a'-'A'; return c; } #define tolower(c) __tolower(c) #define toupper(c) __toupper(c) /* * Fast implementation of tolower() for internal usage. Do not use in your * code. */ static inline char _tolower(const char c) { return c | 0x20; } /* Fast check for octal digit */ static inline int isodigit(const char c) { return c >= '0' && c <= '7'; } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BLOCK_BLK_PM_H_ #define _BLOCK_BLK_PM_H_ #include <linux/pm_runtime.h> #ifdef CONFIG_PM static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { if (!q->dev || !blk_queue_pm_only(q)) return 1; /* Nothing to do */ if (pm && q->rpm_status != RPM_SUSPENDED) return 1; /* Request allowed */ pm_request_resume(q->dev); return 0; } static inline void blk_pm_mark_last_busy(struct request *rq) { if (rq->q->dev && !(rq->rq_flags & RQF_PM)) pm_runtime_mark_last_busy(rq->q->dev); } static inline void blk_pm_requeue_request(struct request *rq) { lockdep_assert_held(&rq->q->queue_lock); if (rq->q->dev && !(rq->rq_flags & RQF_PM)) rq->q->nr_pending--; } static inline void blk_pm_add_request(struct request_queue *q, struct request *rq) { lockdep_assert_held(&q->queue_lock); if (q->dev && !(rq->rq_flags & RQF_PM)) q->nr_pending++; } static inline void blk_pm_put_request(struct request *rq) { lockdep_assert_held(&rq->q->queue_lock); if (rq->q->dev && !(rq->rq_flags & RQF_PM)) --rq->q->nr_pending; } #else static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q) { return 1; } static inline void blk_pm_mark_last_busy(struct request *rq) { } static inline void blk_pm_requeue_request(struct request *rq) { } static inline void blk_pm_add_request(struct request_queue *q, struct request *rq) { } static inline void blk_pm_put_request(struct request *rq) { } #endif #endif /* _BLOCK_BLK_PM_H_ */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fs_context; struct fs_parameter_spec; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; extern int sysctl_protected_fifos; extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)0x1) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)0x2) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)0x4) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)0x8) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) /* File is opened with O_NDELAY (only set for block devices) */ #define FMODE_NDELAY ((__force fmode_t)0x40) /* File is opened with O_EXCL (only set for block devices) */ #define FMODE_EXCL ((__force fmode_t)0x80) /* File is opened using open(.., 3, ..) and is writeable only for ioctls (specialy hack for floppy.c) */ #define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)0x400) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)0x800) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)0x20000) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) #define FMODE_OPENED ((__force fmode_t)0x80000) #define FMODE_CREATED ((__force fmode_t)0x100000) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)0x8000000) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) /* File supports async buffered reads */ #define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; kuid_t ia_uid; kgid_t ia_gid; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by readpage(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; #define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ #define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct * helper code (eg buffer layer) * to clear GFP_FS from alloc */ /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* * Write life time hint values. * Stored in struct inode as u8. */ enum rw_hint { WRITE_LIFE_NOT_SET = 0, WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, }; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) struct kiocb { struct file *ki_filp; /* The 'ki_filp' pointer is shared in a union for aio */ randomized_struct_fields_start loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ union { unsigned int ki_cookie; /* for ->iopoll */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ }; randomized_struct_fields_end }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet * have multiple different users of the data that * we read from a file. * * The simplest case just copies the data to user * mode. */ typedef struct { size_t written; size_t count; union { char __user *buf; void *data; } arg; int error; } read_descriptor_t; typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long); struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); /* * Reads in the requested pages. Unlike ->readpage(), this is * PURELY used for read-ahead!. */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migratepage) (struct address_space *, struct page *, struct page *, enum migrate_mode); bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, unsigned long, unsigned long); void (*is_dirty_writeback) (struct page *, bool *, bool *); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); }; extern const struct address_space_operations empty_aops; /* * pagecache_write_begin/pagecache_write_end must be used by general code * to write into the pagecache. */ int pagecache_write_begin(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @private_lock: For use by the owner of the address_space. * @private_list: For use by the owner of the address_space. * @private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; unsigned long nrexceptional; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t private_lock; struct list_head private_list; void *private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 struct fsnotify_mark_connector; /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; struct timespec64 i_atime; struct timespec64 i_mtime; struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; u8 i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ unsigned long i_state; struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else return inode->i_size; #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else inode->i_size = i_size; #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /* * Track a single file's readahead state */ struct file_ra_state { pgoff_t start; /* where readahead started */ unsigned int size; /* # of readahead pages */ unsigned int async_size; /* do asynchronous readahead when there are only # of pages ahead */ unsigned int ra_pages; /* Maximum readahead window */ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */ loff_t prev_pos; /* Cache last read() position */ }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } struct file { union { struct llist_node fu_llist; struct rcu_head fu_rcuhead; } f_u; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; /* * Protects f_ep_links, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; struct mutex f_pos_lock; loff_t f_pos; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; u64 f_version; #ifdef CONFIG_SECURITY void *f_security; #endif /* needed for tty driver, and maybe others */ void *private_data; #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ struct list_head f_ep_links; struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) { atomic_long_inc(&f->f_count); return f; } #define get_file_rcu_many(x, cnt) \ atomic_long_add_unless(&(x)->f_count, (cnt), 0) #define get_file_rcu(x) get_file_rcu_many((x), 1) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); bool (*lm_breaker_owns_lease)(struct file_lock *); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* that will die - we need it for nfs_lock_info */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock { struct file_lock *fl_blocker; /* The lock, that is blocking us */ struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head fl_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t fl_owner; unsigned int fl_flags; unsigned char fl_type; unsigned int fl_pid; int fl_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t fl_wait; struct file *fl_file; loff_t fl_start; loff_t fl_end; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; } fl_u; } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) #define OFFSET_MAX INT_LIMIT(loff_t) #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); #define locks_inode(f) file_inode(f) #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, unsigned int, struct flock *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_copy_conflock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); extern int locks_delete_block(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec64 *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); extern int lease_modify(struct file_lock *, int, struct list_head *); struct notifier_block; extern int lease_register_notifier(struct notifier_block *); extern void lease_unregister_notifier(struct notifier_block *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); extern bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 __user *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 __user *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } static inline struct dentry *file_dentry(const struct file *file) { return d_real(file->f_path.dentry, file_inode(file)); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(locks_inode(filp), fl); } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { int frozen; /* Is sb frozen? */ wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #ifdef CONFIG_UNICODE struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_marks together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; struct fsnotify_mark_connector __rcu *s_fsnotify_marks; #endif char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ unsigned int s_max_links; fmode_t s_mode; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* * Saved pool identifier for cleancache (-1 means none) */ int cleancache_poolid; struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* * Number of inode/mount/sb objects that are being watched, note that * inodes objects are currently double-accounted. */ atomic_long_t s_fsnotify_connectors; /* Being remounted read-only */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); /** * inode_get_ctime - fetch the current ctime from the inode * @inode: inode from which to fetch ctime * * Grab the current ctime from the inode and return it. */ static inline struct timespec64 inode_get_ctime(const struct inode *inode) { return inode->i_ctime; } /** * inode_set_ctime_to_ts - set the ctime in the inode * @inode: inode in which to set the ctime * @ts: value to set in the ctime field * * Set the ctime in @inode to @ts */ static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_ctime = ts; return ts; } /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /* * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } extern bool inode_owner_or_capable(const struct inode *inode); /* * VFS helper functions.. */ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); struct renamedata { struct inode *old_dir; struct dentry *old_dentry; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) { return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ struct dir_context; typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, bool spin); int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); bool may_pollfree; } __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); int (*mkdir) (struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, struct iov_iter *iter) { return file->f_op->read_iter(kio, iter); } static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, struct iov_iter *iter) { return file->f_op->write_iter(kio, iter); } static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct inode *inode) { return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); } static inline enum rw_hint file_write_hint(struct file *file) { if (file->f_write_hint != WRITE_LIFE_NOT_SET) return file->f_write_hint; return file_inode(file)->i_write_hint; } static inline int iocb_flags(struct file *file); static inline u16 ki_hint_validate(enum rw_hint hint) { typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; if (hint <= max_hint) return hint; return 0; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = iocb_flags(filp), .ki_hint = ki_hint_validate(file_write_hint(filp)), .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, * I_DIRTY_DATASYNC and I_DIRTY_PAGES. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync(). i_atime is the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * mtime has changed in it. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) #define I_DIRTY_DATASYNC (1 << 1) #define I_DIRTY_PAGES (1 << 2) #define __I_NEW 3 #define I_NEW (1 << __I_NEW) #define I_WILL_FREE (1 << 4) #define I_FREEING (1 << 5) #define I_CLEAR (1 << 6) #define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) #define I_REFERENCED (1 << 8) #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define __I_LRU_ISOLATING 19 #define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, struct timespec64 *time, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int sync_inode(struct inode *inode, struct writeback_control *wbc); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) #define fops_put(fops) \ do { if (fops) module_put((fops)->owner); } while(0) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount(struct file_system_type *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); extern long do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec64 *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) #ifdef CONFIG_MANDATORY_FILE_LOCKING extern int locks_mandatory_locked(struct file *); extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char); /* * Candidates for mandatory locking have the setgid bit set * but no group execute bit - an otherwise meaningless combination. */ static inline int __mandatory_lock(struct inode *ino) { return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; } /* * ... and these candidates should be on SB_MANDLOCK mounted fs, * otherwise these will be advisory locks */ static inline int mandatory_lock(struct inode *ino) { return IS_MANDLOCK(ino) && __mandatory_lock(ino); } static inline int locks_verify_locked(struct file *file) { if (mandatory_lock(locks_inode(file))) return locks_mandatory_locked(file); return 0; } static inline int locks_verify_truncate(struct inode *inode, struct file *f, loff_t size) { if (!inode->i_flctx || !mandatory_lock(inode)) return 0; if (size < inode->i_size) { return locks_mandatory_area(inode, f, size, inode->i_size - 1, F_WRLCK); } else { return locks_mandatory_area(inode, f, inode->i_size, size - 1, F_WRLCK); } } #else /* !CONFIG_MANDATORY_FILE_LOCKING */ static inline int locks_mandatory_locked(struct file *file) { return 0; } static inline int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, loff_t end, unsigned char type) { return 0; } static inline int __mandatory_lock(struct inode *inode) { return 0; } static inline int mandatory_lock(struct inode *inode) { return 0; } static inline int locks_verify_locked(struct file *file) { return 0; } static inline int locks_verify_truncate(struct inode *inode, struct file *filp, size_t size) { return 0; } #endif /* CONFIG_MANDATORY_FILE_LOCKING */ #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ int refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); extern long vfs_truncate(const struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); void invalidate_mapping_pagevec(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec); static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) invalidate_mapping_pages(inode->i_mapping, 0, -1); } extern int invalidate_inode_pages2(struct address_space *mapping); extern int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); static inline int filemap_fdatawait(struct address_space *mapping) { return filemap_fdatawait_range(mapping, 0, LLONG_MAX); } extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); extern int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); extern void __filemap_set_wb_err(struct address_space *mapping, int err); static inline int filemap_write_and_wait(struct address_space *mapping) { return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); } extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error * @err: error to be set in mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { /* Fastpath for common case of no error */ if (unlikely(err)) __filemap_set_wb_err(mapping, err); } /** * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * * Grab the errseq_t value from the mapping, and see if it has changed "since" * the given value was sampled. * * If it has then report the latest error set, otherwise return 0. */ static inline int filemap_check_wb_err(struct address_space *mapping, errseq_t since) { return errseq_check(&mapping->wb_err, since); } /** * filemap_sample_wb_err - sample the current errseq_t to test for later errors * @mapping: mapping to be sampled * * Writeback errors are always reported relative to a particular sample point * in the past. This function provides those sample points. */ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) { return errseq_sample(&mapping->wb_err); } /** * file_sample_sb_err - sample the current errseq_t to test for later errors * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. */ static inline errseq_t file_sample_sb_err(struct file *file) { return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb->ki_flags & IOCB_DSYNC) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(d_inode(path->dentry), mask); } extern int __check_sticky(struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * This is used for regular files. * We cannot support write (and maybe mmap read-write shared) accesses and * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode * can have the following values: * 0: no writers, no VM_DENYWRITE mappings * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist * > 0: (i_writecount) users are writing to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(!atomic_read(&inode->i_readcount)); atomic_dec(&inode->i_readcount); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); /* * Userspace may rely on the the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct inode *); extern int file_remove_privs(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from); extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync); extern void block_sync_page(struct page *page); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t no_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif void inode_dio_wait(struct inode *inode); /* * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /* * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } /* * Warn about a page cache invalidation failure diring a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp); extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link_raw(struct dentry *, struct inode *, struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); extern void generic_fillattr(struct inode *, struct kstat *); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); extern struct super_block *get_super_thawed(struct block_device *); extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev); extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct dentry *, struct iattr *); extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern int noop_set_page_dirty(struct page *page); extern void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); extern int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, long, struct file_lock **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); #ifdef CONFIG_UNICODE extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); #endif #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int buffer_migrate_page_norefs(struct address_space *, struct page *, struct page *, enum migrate_mode); #else #define buffer_migrate_page NULL #define buffer_migrate_page_norefs NULL #endif extern int setattr_prepare(struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; ki->ki_flags |= kiocb_flags; return 0; } static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; /* * Don't strictly need d_lock here? If the parent ino could change * then surely we'd have a deeper race in the caller? */ spin_lock(&dentry->d_lock); res = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return res; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0; } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0; } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, parent_ino(file->f_path.dentry), DT_DIR) == 0; } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, unsigned int flags); int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, struct fsxattr *fa); static inline void simple_fill_fsxattr(struct fsxattr *fa, __u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_xflags = xflags; } /* * Flush file data before changing attributes. Caller must hold any locks * required to prevent further writes to this file until we're done setting * flags. */ static inline int inode_drain_writes(struct inode *inode) { inode_dio_wait(inode); return filemap_write_and_wait(inode->i_mapping); } #endif /* _LINUX_FS_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 | // SPDX-License-Identifier: GPL-2.0+ /* * Universal/legacy driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. * * Supports: ISA-compatible 8250/16550 ports * PNP 8250/16550 ports * early_serial_setup() ports * userspace-configurable "phantom" ports * "serial8250" platform devices * serial8250_register_8250_port() ports */ #include <linux/acpi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/console.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/io.h> #ifdef CONFIG_SPARC #include <linux/sunserialcore.h> #endif #include <asm/irq.h> #include "8250.h" /* * Configuration: * share_irqs - whether we pass IRQF_SHARED to request_irq(). This option * is unsafe when used on edge-triggered interrupts. */ static unsigned int share_irqs = SERIAL8250_SHARE_IRQS; static unsigned int nr_uarts = CONFIG_SERIAL_8250_RUNTIME_UARTS; static struct uart_driver serial8250_reg; static unsigned int skip_txen_test; /* force skip of txen test at init time */ #define PASS_LIMIT 512 #include <asm/serial.h> /* * SERIAL_PORT_DFNS tells us about built-in ports that have no * standard enumeration mechanism. Platforms that can find all * serial ports via mechanisms like ACPI or PCI need not supply it. */ #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif static const struct old_serial_port old_serial_port[] = { SERIAL_PORT_DFNS /* defined in asm/serial.h */ }; #define UART_NR CONFIG_SERIAL_8250_NR_UARTS #ifdef CONFIG_SERIAL_8250_RSA #define PORT_RSA_MAX 4 static unsigned long probe_rsa[PORT_RSA_MAX]; static unsigned int probe_rsa_count; #endif /* CONFIG_SERIAL_8250_RSA */ struct irq_info { struct hlist_node node; int irq; spinlock_t lock; /* Protects list not the hash */ struct list_head *head; }; #define NR_IRQ_HASH 32 /* Can be adjusted later */ static struct hlist_head irq_lists[NR_IRQ_HASH]; static DEFINE_MUTEX(hash_mutex); /* Used to walk the hash */ /* * This is the serial driver's interrupt routine. * * Arjan thinks the old way was overly complex, so it got simplified. * Alan disagrees, saying that need the complexity to handle the weird * nature of ISA shared interrupts. (This is a special exception.) * * In order to handle ISA shared interrupts properly, we need to check * that all ports have been serviced, and therefore the ISA interrupt * line has been de-asserted. * * This means we need to loop through all ports. checking that they * don't have an interrupt pending. */ static irqreturn_t serial8250_interrupt(int irq, void *dev_id) { struct irq_info *i = dev_id; struct list_head *l, *end = NULL; int pass_counter = 0, handled = 0; pr_debug("%s(%d): start\n", __func__, irq); spin_lock(&i->lock); l = i->head; do { struct uart_8250_port *up; struct uart_port *port; up = list_entry(l, struct uart_8250_port, list); port = &up->port; if (port->handle_irq(port)) { handled = 1; end = NULL; } else if (end == NULL) end = l; l = l->next; if (l == i->head && pass_counter++ > PASS_LIMIT) break; } while (l != end); spin_unlock(&i->lock); pr_debug("%s(%d): end\n", __func__, irq); return IRQ_RETVAL(handled); } /* * To support ISA shared interrupts, we need to have one interrupt * handler that ensures that the IRQ line has been deasserted * before returning. Failing to do this will result in the IRQ * line being stuck active, and, since ISA irqs are edge triggered, * no more IRQs will be seen. */ static void serial_do_unlink(struct irq_info *i, struct uart_8250_port *up) { spin_lock_irq(&i->lock); if (!list_empty(i->head)) { if (i->head == &up->list) i->head = i->head->next; list_del(&up->list); } else { BUG_ON(i->head != &up->list); i->head = NULL; } spin_unlock_irq(&i->lock); /* List empty so throw away the hash node */ if (i->head == NULL) { hlist_del(&i->node); kfree(i); } } static int serial_link_irq_chain(struct uart_8250_port *up) { struct hlist_head *h; struct hlist_node *n; struct irq_info *i; int ret; mutex_lock(&hash_mutex); h = &irq_lists[up->port.irq % NR_IRQ_HASH]; hlist_for_each(n, h) { i = hlist_entry(n, struct irq_info, node); if (i->irq == up->port.irq) break; } if (n == NULL) { i = kzalloc(sizeof(struct irq_info), GFP_KERNEL); if (i == NULL) { mutex_unlock(&hash_mutex); return -ENOMEM; } spin_lock_init(&i->lock); i->irq = up->port.irq; hlist_add_head(&i->node, h); } mutex_unlock(&hash_mutex); spin_lock_irq(&i->lock); if (i->head) { list_add(&up->list, i->head); spin_unlock_irq(&i->lock); ret = 0; } else { INIT_LIST_HEAD(&up->list); i->head = &up->list; spin_unlock_irq(&i->lock); ret = request_irq(up->port.irq, serial8250_interrupt, up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); } return ret; } static void serial_unlink_irq_chain(struct uart_8250_port *up) { /* * yes, some broken gcc emit "warning: 'i' may be used uninitialized" * but no, we are not going to take a patch that assigns NULL below. */ struct irq_info *i; struct hlist_node *n; struct hlist_head *h; mutex_lock(&hash_mutex); h = &irq_lists[up->port.irq % NR_IRQ_HASH]; hlist_for_each(n, h) { i = hlist_entry(n, struct irq_info, node); if (i->irq == up->port.irq) break; } BUG_ON(n == NULL); BUG_ON(i->head == NULL); if (list_empty(i->head)) free_irq(up->port.irq, i); serial_do_unlink(i, up); mutex_unlock(&hash_mutex); } /* * This function is used to handle ports that do not have an * interrupt. This doesn't work very well for 16450's, but gives * barely passable results for a 16550A. (Although at the expense * of much CPU overhead). */ static void serial8250_timeout(struct timer_list *t) { struct uart_8250_port *up = from_timer(up, t, timer); up->port.handle_irq(&up->port); mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port)); } static void serial8250_backup_timeout(struct timer_list *t) { struct uart_8250_port *up = from_timer(up, t, timer); unsigned int iir, ier = 0, lsr; unsigned long flags; spin_lock_irqsave(&up->port.lock, flags); /* * Must disable interrupts or else we risk racing with the interrupt * based handler. */ if (up->port.irq) { ier = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); } iir = serial_in(up, UART_IIR); /* * This should be a safe test for anyone who doesn't trust the * IIR bits on their UART, but it's specifically designed for * the "Diva" UART used on the management processor on many HP * ia64 and parisc boxes. */ lsr = serial_in(up, UART_LSR); up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; if ((iir & UART_IIR_NO_INT) && (up->ier & UART_IER_THRI) && (!uart_circ_empty(&up->port.state->xmit) || up->port.x_char) && (lsr & UART_LSR_THRE)) { iir &= ~(UART_IIR_ID | UART_IIR_NO_INT); iir |= UART_IIR_THRI; } if (!(iir & UART_IIR_NO_INT)) serial8250_tx_chars(up); if (up->port.irq) serial_out(up, UART_IER, ier); spin_unlock_irqrestore(&up->port.lock, flags); /* Standard timer interval plus 0.2s to keep the port running */ mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port) + HZ / 5); } static void univ8250_setup_timer(struct uart_8250_port *up) { struct uart_port *port = &up->port; /* * The above check will only give an accurate result the first time * the port is opened so this value needs to be preserved. */ if (up->bugs & UART_BUG_THRE) { pr_debug("%s - using backup timer\n", port->name); up->timer.function = serial8250_backup_timeout; mod_timer(&up->timer, jiffies + uart_poll_timeout(port) + HZ / 5); } /* * If the "interrupt" for this port doesn't correspond with any * hardware interrupt, we use a timer-based system. The original * driver used to do this with IRQ0. */ if (!port->irq) mod_timer(&up->timer, jiffies + uart_poll_timeout(port)); } static int univ8250_setup_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (port->irq) return serial_link_irq_chain(up); return 0; } static void univ8250_release_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; del_timer_sync(&up->timer); up->timer.function = serial8250_timeout; if (port->irq) serial_unlink_irq_chain(up); } #ifdef CONFIG_SERIAL_8250_RSA static int serial8250_request_rsa_resource(struct uart_8250_port *up) { unsigned long start = UART_RSA_BASE << up->port.regshift; unsigned int size = 8 << up->port.regshift; struct uart_port *port = &up->port; int ret = -EINVAL; switch (port->iotype) { case UPIO_HUB6: case UPIO_PORT: start += port->iobase; if (request_region(start, size, "serial-rsa")) ret = 0; else ret = -EBUSY; break; } return ret; } static void serial8250_release_rsa_resource(struct uart_8250_port *up) { unsigned long offset = UART_RSA_BASE << up->port.regshift; unsigned int size = 8 << up->port.regshift; struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_HUB6: case UPIO_PORT: release_region(port->iobase + offset, size); break; } } #endif static const struct uart_ops *base_ops; static struct uart_ops univ8250_port_ops; static const struct uart_8250_ops univ8250_driver_ops = { .setup_irq = univ8250_setup_irq, .release_irq = univ8250_release_irq, .setup_timer = univ8250_setup_timer, }; static struct uart_8250_port serial8250_ports[UART_NR]; /** * serial8250_get_port - retrieve struct uart_8250_port * @line: serial line number * * This function retrieves struct uart_8250_port for the specific line. * This struct *must* *not* be used to perform a 8250 or serial core operation * which is not accessible otherwise. Its only purpose is to make the struct * accessible to the runtime-pm callbacks for context suspend/restore. * The lock assumption made here is none because runtime-pm suspend/resume * callbacks should not be invoked if there is any operation performed on the * port. */ struct uart_8250_port *serial8250_get_port(int line) { return &serial8250_ports[line]; } EXPORT_SYMBOL_GPL(serial8250_get_port); static void (*serial8250_isa_config)(int port, struct uart_port *up, u32 *capabilities); void serial8250_set_isa_configurator( void (*v)(int port, struct uart_port *up, u32 *capabilities)) { serial8250_isa_config = v; } EXPORT_SYMBOL(serial8250_set_isa_configurator); #ifdef CONFIG_SERIAL_8250_RSA static void univ8250_config_port(struct uart_port *port, int flags) { struct uart_8250_port *up = up_to_u8250p(port); up->probe &= ~UART_PROBE_RSA; if (port->type == PORT_RSA) { if (serial8250_request_rsa_resource(up) == 0) up->probe |= UART_PROBE_RSA; } else if (flags & UART_CONFIG_TYPE) { int i; for (i = 0; i < probe_rsa_count; i++) { if (probe_rsa[i] == up->port.iobase) { if (serial8250_request_rsa_resource(up) == 0) up->probe |= UART_PROBE_RSA; break; } } } base_ops->config_port(port, flags); if (port->type != PORT_RSA && up->probe & UART_PROBE_RSA) serial8250_release_rsa_resource(up); } static int univ8250_request_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); int ret; ret = base_ops->request_port(port); if (ret == 0 && port->type == PORT_RSA) { ret = serial8250_request_rsa_resource(up); if (ret < 0) base_ops->release_port(port); } return ret; } static void univ8250_release_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (port->type == PORT_RSA) serial8250_release_rsa_resource(up); base_ops->release_port(port); } static void univ8250_rsa_support(struct uart_ops *ops) { ops->config_port = univ8250_config_port; ops->request_port = univ8250_request_port; ops->release_port = univ8250_release_port; } #else #define univ8250_rsa_support(x) do { } while (0) #endif /* CONFIG_SERIAL_8250_RSA */ static inline void serial8250_apply_quirks(struct uart_8250_port *up) { up->port.quirks |= skip_txen_test ? UPQ_NO_TXEN_TEST : 0; } static void __init serial8250_isa_init_ports(void) { struct uart_8250_port *up; static int first = 1; int i, irqflag = 0; if (!first) return; first = 0; if (nr_uarts > UART_NR) nr_uarts = UART_NR; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; struct uart_port *port = &up->port; port->line = i; serial8250_init_port(up); if (!base_ops) base_ops = port->ops; port->ops = &univ8250_port_ops; timer_setup(&up->timer, serial8250_timeout, 0); up->ops = &univ8250_driver_ops; /* * ALPHA_KLUDGE_MCR needs to be killed. */ up->mcr_mask = ~ALPHA_KLUDGE_MCR; up->mcr_force = ALPHA_KLUDGE_MCR; serial8250_set_defaults(up); } /* chain base port ops to support Remote Supervisor Adapter */ univ8250_port_ops = *base_ops; univ8250_rsa_support(&univ8250_port_ops); if (share_irqs) irqflag = IRQF_SHARED; for (i = 0, up = serial8250_ports; i < ARRAY_SIZE(old_serial_port) && i < nr_uarts; i++, up++) { struct uart_port *port = &up->port; port->iobase = old_serial_port[i].port; port->irq = irq_canonicalize(old_serial_port[i].irq); port->irqflags = 0; port->uartclk = old_serial_port[i].baud_base * 16; port->flags = old_serial_port[i].flags; port->hub6 = 0; port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; port->irqflags |= irqflag; if (serial8250_isa_config != NULL) serial8250_isa_config(i, &up->port, &up->capabilities); } } static void __init serial8250_register_ports(struct uart_driver *drv, struct device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type == PORT_8250_CIR) continue; if (up->port.dev) continue; up->port.dev = dev; if (uart_console_enabled(&up->port)) pm_runtime_get_sync(up->port.dev); serial8250_apply_quirks(up); uart_add_one_port(drv, &up->port); } } #ifdef CONFIG_SERIAL_8250_CONSOLE static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { struct uart_8250_port *up = &serial8250_ports[co->index]; serial8250_console_write(up, s, count); } static int univ8250_console_setup(struct console *co, char *options) { struct uart_port *port; int retval; /* * Check whether an invalid uart number has been specified, and * if so, search for the first available port that does have * console support. */ if (co->index >= nr_uarts) co->index = 0; port = &serial8250_ports[co->index].port; /* link port to console */ port->cons = co; retval = serial8250_console_setup(port, options, false); if (retval != 0) port->cons = NULL; return retval; } static int univ8250_console_exit(struct console *co) { struct uart_port *port; port = &serial8250_ports[co->index].port; return serial8250_console_exit(port); } /** * univ8250_console_match - non-standard console matching * @co: registering console * @name: name from console command line * @idx: index from console command line * @options: ptr to option string from console command line * * Only attempts to match console command lines of the form: * console=uart[8250],io|mmio|mmio16|mmio32,<addr>[,<options>] * console=uart[8250],0x<addr>[,<options>] * This form is used to register an initial earlycon boot console and * replace it with the serial8250_console at 8250 driver init. * * Performs console setup for a match (as required by interface) * If no <options> are specified, then assume the h/w is already setup. * * Returns 0 if console matches; otherwise non-zero to use default matching */ static int univ8250_console_match(struct console *co, char *name, int idx, char *options) { char match[] = "uart"; /* 8250-specific earlycon name */ unsigned char iotype; resource_size_t addr; int i; if (strncmp(name, match, 4) != 0) return -ENODEV; if (uart_parse_earlycon(options, &iotype, &addr, &options)) return -ENODEV; /* try to match the port specified on the command line */ for (i = 0; i < nr_uarts; i++) { struct uart_port *port = &serial8250_ports[i].port; if (port->iotype != iotype) continue; if ((iotype == UPIO_MEM || iotype == UPIO_MEM16 || iotype == UPIO_MEM32 || iotype == UPIO_MEM32BE) && (port->mapbase != addr)) continue; if (iotype == UPIO_PORT && port->iobase != addr) continue; co->index = i; port->cons = co; return serial8250_console_setup(port, options, true); } return -ENODEV; } static struct console univ8250_console = { .name = "ttyS", .write = univ8250_console_write, .device = uart_console_device, .setup = univ8250_console_setup, .exit = univ8250_console_exit, .match = univ8250_console_match, .flags = CON_PRINTBUFFER | CON_ANYTIME, .index = -1, .data = &serial8250_reg, }; static int __init univ8250_console_init(void) { if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); register_console(&univ8250_console); return 0; } console_initcall(univ8250_console_init); #define SERIAL8250_CONSOLE (&univ8250_console) #else #define SERIAL8250_CONSOLE NULL #endif static struct uart_driver serial8250_reg = { .owner = THIS_MODULE, .driver_name = "serial", .dev_name = "ttyS", .major = TTY_MAJOR, .minor = 64, .cons = SERIAL8250_CONSOLE, }; /* * early_serial_setup - early registration for 8250 ports * * Setup an 8250 port structure prior to console initialisation. Use * after console initialisation will cause undefined behaviour. */ int __init early_serial_setup(struct uart_port *port) { struct uart_port *p; if (port->line >= ARRAY_SIZE(serial8250_ports) || nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); p = &serial8250_ports[port->line].port; p->iobase = port->iobase; p->membase = port->membase; p->irq = port->irq; p->irqflags = port->irqflags; p->uartclk = port->uartclk; p->fifosize = port->fifosize; p->regshift = port->regshift; p->iotype = port->iotype; p->flags = port->flags; p->mapbase = port->mapbase; p->mapsize = port->mapsize; p->private_data = port->private_data; p->type = port->type; p->line = port->line; serial8250_set_defaults(up_to_u8250p(p)); if (port->serial_in) p->serial_in = port->serial_in; if (port->serial_out) p->serial_out = port->serial_out; if (port->handle_irq) p->handle_irq = port->handle_irq; return 0; } /** * serial8250_suspend_port - suspend one serial port * @line: serial line number * * Suspend one serial port. */ void serial8250_suspend_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; if (!console_suspend_enabled && uart_console(port) && port->type != PORT_8250) { unsigned char canary = 0xa5; serial_out(up, UART_SCR, canary); if (serial_in(up, UART_SCR) == canary) up->canary = canary; } uart_suspend_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_suspend_port); /** * serial8250_resume_port - resume one serial port * @line: serial line number * * Resume one serial port. */ void serial8250_resume_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; up->canary = 0; if (up->capabilities & UART_NATSEMI) { /* Ensure it's still in high speed mode */ serial_port_out(port, UART_LCR, 0xE0); ns16550a_goto_highspeed(up); serial_port_out(port, UART_LCR, 0); port->uartclk = 921600*16; } uart_resume_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_resume_port); /* * Register a set of serial devices attached to a platform device. The * list is terminated with a zero flags entry, which means we expect * all entries to have at least UPF_BOOT_AUTOCONF set. */ static int serial8250_probe(struct platform_device *dev) { struct plat_serial8250_port *p = dev_get_platdata(&dev->dev); struct uart_8250_port uart; int ret, i, irqflag = 0; memset(&uart, 0, sizeof(uart)); if (share_irqs) irqflag = IRQF_SHARED; for (i = 0; p && p->flags != 0; p++, i++) { uart.port.iobase = p->iobase; uart.port.membase = p->membase; uart.port.irq = p->irq; uart.port.irqflags = p->irqflags; uart.port.uartclk = p->uartclk; uart.port.regshift = p->regshift; uart.port.iotype = p->iotype; uart.port.flags = p->flags; uart.port.mapbase = p->mapbase; uart.port.hub6 = p->hub6; uart.port.has_sysrq = p->has_sysrq; uart.port.private_data = p->private_data; uart.port.type = p->type; uart.port.serial_in = p->serial_in; uart.port.serial_out = p->serial_out; uart.port.handle_irq = p->handle_irq; uart.port.handle_break = p->handle_break; uart.port.set_termios = p->set_termios; uart.port.set_ldisc = p->set_ldisc; uart.port.get_mctrl = p->get_mctrl; uart.port.pm = p->pm; uart.port.dev = &dev->dev; uart.port.irqflags |= irqflag; ret = serial8250_register_8250_port(&uart); if (ret < 0) { dev_err(&dev->dev, "unable to register port at index %d " "(IO%lx MEM%llx IRQ%d): %d\n", i, p->iobase, (unsigned long long)p->mapbase, p->irq, ret); } } return 0; } /* * Remove serial ports registered against a platform device. */ static int serial8250_remove(struct platform_device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.dev == &dev->dev) serial8250_unregister_port(i); } return 0; } static int serial8250_suspend(struct platform_device *dev, pm_message_t state) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) uart_suspend_port(&serial8250_reg, &up->port); } return 0; } static int serial8250_resume(struct platform_device *dev) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) serial8250_resume_port(i); } return 0; } static struct platform_driver serial8250_isa_driver = { .probe = serial8250_probe, .remove = serial8250_remove, .suspend = serial8250_suspend, .resume = serial8250_resume, .driver = { .name = "serial8250", }, }; /* * This "device" covers _all_ ISA 8250-compatible serial devices listed * in the table in include/asm/serial.h */ static struct platform_device *serial8250_isa_devs; /* * serial8250_register_8250_port and serial8250_unregister_port allows for * 16x50 serial ports to be configured at run-time, to support PCMCIA * modems and PCI multiport cards. */ static DEFINE_MUTEX(serial_mutex); static struct uart_8250_port *serial8250_find_match_or_unused(struct uart_port *port) { int i; /* * First, find a port entry which matches. */ for (i = 0; i < nr_uarts; i++) if (uart_match_port(&serial8250_ports[i].port, port)) return &serial8250_ports[i]; /* try line number first if still available */ i = port->line; if (i < nr_uarts && serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * We didn't find a matching entry, so look for the first * free entry. We look for one which hasn't been previously * used (indicated by zero iobase). */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * That also failed. Last resort is to find any entry which * doesn't have a real port associated with it. */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN) return &serial8250_ports[i]; return NULL; } static void serial_8250_overrun_backoff_work(struct work_struct *work) { struct uart_8250_port *up = container_of(to_delayed_work(work), struct uart_8250_port, overrun_backoff); struct uart_port *port = &up->port; unsigned long flags; spin_lock_irqsave(&port->lock, flags); up->ier |= UART_IER_RLSI | UART_IER_RDI; up->port.read_status_mask |= UART_LSR_DR; serial_out(up, UART_IER, up->ier); spin_unlock_irqrestore(&port->lock, flags); } /** * serial8250_register_8250_port - register a serial port * @up: serial port template * * Configure the serial port specified by the request. If the * port exists and is in use, it is hung up and unregistered * first. * * The port is then probed and if necessary the IRQ is autodetected * If this fails an error is returned. * * On success the port is ready to use and the line number is returned. */ int serial8250_register_8250_port(struct uart_8250_port *up) { struct uart_8250_port *uart; int ret = -ENOSPC; if (up->port.uartclk == 0) return -EINVAL; mutex_lock(&serial_mutex); uart = serial8250_find_match_or_unused(&up->port); if (uart && uart->port.type != PORT_8250_CIR) { struct mctrl_gpios *gpios; if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); uart->port.iobase = up->port.iobase; uart->port.membase = up->port.membase; uart->port.irq = up->port.irq; uart->port.irqflags = up->port.irqflags; uart->port.uartclk = up->port.uartclk; uart->port.fifosize = up->port.fifosize; uart->port.regshift = up->port.regshift; uart->port.iotype = up->port.iotype; uart->port.flags = up->port.flags | UPF_BOOT_AUTOCONF; uart->bugs = up->bugs; uart->port.mapbase = up->port.mapbase; uart->port.mapsize = up->port.mapsize; uart->port.private_data = up->port.private_data; uart->tx_loadsz = up->tx_loadsz; uart->capabilities = up->capabilities; uart->port.throttle = up->port.throttle; uart->port.unthrottle = up->port.unthrottle; uart->port.rs485_config = up->port.rs485_config; uart->port.rs485_supported = up->port.rs485_supported; uart->port.rs485 = up->port.rs485; uart->rs485_start_tx = up->rs485_start_tx; uart->rs485_stop_tx = up->rs485_stop_tx; uart->dma = up->dma; /* Take tx_loadsz from fifosize if it wasn't set separately */ if (uart->port.fifosize && !uart->tx_loadsz) uart->tx_loadsz = uart->port.fifosize; if (up->port.dev) { uart->port.dev = up->port.dev; ret = uart_get_rs485_mode(&uart->port); if (ret) goto err; } if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; /* * Only call mctrl_gpio_init(), if the device has no ACPI * companion device */ if (!has_acpi_companion(uart->port.dev)) { gpios = mctrl_gpio_init(&uart->port, 0); if (IS_ERR(gpios)) { ret = PTR_ERR(gpios); goto err; } else { uart->gpios = gpios; } } serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ if (up->port.serial_in) uart->port.serial_in = up->port.serial_in; if (up->port.serial_out) uart->port.serial_out = up->port.serial_out; if (up->port.handle_irq) uart->port.handle_irq = up->port.handle_irq; /* Possibly override set_termios call */ if (up->port.set_termios) uart->port.set_termios = up->port.set_termios; if (up->port.set_ldisc) uart->port.set_ldisc = up->port.set_ldisc; if (up->port.get_mctrl) uart->port.get_mctrl = up->port.get_mctrl; if (up->port.set_mctrl) uart->port.set_mctrl = up->port.set_mctrl; if (up->port.get_divisor) uart->port.get_divisor = up->port.get_divisor; if (up->port.set_divisor) uart->port.set_divisor = up->port.set_divisor; if (up->port.startup) uart->port.startup = up->port.startup; if (up->port.shutdown) uart->port.shutdown = up->port.shutdown; if (up->port.pm) uart->port.pm = up->port.pm; if (up->port.handle_break) uart->port.handle_break = up->port.handle_break; if (up->dl_read) uart->dl_read = up->dl_read; if (up->dl_write) uart->dl_write = up->dl_write; if (uart->port.type != PORT_8250_CIR) { if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); serial8250_apply_quirks(uart); ret = uart_add_one_port(&serial8250_reg, &uart->port); if (ret) goto err; ret = uart->port.line; } else { dev_info(uart->port.dev, "skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n", uart->port.iobase, (unsigned long long)uart->port.mapbase, uart->port.irq); ret = 0; } /* Initialise interrupt backoff work if required */ if (up->overrun_backoff_time_ms > 0) { uart->overrun_backoff_time_ms = up->overrun_backoff_time_ms; INIT_DELAYED_WORK(&uart->overrun_backoff, serial_8250_overrun_backoff_work); } else { uart->overrun_backoff_time_ms = 0; } } mutex_unlock(&serial_mutex); return ret; err: uart->port.dev = NULL; mutex_unlock(&serial_mutex); return ret; } EXPORT_SYMBOL(serial8250_register_8250_port); /** * serial8250_unregister_port - remove a 16x50 serial port at runtime * @line: serial line number * * Remove one serial port. This may not be called from interrupt * context. We hand the port back to the our control. */ void serial8250_unregister_port(int line) { struct uart_8250_port *uart = &serial8250_ports[line]; mutex_lock(&serial_mutex); if (uart->em485) { unsigned long flags; spin_lock_irqsave(&uart->port.lock, flags); serial8250_em485_destroy(uart); spin_unlock_irqrestore(&uart->port.lock, flags); } uart_remove_one_port(&serial8250_reg, &uart->port); if (serial8250_isa_devs) { uart->port.flags &= ~UPF_BOOT_AUTOCONF; uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->capabilities = 0; serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { uart->port.dev = NULL; } mutex_unlock(&serial_mutex); } EXPORT_SYMBOL(serial8250_unregister_port); static int __init serial8250_init(void) { int ret; if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); pr_info("Serial: 8250/16550 driver, %d ports, IRQ sharing %sabled\n", nr_uarts, share_irqs ? "en" : "dis"); #ifdef CONFIG_SPARC ret = sunserial_register_minors(&serial8250_reg, UART_NR); #else serial8250_reg.nr = UART_NR; ret = uart_register_driver(&serial8250_reg); #endif if (ret) goto out; ret = serial8250_pnp_init(); if (ret) goto unreg_uart_drv; serial8250_isa_devs = platform_device_alloc("serial8250", PLAT8250_DEV_LEGACY); if (!serial8250_isa_devs) { ret = -ENOMEM; goto unreg_pnp; } ret = platform_device_add(serial8250_isa_devs); if (ret) goto put_dev; serial8250_register_ports(&serial8250_reg, &serial8250_isa_devs->dev); ret = platform_driver_register(&serial8250_isa_driver); if (ret == 0) goto out; platform_device_del(serial8250_isa_devs); put_dev: platform_device_put(serial8250_isa_devs); unreg_pnp: serial8250_pnp_exit(); unreg_uart_drv: #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif out: return ret; } static void __exit serial8250_exit(void) { struct platform_device *isa_dev = serial8250_isa_devs; /* * This tells serial8250_unregister_port() not to re-register * the ports (thereby making serial8250_isa_driver permanently * in use.) */ serial8250_isa_devs = NULL; platform_driver_unregister(&serial8250_isa_driver); platform_device_unregister(isa_dev); serial8250_pnp_exit(); #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif } module_init(serial8250_init); module_exit(serial8250_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic 8250/16x50 serial driver"); module_param_hw(share_irqs, uint, other, 0644); MODULE_PARM_DESC(share_irqs, "Share IRQs with other non-8250/16x50 devices (unsafe)"); module_param(nr_uarts, uint, 0644); MODULE_PARM_DESC(nr_uarts, "Maximum number of UARTs supported. (1-" __MODULE_STRING(CONFIG_SERIAL_8250_NR_UARTS) ")"); module_param(skip_txen_test, uint, 0644); MODULE_PARM_DESC(skip_txen_test, "Skip checking for the TXEN bug at init time"); #ifdef CONFIG_SERIAL_8250_RSA module_param_hw_array(probe_rsa, ulong, ioport, &probe_rsa_count, 0444); MODULE_PARM_DESC(probe_rsa, "Probe I/O ports for RSA"); #endif MODULE_ALIAS_CHARDEV_MAJOR(TTY_MAJOR); #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS #ifndef MODULE /* This module was renamed to 8250_core in 3.7. Keep the old "8250" name * working as well for the module options so we don't break people. We * need to keep the names identical and the convenient macros will happily * refuse to let us do that by failing the build with redefinition errors * of global variables. So we stick them inside a dummy function to avoid * those conflicts. The options still get parsed, and the redefined * MODULE_PARAM_PREFIX lets us keep the "8250." syntax alive. * * This is hacky. I'm sorry. */ static void __used s8250_options(void) { #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "8250_core." module_param_cb(share_irqs, ¶m_ops_uint, &share_irqs, 0644); module_param_cb(nr_uarts, ¶m_ops_uint, &nr_uarts, 0644); module_param_cb(skip_txen_test, ¶m_ops_uint, &skip_txen_test, 0644); #ifdef CONFIG_SERIAL_8250_RSA __module_param_call(MODULE_PARAM_PREFIX, probe_rsa, ¶m_array_ops, .arr = &__param_arr_probe_rsa, 0444, -1, 0); #endif } #else MODULE_ALIAS("8250_core"); #endif #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> #include <linux/tty.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #endif #ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) #ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } #endif static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { #ifdef CONFIG_VMAP_STACK void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Clear the KASAN shadow of the stack. */ kasan_unpoison_shadow(s->addr, THREAD_SIZE); /* Clear stale pointers from reused stack. */ memset(s->addr, 0, THREAD_SIZE); tsk->stack_vm_area = s; tsk->stack = s->addr; return s->addr; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ if (stack) { tsk->stack_vm_area = find_vm_area(stack); tsk->stack = stack; } return stack; #else struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return tsk->stack; } return NULL; #endif } static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK struct vm_struct *vm = task_stack_vm_area(tsk); if (vm) { int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, tsk->stack_vm_area) != NULL) continue; return; } vfree_atomic(tsk->stack); return; } #endif __free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_stack_cache; static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack; } static void free_thread_stack(struct task_struct *tsk) { kmem_cache_free(thread_stack_cache, tsk->stack); } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif #endif /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (vma) vma_init(vma, mm); return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (new) { ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); /* * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; } return new; } void vm_area_free(struct vm_area_struct *vma) { kmem_cache_free(vm_area_cachep, vma); } static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); struct vm_struct *vm = task_stack_vm_area(tsk); /* All stack pages are in the same node. */ if (vm) mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); else mod_lruvec_slab_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } static int memcg_charge_kernel_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK struct vm_struct *vm = task_stack_vm_area(tsk); int ret; BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); if (vm) { int i; BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { /* * If memcg_kmem_charge_page() fails, page->mem_cgroup * pointer is NULL, and memcg_kmem_uncharge_page() in * free_thread_stack() will ignore this page. */ ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) return ret; } } #endif return 0; } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(tsk->state != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ account_kernel_stack(tsk, -1); free_thread_stack(tsk); tsk->stack = NULL; #ifdef CONFIG_VMAP_STACK tsk->stack_vm_area = NULL; #endif } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp, *prev, **pprev; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; LIST_HEAD(uf); uprobe_start_dup_mmap(); if (mmap_write_lock_killable(oldmm)) { retval = -EINTR; goto fail_uprobe_end; } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; rb_link = &mm->mm_rb.rb_node; rb_parent = NULL; pprev = &mm->mmap; retval = ksm_fork(mm, oldmm); if (retval) goto out; retval = khugepaged_fork(mm, oldmm); if (retval) goto out; prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); file = tmp->vm_file; if (file) { struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; get_file(file); if (tmp->vm_flags & VM_DENYWRITE) put_write_access(inode); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } /* * Clear hugetlb-related page reserves for children. This only * affects MAP_PRIVATE mappings. Faults generated by the child * are not guaranteed to succeed, even if read-only */ if (is_vm_hugetlb_page(tmp)) reset_vma_resv_huge_pages(tmp); /* * Link in the new vma and copy the page table entries. */ *pprev = tmp; pprev = &tmp->vm_next; tmp->vm_prev = prev; prev = tmp; __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; rb_parent = &tmp->vm_rb; mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); if (retval) goto out; } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); dup_userfaultfd_complete(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = atomic_long_read(&mm->rss_stat.count[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); if (!profile_handoff_task(tsk)) free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = totalram_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } #endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */ void __init fork_init(void) { int i; #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); #endif /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) { init_user_ns.ucount_max[i] = max_threads/2; } #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; unsigned long *stack; struct vm_struct *stack_vm_area __maybe_unused; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; stack = alloc_thread_stack_node(tsk, node); if (!stack) goto free_tsk; if (memcg_charge_kernel_stack(tsk)) goto free_stack; stack_vm_area = task_stack_vm_area(tsk); err = arch_dup_task_struct(tsk, orig); /* * arch_dup_task_struct() clobbers the stack-related fields. Make * sure they're properly initialized before using any stack-related * functions again. */ tsk->stack = stack; #ifdef CONFIG_VMAP_STACK tsk->stack_vm_area = stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif if (err) goto free_stack; err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->pf_io_worker = NULL; account_kernel_stack(tsk, 1); kcov_task_init(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_queue = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif return tsk; free_stack: free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_pasid(struct mm_struct *mm) { #ifdef CONFIG_IOMMU_SUPPORT mm->pasid = INIT_PASID; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mm->mmap = NULL; mm->mm_rb = RB_ROOT; mm->vmacache_seqnum = 0; atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic_set(&mm->has_pinned, 0); atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_init_pasid(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (init_new_context(p, mm)) goto fail_nocontext; mm->user_ns = get_user_ns(user_ns); return mm; fail_nocontext: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_page(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve task is single * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the * mm->exe_file, but does so without using set_mm_exe_file() in order * to do avoid the need for any locks. */ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) get_file(new_exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) fput(old_exe_file); } /** * get_mm_exe_file - acquire a reference to the mm's executable file * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = rcu_dereference(mm->exe_file); if (exe_file && !get_file_rcu(exe_file)) exe_file = NULL; rcu_read_unlock(); return exe_file; } EXPORT_SYMBOL(get_mm_exe_file); /** * get_task_exe_file - acquire a reference to the task's executable file * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (!(task->flags & PF_KTHREAD)) exe_file = get_mm_exe_file(mm); } task_unlock(task); return exe_file; } EXPORT_SYMBOL(get_task_exe_file); /** * get_task_mm - acquire a reference to the task's mm * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (task->flags & PF_KTHREAD) mm = NULL; else mmget(mm); } task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (mm && mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { int killed; freezer_do_not_count(); cgroup_enter_frozen(); killed = wait_for_completion_killable(vfork); cgroup_leave_frozen(false); freezer_count(); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) && atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); if (err) goto free_pt; mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; int retval; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; /* initialize the new vmacache entries */ vmacache_flush(tsk); if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; goto good_mm; } retval = -ENOMEM; mm = dup_mm(tsk, current->mm); if (!mm) goto fail_nomem; good_mm: tsk->mm = mm; tsk->active_mm = mm; return 0; fail_nomem: return retval; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) goto out; if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); goto out; } newf = dup_fd(oldf, NR_OPEN_MAX, &error); if (!newf) goto out; tsk->files = newf; error = 0; out: return error; } static int copy_io(unsigned long clone_flags, struct task_struct *tsk) { #ifdef CONFIG_BLOCK struct io_context *ioc = current->io_context; struct io_context *new_ioc; if (!ioc) return 0; /* * Share io context with parent, if CLONE_IO is set */ if (clone_flags & CLONE_IO) { ioc_task_link(ioc); tsk->io_context = ioc; } else if (ioprio_valid(ioc->ioprio)) { new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); if (unlikely(!new_ioc)) return -ENOMEM; new_ioc->ioprio = ioc->ioprio; put_io_context(new_ioc); } #endif return 0; } static int copy_sighand(u64 clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_tsk_thread_flag(p, TIF_SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&task->pid_links[type]); } } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } struct pid *pidfd_pid(const struct file *file) { if (file->f_op == &pidfd_fops) return file->private_data; return ERR_PTR(-EBADF); } static int pidfd_release(struct inode *inode, struct file *file) { struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); return 0; } #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestoral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = f->private_data; struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Inform pollers only when the whole thread group exits. * If the thread group leader exits before all other threads in the * group, then poll(2) should block, similar to the wait(2) family. */ if (thread_group_exited(pid)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } const struct file_operations pidfd_fops = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @pidfd: the pidfd to return * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * The helper doesn't perform checks on @pid which makes it useful for pidfds * created via CLONE_PIDFD where @pid has no task attached when the pidfd and * pidfd file are prepared. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { int pidfd; struct file *pidfd_file; if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) return -EINVAL; pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (pidfd < 0) return pidfd; pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, flags | O_RDWR | O_CLOEXEC); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } get_pid(pid); /* held by pidfd_file now */ *ret = pidfd_file; return pidfd; } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @pidfd: the pidfd to return * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is used as a thread group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } /* * If the new process will be in a different time namespace * do not allow it to share VM or a thread group with the forking task. */ if (clone_flags & (CLONE_THREAD | CLONE_VM)) { if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. * - CLONE_THREAD is blocked until someone really needs it. */ if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; if (args->io_thread) { /* * Mark us an IO worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_IO_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } /* * This _must_ happen before we call free_task(), i.e. before we jump * to any of the bad_fork_* labels. This is to avoid freeing * p->set_child_tid which is (ab)used as a kthread's data pointer for * kernel threads (PF_KTHREAD). */ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; if (atomic_read(&p->real_cred->user->processes) >= task_rlimit(p, RLIMIT_NPROC)) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_free; } current->flags &= ~PF_NPROC_EXCEEDED; retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_threadgroup_lock; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(p, TIF_SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; clear_posix_cputimers_work(p); /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); spin_lock(¤t->sighand->siglock); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_cancel_cgroup; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_cancel_cgroup; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p, args); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_cancel_cgroup: spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif delayacct_tsk_free(p); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); exit_creds(p); bad_fork_free: p->state = TASK_DEAD; put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, .io_thread = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((args->flags & CLONE_PIDFD) && (args->flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reuseable for clone3 * - make the CSIGNAL bits reuseable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } #endif void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp) { struct files_struct *fd = current->files; int error = 0; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { *new_fdp = dup_fd(fd, max_fds, &error); if (!*new_fdp) return error; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *fd, *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) { fd = current->files; current->files = new_fd; new_fd = fd; } task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 | /* * Resizable virtual memory filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. * Copyright (C) 2002-2011 Hugh Dickins. * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * * Extended attribute support for tmpfs: * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net> * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> * * tiny-shmem: * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com> * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> #include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/khugepaged.h> #include <linux/hugetlb.h> #include <linux/frontswap.h> #include <linux/fs_parser.h> #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */ static struct vfsmount *shm_mnt; #ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/shmem_fs.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/percpu_counter.h> #include <linux/falloc.h> #include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/migrate.h> #include <linux/highmem.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <uapi/linux/memfd.h> #include <linux/userfaultfd_k.h> #include <linux/rmap.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include "internal.h" #define BLOCKS_PER_PAGE (PAGE_SIZE/512) #define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 /* Symlink up to this size is kmalloc'ed instead of using a swappable page */ #define SHORT_SYMLINK_LEN 128 /* * shmem_fallocate communicates with shmem_fault or shmem_writepage via * inode->i_private (with i_mutex making sure that it has only one user at * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ pgoff_t nr_unswapped; /* how often writepage refused to swap out */ }; struct shmem_options { unsigned long long blocks; unsigned long long inodes; struct mempolicy *mpol; kuid_t uid; kgid_t gid; umode_t mode; bool full_inums; int huge; int seen; #define SHMEM_SEEN_BLOCKS 1 #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 #define SHMEM_SEEN_INUMS 8 }; #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { return totalram_pages() / 2; } static unsigned long shmem_default_max_inodes(void) { unsigned long nr_pages = totalram_pages(); return min(nr_pages - totalhigh_pages(), nr_pages / 2); } #endif static bool shmem_should_replace_page(struct page *page, gfp_t gfp); static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index); static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type); int shmem_getpage(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp) { return shmem_getpage_gfp(inode, index, pagep, sgp, mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { return sb->s_fs_info; } /* * shmem_file_setup pre-accounts the whole fixed size of a VM object, * for shared memory and for shared anonymous (/dev/zero) mappings * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1), * consistent with the pre-accounting of private mappings ... */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { return (flags & VM_NORESERVE) ? 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } static inline int shmem_reacct_size(unsigned long flags, loff_t oldsize, loff_t newsize) { if (!(flags & VM_NORESERVE)) { if (VM_ACCT(newsize) > VM_ACCT(oldsize)) return security_vm_enough_memory_mm(current->mm, VM_ACCT(newsize) - VM_ACCT(oldsize)); else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); } return 0; } /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ static inline int shmem_acct_block(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; return security_vm_enough_memory_mm(current->mm, pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static inline bool shmem_inode_acct_block(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (shmem_acct_block(info->flags, pages)) return false; if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks - pages) > 0) goto unacct; percpu_counter_add(&sbinfo->used_blocks, pages); } return true; unacct: shmem_unacct_blocks(info->flags, pages); return false; } static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_sub(&sbinfo->used_blocks, pages); shmem_unacct_blocks(info->flags, pages); } static const struct super_operations shmem_ops; static const struct address_space_operations shmem_aops; static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; static struct file_system_type shmem_fs_type; bool vma_is_shmem(struct vm_area_struct *vma) { return vma->vm_ops == &shmem_vm_ops; } static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); /* * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and * produces a novel ino for the newly allocated inode. * * It may also be called when making a hard link to permit the space needed by * each dentry. However, in that case, no new inode number is needed since that * internally draws from another pool of inode numbers (currently global * get_next_ino()). This case is indicated by passing NULL as inop. */ #define SHMEM_INO_BATCH 1024 static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; if (!(sb->s_flags & SB_KERNMOUNT)) { spin_lock(&sbinfo->stat_lock); if (sbinfo->max_inodes) { if (!sbinfo->free_inodes) { spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_inodes--; } if (inop) { ino = sbinfo->next_ino++; if (unlikely(is_zero_ino(ino))) ino = sbinfo->next_ino++; if (unlikely(!sbinfo->full_inums && ino > UINT_MAX)) { /* * Emulate get_next_ino uint wraparound for * compatibility */ if (IS_ENABLED(CONFIG_64BIT)) pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n", __func__, MINOR(sb->s_dev)); sbinfo->next_ino = 1; ino = sbinfo->next_ino++; } *inop = ino; } spin_unlock(&sbinfo->stat_lock); } else if (inop) { /* * __shmem_file_setup, one of our callers, is lock-free: it * doesn't hold stat_lock in shmem_reserve_inode since * max_inodes is always 0, and is called from potentially * unknown contexts. As such, use a per-cpu batched allocator * which doesn't require the per-sb stat_lock unless we are at * the batch boundary. * * We don't need to worry about inode{32,64} since SB_KERNMOUNT * shmem mounts are not exposed to userspace, so we don't need * to worry about things like glibc compatibility. */ ino_t *next_ino; next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); ino = *next_ino; if (unlikely(ino % SHMEM_INO_BATCH == 0)) { spin_lock(&sbinfo->stat_lock); ino = sbinfo->next_ino; sbinfo->next_ino += SHMEM_INO_BATCH; spin_unlock(&sbinfo->stat_lock); if (unlikely(is_zero_ino(ino))) ino++; } *inop = ino; *next_ino = ++ino; put_cpu(); } return 0; } static void shmem_free_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } /** * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop * undirtied hole pages behind our back. * * But normally info->alloced == inode->i_mapping->nrpages + info->swapped * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped) * * It has to be called with the spinlock held. */ static void shmem_recalc_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); long freed; freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { info->alloced -= freed; inode->i_blocks -= freed * BLOCKS_PER_PAGE; shmem_inode_unacct_blocks(inode, freed); } } bool shmem_charge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; if (!shmem_inode_acct_block(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ inode->i_mapping->nrpages += pages; spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); return true; } void shmem_uncharge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; /* nrpages adjustment done by __delete_from_page_cache() or caller */ spin_lock_irqsave(&info->lock, flags); info->alloced -= pages; inode->i_blocks -= pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); shmem_inode_unacct_blocks(inode, pages); } /* * Replace item expected in xarray by a new item, while holding xa_lock. */ static int shmem_replace_entry(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { XA_STATE(xas, &mapping->i_pages, index); void *item; VM_BUG_ON(!expected); VM_BUG_ON(!replacement); item = xas_load(&xas); if (item != expected) return -ENOENT; xas_store(&xas, replacement); return 0; } /* * Sometimes, before we decide whether to proceed or to fail, we must check * that an entry was not already brought back from swap by a racing thread. * * Checking page is not enough: by the time a SwapCache page is locked, it * might be reused, and again be SwapCache, using the same swap as before. */ static bool shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) { return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap); } /* * Definitions for "huge tmpfs": tmpfs mounted with the huge= option * * SHMEM_HUGE_NEVER: * disables huge pages for the mount; * SHMEM_HUGE_ALWAYS: * enables huge pages for the mount; * SHMEM_HUGE_WITHIN_SIZE: * only allocate huge pages if the page will be fully within i_size, * also respect fadvise()/madvise() hints; * SHMEM_HUGE_ADVISE: * only allocate huge pages if requested with fadvise()/madvise(); */ #define SHMEM_HUGE_NEVER 0 #define SHMEM_HUGE_ALWAYS 1 #define SHMEM_HUGE_WITHIN_SIZE 2 #define SHMEM_HUGE_ADVISE 3 /* * Special values. * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: * * SHMEM_HUGE_DENY: * disables huge on shm_mnt and all mounts, for emergency use; * SHMEM_HUGE_FORCE: * enables huge on shm_mnt and all mounts, w/o needing option, for testing; * */ #define SHMEM_HUGE_DENY (-1) #define SHMEM_HUGE_FORCE (-2) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* ifdef here to avoid bloating shmem.o when not necessary */ static int shmem_huge __read_mostly; #if defined(CONFIG_SYSFS) static int shmem_parse_huge(const char *str) { if (!strcmp(str, "never")) return SHMEM_HUGE_NEVER; if (!strcmp(str, "always")) return SHMEM_HUGE_ALWAYS; if (!strcmp(str, "within_size")) return SHMEM_HUGE_WITHIN_SIZE; if (!strcmp(str, "advise")) return SHMEM_HUGE_ADVISE; if (!strcmp(str, "deny")) return SHMEM_HUGE_DENY; if (!strcmp(str, "force")) return SHMEM_HUGE_FORCE; return -EINVAL; } #endif #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) static const char *shmem_format_huge(int huge) { switch (huge) { case SHMEM_HUGE_NEVER: return "never"; case SHMEM_HUGE_ALWAYS: return "always"; case SHMEM_HUGE_WITHIN_SIZE: return "within_size"; case SHMEM_HUGE_ADVISE: return "advise"; case SHMEM_HUGE_DENY: return "deny"; case SHMEM_HUGE_FORCE: return "force"; default: VM_BUG_ON(1); return "bad_val"; } } #endif static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { LIST_HEAD(list), *pos, *next; LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; struct page *page; unsigned long batch = sc ? sc->nr_to_scan : 128; int split = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; spin_lock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &sbinfo->shrinklist) { info = list_entry(pos, struct shmem_inode_info, shrinklist); /* pin the inode */ inode = igrab(&info->vfs_inode); /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); goto next; } /* Check if there's anything to gain */ if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { list_move(&info->shrinklist, &to_remove); goto next; } list_move(&info->shrinklist, &list); next: sbinfo->shrinklist_len--; if (!--batch) break; } spin_unlock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &to_remove) { info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; list_del_init(&info->shrinklist); iput(inode); } list_for_each_safe(pos, next, &list) { int ret; info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; if (nr_to_split && split >= nr_to_split) goto move_back; page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); if (!page) goto drop; /* No huge page at the end of the file: nothing to split */ if (!PageTransHuge(page)) { put_page(page); goto drop; } /* * Move the inode on the list back to shrinklist if we failed * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!trylock_page(page)) { put_page(page); goto move_back; } ret = split_huge_page(page); unlock_page(page); put_page(page); /* If split failed move the inode on the list back to shrinklist */ if (ret) goto move_back; split++; drop: list_del_init(&info->shrinklist); goto put; move_back: /* * Make sure the inode is either on the global list or deleted * from any local list before iput() since it could be deleted * in another thread once we put the inode (then the local list * is corrupted). */ spin_lock(&sbinfo->shrinklist_lock); list_move(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; spin_unlock(&sbinfo->shrinklist_lock); put: iput(inode); } return split; } static long shmem_unused_huge_scan(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (!READ_ONCE(sbinfo->shrinklist_len)) return SHRINK_STOP; return shmem_unused_huge_shrink(sbinfo, sc, 0); } static long shmem_unused_huge_count(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); return READ_ONCE(sbinfo->shrinklist_len); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ #define shmem_huge SHMEM_HUGE_DENY static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) && shmem_huge != SHMEM_HUGE_DENY) return true; return false; } /* * Like add_to_page_cache_locked, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp, struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); unsigned long i = 0; unsigned long nr = compound_nr(page); int error; VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); VM_BUG_ON(expected && PageTransHuge(page)); page_ref_add(page, nr); page->mapping = mapping; page->index = index; if (!PageSwapCache(page)) { error = mem_cgroup_charge(page, charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); count_vm_event(THP_FILE_FALLBACK_CHARGE); } goto error; } } cgroup_throttle_swaprate(page, gfp); do { void *entry; xas_lock_irq(&xas); entry = xas_find_conflict(&xas); if (entry != expected) xas_set_err(&xas, -EEXIST); xas_create_range(&xas); if (xas_error(&xas)) goto unlock; next: xas_store(&xas, page); if (++i < nr) { xas_next(&xas); goto next; } if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); __inc_node_page_state(page, NR_SHMEM_THPS); } mapping->nrpages += nr; __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); __mod_lruvec_page_state(page, NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); goto error; } return 0; error: page->mapping = NULL; page_ref_sub(page, nr); return error; } /* * Like delete_from_page_cache, but substitutes swap for page. */ static void shmem_delete_from_page_cache(struct page *page, void *radswap) { struct address_space *mapping = page->mapping; int error; VM_BUG_ON_PAGE(PageCompound(page), page); xa_lock_irq(&mapping->i_pages); error = shmem_replace_entry(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; __dec_lruvec_page_state(page, NR_FILE_PAGES); __dec_lruvec_page_state(page, NR_SHMEM); xa_unlock_irq(&mapping->i_pages); put_page(page); BUG_ON(error); } /* * Remove swap entry from page cache, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { void *old; old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); if (old != radswap) return -ENOENT; free_swap_and_cache(radix_to_swp_entry(radswap)); return 0; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given offsets are swapped out. * * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; rcu_read_lock(); xas_for_each(&xas, page, end - 1) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return swapped << PAGE_SHIFT; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given vma is swapped out. * * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_swap_usage(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; unsigned long swapped; /* Be careful as we don't hold info->lock */ swapped = READ_ONCE(info->swapped); /* * The easier cases are when the shmem object has nothing in swap, or * the vma maps it whole. Then we can simply use the stats that we * already track. */ if (!swapped) return 0; if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) return swapped << PAGE_SHIFT; /* Here comes the more involved part */ return shmem_partial_swap_usage(mapping, linear_page_index(vma, vma->vm_start), linear_page_index(vma, vma->vm_end)); } /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ void shmem_unlock_mapping(struct address_space *mapping) { struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index = 0; pagevec_init(&pvec); /* * Minor point, but we might as well stop if someone else SHM_LOCKs it. */ while (!mapping_unevictable(mapping)) { /* * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ pvec.nr = find_get_entries(mapping, index, PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(&pvec); pagevec_release(&pvec); cond_resched(); } } /* * Check whether a hole-punch or truncation needs to split a huge page, * returning true if no split was required, or the split has been successful. * * Eviction (or truncation to 0 size) should never need to split a huge page; * but in rare cases might do so, if shmem_undo_range() failed to trylock on * head, and then succeeded to trylock on tail. * * A split can only succeed when there are no additional references on the * huge page: so the split below relies upon find_get_entries() having stopped * when it found a subpage of the huge page, without getting further references. */ static bool shmem_punch_compound(struct page *page, pgoff_t start, pgoff_t end) { if (!PageTransCompound(page)) return true; /* Just proceed to delete a huge page wholly within the range punched */ if (PageHead(page) && page->index >= start && page->index + HPAGE_PMD_NR <= end) return true; /* Try to split huge page, so we can truly punch the hole or truncate */ return split_huge_page(page) >= 0; } /* * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, bool unfalloc) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; pgoff_t end = (lend + 1) >> PAGE_SHIFT; unsigned int partial_start = lstart & (PAGE_SIZE - 1); unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; pgoff_t index; int i; if (lend == -1) end = -1; /* unsigned, so actually very big */ pagevec_init(&pvec); index = start; while (index < end) { pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) break; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; if (index >= end) break; if (xa_is_value(page)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, index, page); continue; } VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); if (!trylock_page(page)) continue; if ((!unfalloc || !PageUptodate(page)) && page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); if (shmem_punch_compound(page, start, end)) truncate_inode_page(mapping, page); } unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } if (partial_start) { struct page *page = NULL; shmem_getpage(inode, start - 1, &page, SGP_READ); if (page) { unsigned int top = PAGE_SIZE; if (start > end) { top = partial_end; partial_end = 0; } zero_user_segment(page, partial_start, top); set_page_dirty(page); unlock_page(page); put_page(page); } } if (partial_end) { struct page *page = NULL; shmem_getpage(inode, end, &page, SGP_READ); if (page) { zero_user_segment(page, 0, partial_end); set_page_dirty(page); unlock_page(page); put_page(page); } } if (start >= end) return; index = start; while (index < end) { cond_resched(); pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; /* But if truncating, restart to make sure all gone */ index = start; continue; } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; if (index >= end) break; if (xa_is_value(page)) { if (unfalloc) continue; if (shmem_free_swap(mapping, index, page)) { /* Swap was replaced by page: retry */ index--; break; } nr_swaps_freed++; continue; } lock_page(page); if (!unfalloc || !PageUptodate(page)) { if (page_mapping(page) != mapping) { /* Page was replaced by swap: retry */ unlock_page(page); index--; break; } VM_BUG_ON_PAGE(PageWriteback(page), page); if (shmem_punch_compound(page, start, end)) truncate_inode_page(mapping, page); else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Wipe the page and don't get stuck */ clear_highpage(page); flush_dcache_page(page); set_page_dirty(page); if (index < round_up(start, HPAGE_PMD_NR)) start = index + 1; } } unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); index++; } spin_lock_irq(&info->lock); info->swapped -= nr_swaps_freed; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { shmem_undo_range(inode, lstart, lend, false); inode->i_ctime = inode->i_mtime = current_time(inode); } EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = path->dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb); if (info->alloced - info->swapped != inode->i_mapping->nrpages) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } generic_fillattr(inode, stat); if (is_huge_enabled(sb_info)) stat->blksize = HPAGE_PMD_SIZE; return 0; } static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int error; error = setattr_prepare(dentry, attr); if (error) return error; if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; /* protected by i_mutex */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; if (newsize != oldsize) { error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); if (error) return error; i_size_write(inode, newsize); inode->i_ctime = inode->i_mtime = current_time(inode); } if (newsize <= oldsize) { loff_t holebegin = round_up(newsize, PAGE_SIZE); if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); if (info->alloced) shmem_truncate_range(inode, newsize, (loff_t)-1); /* unmap again to remove racily COWed private pages */ if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); /* * Part of the huge page can be beyond i_size: subject * to shrink under memory pressure. */ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { spin_lock(&sbinfo->shrinklist_lock); /* * _careful to defend against unlocked access to * ->shrink_list in shmem_unused_huge_shrink() */ if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; } spin_unlock(&sbinfo->shrinklist_lock); } } } setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) error = posix_acl_chmod(inode, inode->i_mode); return error; } static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (inode->i_mapping->a_ops == &shmem_aops) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->shrinklist)) { spin_lock(&sbinfo->shrinklist_lock); if (!list_empty(&info->shrinklist)) { list_del_init(&info->shrinklist); sbinfo->shrinklist_len--; } spin_unlock(&sbinfo->shrinklist_lock); } while (!list_empty(&info->swaplist)) { /* Wait while shmem_unuse() is scanning this inode... */ wait_var_event(&info->stop_eviction, !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); /* ...but beware of the race if we peeked too early */ if (!atomic_read(&info->stop_eviction)) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); shmem_free_inode(inode->i_sb); clear_inode(inode); } extern struct swap_info_struct *swap_info[]; static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, unsigned int type, bool frontswap) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; swp_entry_t entry; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; if (!xa_is_value(page)) continue; entry = radix_to_swp_entry(page); if (swp_type(entry) != type) continue; if (frontswap && !frontswap_test(swap_info[type], swp_offset(entry))) continue; indices[ret] = xas.xa_index; entries[ret] = page; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } if (++ret == nr_entries) break; } rcu_read_unlock(); return ret; } /* * Move the swapped pages for an inode to page cache. Returns the count * of pages swapped in, or the error in case of failure. */ static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, pgoff_t *indices) { int i = 0; int ret = 0; int error = 0; struct address_space *mapping = inode->i_mapping; for (i = 0; i < pvec.nr; i++) { struct page *page = pvec.pages[i]; if (!xa_is_value(page)) continue; error = shmem_swapin_page(inode, indices[i], &page, SGP_CACHE, mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { unlock_page(page); put_page(page); ret++; } if (error == -ENOMEM) break; error = 0; } return error ? error : ret; } /* * If swap found in inode, free it and move page from swapcache to filecache. */ static int shmem_unuse_inode(struct inode *inode, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); int ret = 0; pagevec_init(&pvec); do { unsigned int nr_entries = PAGEVEC_SIZE; if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) nr_entries = *fs_pages_to_unuse; pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, pvec.pages, indices, type, frontswap); if (pvec.nr == 0) { ret = 0; break; } ret = shmem_unuse_swap_entries(inode, pvec, indices); if (ret < 0) break; if (frontswap_partial) { *fs_pages_to_unuse -= ret; if (*fs_pages_to_unuse == 0) { ret = FRONTSWAP_PAGES_UNUSED; break; } } start = indices[pvec.nr - 1]; } while (true); return ret; } /* * Read all the shared memory data that resides in the swap * device 'type' back into memory, so the swap device can be * unused. */ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } /* * Drop the swaplist mutex while searching the inode for swap; * but before doing so, make sure shmem_evict_inode() will not * remove placeholder inode from swaplist, nor let it be freed * (igrab() would protect from unlink, but not from unmount). */ atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); mutex_lock(&shmem_swaplist_mutex); next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); if (atomic_dec_and_test(&info->stop_eviction)) wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); return error; } /* * Move the page from the page cache to the swap cache. */ static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; struct address_space *mapping; struct inode *inode; swp_entry_t swap; pgoff_t index; VM_BUG_ON_PAGE(PageCompound(page), page); BUG_ON(!PageLocked(page)); mapping = page->mapping; index = page->index; inode = mapping->host; info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; if (!total_swap_pages) goto redirty; /* * Our capabilities prevent regular writeback or sync from ever calling * shmem_writepage; but a stacking filesystem might use ->writepage of * its underlying filesystem, in which case tmpfs should write out to * swap only in response to memory pressure, and not for the writeback * threads or sync. */ if (!wbc->for_reclaim) { WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ goto redirty; } /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC * value into swapfile.c, the only way we can correctly account for a * fallocated page arriving here is now to initialize it and write it. * * That's okay for a page already fallocated earlier, but if we have * not yet completed the fallocation, then (a) we want to keep track * of this page in case we have to undo it, and (b) it may not be a * good idea to continue anyway, once we're pushing into swap. So * reactivate the page, and let shmem_fallocate() quit when too many. */ if (!PageUptodate(page)) { if (inode->i_private) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); if (shmem_falloc) goto redirty; } clear_highpage(page); flush_dcache_page(page); SetPageUptodate(page); } swap = get_swap_page(page); if (!swap.val) goto redirty; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, * if it's not already there. Do it now before the page is * moved to swap cache, when its pagelock no longer protects * the inode from eviction. But don't unlock the mutex until * we've incremented swapped, because shmem_unuse_inode() will * prune a !swapped inode from the swaplist under this mutex. */ mutex_lock(&shmem_swaplist_mutex); if (list_empty(&info->swaplist)) list_add(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, NULL) == 0) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); info->swapped++; spin_unlock_irq(&info->lock); swap_shmem_alloc(swap); shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); return 0; } mutex_unlock(&shmem_swaplist_mutex); put_swap_page(page, swap); redirty: set_page_dirty(page); if (wbc->for_reclaim) return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */ unlock_page(page); return 0; } #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; if (!mpol || mpol->mode == MPOL_DEFAULT) return; /* show nothing */ mpol_to_str(buffer, sizeof(buffer), mpol); seq_printf(seq, ",mpol=%s", buffer); } static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); spin_unlock(&sbinfo->stat_lock); } return mpol; } #else /* !CONFIG_NUMA || !CONFIG_TMPFS */ static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { return NULL; } #endif /* CONFIG_NUMA && CONFIG_TMPFS */ #ifndef CONFIG_NUMA #define vm_policy vm_private_data #endif static void shmem_pseudo_vma_init(struct vm_area_struct *vma, struct shmem_inode_info *info, pgoff_t index) { /* Create a pseudo vma that just contains the policy */ vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); } static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) { /* Drop reference taken by mpol_shared_policy_lookup() */ mpol_cond_put(vma->vm_policy); } static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; struct vm_fault vmf; shmem_pseudo_vma_init(&pvma, info, index); vmf.vma = &pvma; vmf.address = 0; page = swap_cluster_readahead(swap, gfp, &vmf); shmem_pseudo_vma_destroy(&pvma); return page; } static struct page *shmem_alloc_hugepage(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct address_space *mapping = info->vfs_inode.i_mapping; pgoff_t hindex; struct page *page; hindex = round_down(index, HPAGE_PMD_NR); if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, XA_PRESENT)) return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); else count_vm_event(THP_FILE_FALLBACK); return page; } static struct page *shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; shmem_pseudo_vma_init(&pvma, info, index); page = alloc_page_vma(gfp, &pvma, 0); shmem_pseudo_vma_destroy(&pvma); return page; } static struct page *shmem_alloc_and_acct_page(gfp_t gfp, struct inode *inode, pgoff_t index, bool huge) { struct shmem_inode_info *info = SHMEM_I(inode); struct page *page; int nr; int err = -ENOSPC; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) huge = false; nr = huge ? HPAGE_PMD_NR : 1; if (!shmem_inode_acct_block(inode, nr)) goto failed; if (huge) page = shmem_alloc_hugepage(gfp, info, index); else page = shmem_alloc_page(gfp, info, index); if (page) { __SetPageLocked(page); __SetPageSwapBacked(page); return page; } err = -ENOMEM; shmem_inode_unacct_blocks(inode, nr); failed: return ERR_PTR(err); } /* * When a page is moved from swapcache to shmem filecache (either by the * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of * shmem_unuse_inode()), it may have been read in earlier from swap, in * ignorance of the mapping it belongs to. If that mapping has special * constraints (like the gma500 GEM driver, which requires RAM below 4GB), * we may need to copy to a suitable page before moving to filecache. * * In a future release, this may well be extended to respect cpuset and * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); * but for now it is a simple matter of zone. */ static bool shmem_should_replace_page(struct page *page, gfp_t gfp) { return page_zonenum(page) > gfp_zone(gfp); } static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct page *oldpage, *newpage; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; int error; oldpage = *pagep; entry.val = page_private(oldpage); swap_index = swp_offset(entry); swap_mapping = page_mapping(oldpage); /* * We have arrived here because our zones are constrained, so don't * limit chance of success by further cpuset and node constraints. */ gfp &= ~GFP_CONSTRAINT_MASK; newpage = shmem_alloc_page(gfp, info, index); if (!newpage) return -ENOMEM; get_page(newpage); copy_highpage(newpage, oldpage); flush_dcache_page(newpage); __SetPageLocked(newpage); __SetPageSwapBacked(newpage); SetPageUptodate(newpage); set_page_private(newpage, entry.val); SetPageSwapCache(newpage); /* * Our caller will very soon move newpage out of swapcache, but it's * a nice clean interface for us to replace oldpage by newpage there. */ xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { mem_cgroup_migrate(oldpage, newpage); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } xa_unlock_irq(&swap_mapping->i_pages); if (unlikely(error)) { /* * Is this possible? I think not, now that our callers check * both PageSwapCache and page_private after getting page lock; * but be defensive. Reverse old to newpage for clear and free. */ oldpage = newpage; } else { lru_cache_add(newpage); *pagep = newpage; } ClearPageSwapCache(oldpage); set_page_private(oldpage, 0); unlock_page(oldpage); put_page(oldpage); put_page(oldpage); return error; } /* * Swap in the page pointed to by *pagep. * Caller has to make sure that *pagep contains a valid swapped page. * Returns 0 and the page in pagep if success. On failure, returns the * error code and NULL in *pagep. */ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; struct page *page; swp_entry_t swap; int error; VM_BUG_ON(!*pagep || !xa_is_value(*pagep)); swap = radix_to_swp_entry(*pagep); *pagep = NULL; /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); if (!page) { /* Or update major stats only when swapin succeeds?? */ if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(charge_mm, PGMAJFAULT); } /* Here we actually start the io */ page = shmem_swapin(swap, gfp, info, index); if (!page) { error = -ENOMEM; goto failed; } } /* We have to do this with page locked to prevent races */ lock_page(page); if (!PageSwapCache(page) || page_private(page) != swap.val || !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; goto unlock; } if (!PageUptodate(page)) { error = -EIO; goto failed; } wait_on_page_writeback(page); /* * Some architectures may have to restore extra metadata to the * physical page after reading from swap. */ arch_swap_restore(swap, page); if (shmem_should_replace_page(page, gfp)) { error = shmem_replace_page(&page, gfp, info, index); if (error) goto failed; } error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap), gfp, charge_mm); if (error) goto failed; spin_lock_irq(&info->lock); info->swapped--; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); if (sgp == SGP_WRITE) mark_page_accessed(page); delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); *pagep = page; return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { unlock_page(page); put_page(page); } return error; } /* * shmem_getpage_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * * vmf and fault_type are only supplied by shmem_fault: * otherwise they are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; int error; int once = 0; int alloced = 0; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) sgp = SGP_CACHE; repeat: if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { return -EINVAL; } sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : current->mm; page = find_lock_entry(mapping, index); if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); if (error == -EEXIST) goto repeat; *pagep = page; return error; } if (page) hindex = page->index; if (page && sgp == SGP_WRITE) mark_page_accessed(page); /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) goto clear; unlock_page(page); put_page(page); page = NULL; hindex = index; } if (page || sgp == SGP_READ) goto out; /* * Fast cache lookup did not find it: * bring it back from swap or allocate. */ if (vma && userfaultfd_missing(vma)) { *fault_type = handle_userfault(vmf, VM_UFFD_MISSING); return 0; } /* shmem_symlink() */ if (mapping->a_ops != &shmem_aops) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_FORCE) goto alloc_huge; switch (sbinfo->huge) { case SHMEM_HUGE_NEVER: goto alloc_nohuge; case SHMEM_HUGE_WITHIN_SIZE: { loff_t i_size; pgoff_t off; off = round_up(index, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); if (i_size >= HPAGE_PMD_SIZE && i_size >> PAGE_SHIFT >= off) goto alloc_huge; fallthrough; } case SHMEM_HUGE_ADVISE: if (sgp_huge == SGP_HUGE) goto alloc_huge; /* TODO: implement fadvise() hints */ goto alloc_nohuge; } alloc_huge: page = shmem_alloc_and_acct_page(gfp, inode, index, true); if (IS_ERR(page)) { alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, index, false); } if (IS_ERR(page)) { int retry = 5; error = PTR_ERR(page); page = NULL; if (error != -ENOSPC) goto unlock; /* * Try to reclaim some space by splitting a huge page * beyond i_size on the filesystem. */ while (retry--) { int ret; ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); if (ret == SHRINK_STOP) break; if (ret) goto alloc_nohuge; } goto unlock; } if (PageTransHuge(page)) hindex = round_down(index, HPAGE_PMD_NR); else hindex = index; if (sgp == SGP_WRITE) __SetPageReferenced(page); error = shmem_add_to_page_cache(page, mapping, hindex, NULL, gfp & GFP_RECLAIM_MASK, charge_mm); if (error) goto unacct; lru_cache_add(page); spin_lock_irq(&info->lock); info->alloced += compound_nr(page); inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); alloced = true; if (PageTransHuge(page) && DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < hindex + HPAGE_PMD_NR - 1) { /* * Part of the huge page is beyond i_size: subject * to shrink under memory pressure. */ spin_lock(&sbinfo->shrinklist_lock); /* * _careful to defend against unlocked access to * ->shrink_list in shmem_unused_huge_shrink() */ if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; } spin_unlock(&sbinfo->shrinklist_lock); } /* * Let SGP_FALLOC use the SGP_WRITE optimization on a new page. */ if (sgp == SGP_FALLOC) sgp = SGP_WRITE; clear: /* * Let SGP_WRITE caller clear ends if write does not fill page; * but SGP_FALLOC on a page fallocated earlier must initialize * it now, lest undo on failure cancel our earlier guarantee. */ if (sgp != SGP_WRITE && !PageUptodate(page)) { int i; for (i = 0; i < compound_nr(page); i++) { clear_highpage(page + i); flush_dcache_page(page + i); } SetPageUptodate(page); } /* Perhaps the file has been truncated since we checked */ if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { if (alloced) { ClearPageDirty(page); delete_from_page_cache(page); spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } error = -EINVAL; goto unlock; } out: *pagep = page + index - hindex; return 0; /* * Error recovery. */ unacct: shmem_inode_unacct_blocks(inode, compound_nr(page)); if (PageTransHuge(page)) { unlock_page(page); put_page(page); goto alloc_nohuge; } unlock: if (page) { unlock_page(page); put_page(page); } if (error == -ENOSPC && !once++) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); goto repeat; } if (error == -EEXIST) goto repeat; return error; } /* * This is like autoremove_wake_function, but it removes the wait queue * entry unconditionally - even if something else had already woken the * target. */ static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); list_del_init(&wait->entry); return ret; } static vm_fault_t shmem_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct inode *inode = file_inode(vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); enum sgp_type sgp; int err; vm_fault_t ret = VM_FAULT_LOCKED; /* * Trinity finds that probing a hole which tmpfs is punching can * prevent the hole-punch from ever completing: which in turn * locks writers out with its hold on i_mutex. So refrain from * faulting pages into the hole while it's being punched. Although * shmem_undo_range() does remove the additions, it may be unable to * keep up, as each new page needs its own unmap_mapping_range() call, * and the i_mmap tree grows ever slower to scan if new vmas are added. * * It does not matter if we sometimes reach this check just before the * hole-punch begins, so that one fault then races with the punch: * we just need to make racing faults a rare case. * * The implementation below would be much simpler if we just used a * standard mutex or completion: but we cannot take i_mutex in fault, * and bloating every shmem inode for this unlikely case would be sad. */ if (unlikely(inode->i_private)) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && shmem_falloc->waitq && vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { struct file *fpin; wait_queue_head_t *shmem_falloc_waitq; DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; fpin = maybe_unlock_mmap_for_io(vmf, NULL); if (fpin) ret = VM_FAULT_RETRY; shmem_falloc_waitq = shmem_falloc->waitq; prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); schedule(); /* * shmem_falloc_waitq points into the shmem_fallocate() * stack of the hole-punching task: shmem_falloc_waitq * is usually invalid by the time we reach here, but * finish_wait() does not dereference it in that case; * though i_lock needed lest racing with wake_up_all(). */ spin_lock(&inode->i_lock); finish_wait(shmem_falloc_waitq, &shmem_fault_wait); spin_unlock(&inode->i_lock); if (fpin) fput(fpin); return ret; } spin_unlock(&inode->i_lock); } sgp = SGP_CACHE; if ((vma->vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) sgp = SGP_NOHUGE; else if (vma->vm_flags & VM_HUGEPAGE) sgp = SGP_HUGE; err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, gfp, vma, vmf, &ret); if (err) return vmf_error(err); return ret; } unsigned long shmem_get_unmapped_area(struct file *file, unsigned long uaddr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); unsigned long addr; unsigned long offset; unsigned long inflated_len; unsigned long inflated_addr; unsigned long inflated_offset; if (len > TASK_SIZE) return -ENOMEM; get_area = current->mm->get_unmapped_area; addr = get_area(file, uaddr, len, pgoff, flags); if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return addr; if (IS_ERR_VALUE(addr)) return addr; if (addr & ~PAGE_MASK) return addr; if (addr > TASK_SIZE - len) return addr; if (shmem_huge == SHMEM_HUGE_DENY) return addr; if (len < HPAGE_PMD_SIZE) return addr; if (flags & MAP_FIXED) return addr; /* * Our priority is to support MAP_SHARED mapped hugely; * and support MAP_PRIVATE mapped hugely too, until it is COWed. * But if caller specified an address hint and we allocated area there * successfully, respect that as before. */ if (uaddr == addr) return addr; if (shmem_huge != SHMEM_HUGE_FORCE) { struct super_block *sb; if (file) { VM_BUG_ON(file->f_op != &shmem_file_operations); sb = file_inode(file)->i_sb; } else { /* * Called directly from mm/mmap.c, or drivers/char/mem.c * for "/dev/zero", to create a shared anonymous object. */ if (IS_ERR(shm_mnt)) return addr; sb = shm_mnt->mnt_sb; } if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER) return addr; } offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1); if (offset && offset + len < 2 * HPAGE_PMD_SIZE) return addr; if ((addr & (HPAGE_PMD_SIZE-1)) == offset) return addr; inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE; if (inflated_len > TASK_SIZE) return addr; if (inflated_len < len) return addr; inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags); if (IS_ERR_VALUE(inflated_addr)) return addr; if (inflated_addr & ~PAGE_MASK) return addr; inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1); inflated_addr += offset - inflated_offset; if (inflated_offset > offset) inflated_addr += HPAGE_PMD_SIZE; if (inflated_addr > TASK_SIZE - len) return addr; return inflated_addr; } #ifdef CONFIG_NUMA static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { struct inode *inode = file_inode(vma->vm_file); return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) { struct inode *inode = file_inode(vma->vm_file); pgoff_t index; index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } #endif int shmem_lock(struct file *file, int lock, struct user_struct *user) { struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; /* * What serializes the accesses to info->flags? * ipc_lock_object() when called from shmctl_do_lock(), * no serialization needed when called from shm_destroy(). */ if (lock && !(info->flags & VM_LOCKED)) { if (!user_shm_lock(inode->i_size, user)) goto out_nomem; info->flags |= VM_LOCKED; mapping_set_unevictable(file->f_mapping); } if (!lock && (info->flags & VM_LOCKED) && user) { user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); } retval = 0; out_nomem: return retval; } static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); int ret; ret = seal_check_write(info->seals, vma); if (ret) return ret; file_accessed(file); vma->vm_ops = &shmem_vm_ops; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < (vma->vm_end & HPAGE_PMD_MASK)) { khugepaged_enter(vma, vma->vm_flags); } return 0; } static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; if (shmem_reserve_inode(sb, &ino)) return NULL; inode = new_inode(sb); if (inode) { inode->i_ino = ino; inode_init_owner(inode, dir, mode); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_generation = prandom_u32(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); switch (mode & S_IFMT) { default: inode->i_op = &shmem_special_inode_operations; init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_inode_operations; inode->i_fop = &shmem_file_operations; mpol_shared_policy_init(&info->policy, shmem_get_sbmpol(sbinfo)); break; case S_IFDIR: inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; inode->i_fop = &simple_dir_operations; break; case S_IFLNK: /* * Must not load anything in the rbtree, * mpol_free_shared_policy will not be called. */ mpol_shared_policy_init(&info->policy, NULL); break; } lockdep_annotate_inode_mutex_key(inode); } else shmem_free_inode(sb); return inode; } bool shmem_mapping(struct address_space *mapping) { return mapping->a_ops == &shmem_aops; } static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, bool zeropage, struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); spinlock_t *ptl; void *page_kaddr; struct page *page; pte_t _dst_pte, *dst_pte; int ret; pgoff_t offset, max_off; ret = -ENOMEM; if (!shmem_inode_acct_block(inode, 1)) { /* * We may have got a page, returned -ENOENT triggering a retry, * and now we find ourselves with -ENOMEM. Release the page, to * avoid a BUG_ON in our caller. */ if (unlikely(*pagep)) { put_page(*pagep); *pagep = NULL; } goto out; } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); if (!page) goto out_unacct_blocks; if (!zeropage) { /* mcopy_atomic */ page_kaddr = kmap_atomic(page); ret = copy_from_user(page_kaddr, (const void __user *)src_addr, PAGE_SIZE); kunmap_atomic(page_kaddr); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { *pagep = page; shmem_inode_unacct_blocks(inode, 1); /* don't free the page */ return -ENOENT; } } else { /* mfill_zeropage_atomic */ clear_highpage(page); } } else { page = *pagep; *pagep = NULL; } VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); __SetPageLocked(page); __SetPageSwapBacked(page); __SetPageUptodate(page); ret = -EFAULT; offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) goto out_release; ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, gfp & GFP_RECLAIM_MASK, dst_mm); if (ret) goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); else { /* * We don't set the pte dirty if the vma has no * VM_WRITE permission, so mark the page dirty or it * could be freed from under us. We could do it * unconditionally before unlock_page(), but doing it * only if VM_WRITE is not set is faster. */ set_page_dirty(page); } dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); ret = -EFAULT; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) goto out_release_unlock; ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_release_unlock; lru_cache_add(page); spin_lock_irq(&info->lock); info->alloced++; inode->i_blocks += BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); inc_mm_counter(dst_mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); pte_unmap_unlock(dst_pte, ptl); unlock_page(page); ret = 0; out: return ret; out_release_unlock: pte_unmap_unlock(dst_pte, ptl); ClearPageDirty(page); delete_from_page_cache(page); out_release: unlock_page(page); put_page(page); out_unacct_blocks: shmem_inode_unacct_blocks(inode, 1); goto out; } int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep) { return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, false, pagep); } int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { struct page *page = NULL; return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, 0, true, &page); } #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; #ifdef CONFIG_TMPFS_XATTR static int shmem_initxattrs(struct inode *, const struct xattr *, void *); #else #define shmem_initxattrs NULL #endif static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) { if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) return -EPERM; if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) return -EPERM; } return shmem_getpage(inode, index, pagep, SGP_WRITE); } static int shmem_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; if (pos + copied > inode->i_size) i_size_write(inode, pos + copied); if (!PageUptodate(page)) { struct page *head = compound_head(page); if (PageTransCompound(page)) { int i; for (i = 0; i < HPAGE_PMD_NR; i++) { if (head + i == page) continue; clear_highpage(head + i); flush_dcache_page(head + i); } } if (copied < PAGE_SIZE) { unsigned from = pos & (PAGE_SIZE - 1); zero_user_segments(page, 0, from, from + copied, PAGE_SIZE); } SetPageUptodate(head); } set_page_dirty(page); unlock_page(page); put_page(page); return copied; } static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; enum sgp_type sgp = SGP_READ; int error = 0; ssize_t retval = 0; loff_t *ppos = &iocb->ki_pos; /* * Might this read be for a stacking filesystem? Then when reading * holes of a sparse file, we actually need to allocate those pages, * and even mark them dirty, so it cannot exceed the max_blocks limit. */ if (!iter_is_iovec(to)) sgp = SGP_CACHE; index = *ppos >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page = NULL; pgoff_t end_index; unsigned long nr, ret; loff_t i_size = i_size_read(inode); end_index = i_size >> PAGE_SHIFT; if (index > end_index) break; if (index == end_index) { nr = i_size & ~PAGE_MASK; if (nr <= offset) break; } error = shmem_getpage(inode, index, &page, sgp); if (error) { if (error == -EINVAL) error = 0; break; } if (page) { if (sgp == SGP_CACHE) set_page_dirty(page); unlock_page(page); } /* * We must evaluate after, since reads (unlike writes) * are called without i_mutex protection against truncate */ nr = PAGE_SIZE; i_size = i_size_read(inode); end_index = i_size >> PAGE_SHIFT; if (index == end_index) { nr = i_size & ~PAGE_MASK; if (nr <= offset) { if (page) put_page(page); break; } } nr -= offset; if (page) { /* * If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * Mark the page accessed if we read the beginning. */ if (!offset) mark_page_accessed(page); } else { page = ZERO_PAGE(0); get_page(page); } /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { error = -EFAULT; break; } cond_resched(); } *ppos = ((loff_t) index << PAGE_SHIFT) + offset; file_accessed(file); return retval ? retval : error; } /* * llseek SEEK_DATA or SEEK_HOLE through the page cache. */ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pgoff_t index, pgoff_t end, int whence) { struct page *page; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; bool done = false; int i; pagevec_init(&pvec); pvec.nr = 1; /* start small: we may be there already */ while (!done) { pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) index = end; break; } for (i = 0; i < pvec.nr; i++, index++) { if (index < indices[i]) { if (whence == SEEK_HOLE) { done = true; break; } index = indices[i]; } page = pvec.pages[i]; if (page && !xa_is_value(page)) { if (!PageUptodate(page)) page = NULL; } if (index >= end || (page && whence == SEEK_DATA) || (!page && whence == SEEK_HOLE)) { done = true; break; } } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); } return index; } static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t start, end; loff_t new_offset; if (whence != SEEK_DATA && whence != SEEK_HOLE) return generic_file_llseek_size(file, offset, whence, MAX_LFS_FILESIZE, i_size_read(inode)); inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ if (offset < 0 || offset >= inode->i_size) offset = -ENXIO; else { start = offset >> PAGE_SHIFT; end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; new_offset = shmem_seek_hole_data(mapping, start, end, whence); new_offset <<= PAGE_SHIFT; if (new_offset > offset) { if (new_offset < inode->i_size) offset = new_offset; else if (whence == SEEK_DATA) offset = -ENXIO; else offset = inode->i_size; } } if (offset >= 0) offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); inode_unlock(inode); return offset; } static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_falloc shmem_falloc; pgoff_t start, index, end; int error; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); /* protected by i_mutex */ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { error = -EPERM; goto out; } shmem_falloc.waitq = &shmem_falloc_waitq; shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ spin_lock(&inode->i_lock); inode->i_private = NULL; wake_up_all(&shmem_falloc_waitq); WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head)); spin_unlock(&inode->i_lock); error = 0; goto out; } /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ error = inode_newsize_ok(inode, offset + len); if (error) goto out; if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { error = -EPERM; goto out; } start = offset >> PAGE_SHIFT; end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Try to avoid a swapstorm if len is impossible to satisfy */ if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { error = -ENOSPC; goto out; } shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; shmem_falloc.nr_unswapped = 0; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); for (index = start; index < end; index++) { struct page *page; /* * Good, the fallocate(2) manpage permits EINTR: we may have * been interrupted because we are using up too much memory. */ if (signal_pending(current)) error = -EINTR; else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) error = -ENOMEM; else error = shmem_getpage(inode, index, &page, SGP_FALLOC); if (error) { /* Remove the !PageUptodate pages we added */ if (index > start) { shmem_undo_range(inode, (loff_t)start << PAGE_SHIFT, ((loff_t)index << PAGE_SHIFT) - 1, true); } goto undone; } /* * Inform shmem_writepage() how far we have reached. * No need for lock or barrier: we have the page lock. */ shmem_falloc.next++; if (!PageUptodate(page)) shmem_falloc.nr_falloced++; /* * If !PageUptodate, leave it that way so that freeable pages * can be recognized if we need to rollback on error later. * But set_page_dirty so that memory pressure will swap rather * than free the pages we are allocating (and SGP_CACHE pages * might still be clean: we now need to mark those dirty too). */ set_page_dirty(page); unlock_page(page); put_page(page); cond_resched(); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = current_time(inode); undone: spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); out: inode_unlock(inode); return error; } static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; buf->f_bavail = buf->f_bfree = sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks); } if (sbinfo->max_inodes) { buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } /* else leave those fields 0 like simple_statfs */ return 0; } /* * File creation. Allocate an inode, and we're done.. */ static int shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; int error = -ENOSPC; inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = simple_acl_create(dir, inode); if (error) goto out_iput; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = 0; dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = current_time(dir); d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ } return error; out_iput: iput(inode); return error; } static int shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; int error = -ENOSPC; inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = simple_acl_create(dir, inode); if (error) goto out_iput; d_tmpfile(dentry, inode); } return error; out_iput: iput(inode); return error; } static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error; if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; inc_nlink(dir); return 0; } static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return shmem_mknod(dir, dentry, mode | S_IFREG, 0); } /* * Link a file.. */ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); int ret = 0; /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and * tmpfs dentries cannot be pruned until they are unlinked. * But if an O_TMPFILE file is linked into the tmpfs, the * first link must skip that, to get the accounting right. */ if (inode->i_nlink) { ret = shmem_reserve_inode(inode->i_sb, NULL); if (ret) goto out; } dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); inc_nlink(inode); ihold(inode); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); out: return ret; } static int shmem_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) shmem_free_inode(inode->i_sb); dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); drop_nlink(inode); dput(dentry); /* Undo the count from "create" - this does all the work */ return 0; } static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); drop_nlink(dir); return shmem_unlink(dir, dentry); } static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { bool old_is_dir = d_is_dir(old_dentry); bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { drop_nlink(old_dir); inc_nlink(new_dir); } else { drop_nlink(new_dir); inc_nlink(old_dir); } } old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = new_dir->i_mtime = d_inode(old_dentry)->i_ctime = d_inode(new_dentry)->i_ctime = current_time(old_dir); return 0; } static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) { struct dentry *whiteout; int error; whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name); if (!whiteout) return -ENOMEM; error = shmem_mknod(old_dir, whiteout, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); dput(whiteout); if (error) return error; /* * Cheat and hash the whiteout while the old dentry is still in * place, instead of playing games with FS_RENAME_DOES_D_MOVE. * * d_lookup() will consistently find one of them at this point, * not sure which one, but that isn't even important. */ d_rehash(whiteout); return 0; } /* * The VFS layer already does all the dentry stuff for rename, * we just have to decrement the usage count for the target if * it exists so that the VFS layer correctly free's it when it * gets overwritten. */ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *inode = d_inode(old_dentry); int they_are_dirs = S_ISDIR(inode->i_mode); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { int error; error = shmem_whiteout(old_dir, old_dentry); if (error) return error; } if (d_really_is_positive(new_dentry)) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; new_dir->i_size += BOGO_DIRENT_SIZE; old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = new_dir->i_mtime = inode->i_ctime = current_time(old_dir); return 0; } static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { int error; int len; struct inode *inode; struct page *page; len = strlen(symname) + 1; if (len > PAGE_SIZE) return -ENAMETOOLONG; inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK | 0777, 0, VM_NORESERVE); if (!inode) return -ENOSPC; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) { iput(inode); return error; } inode->i_size = len-1; if (len <= SHORT_SYMLINK_LEN) { inode->i_link = kmemdup(symname, len, GFP_KERNEL); if (!inode->i_link) { iput(inode); return -ENOMEM; } inode->i_op = &shmem_short_symlink_operations; } else { inode_nohighmem(inode); error = shmem_getpage(inode, 0, &page, SGP_WRITE); if (error) { iput(inode); return error; } inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; memcpy(page_address(page), symname, len); SetPageUptodate(page); set_page_dirty(page); unlock_page(page); put_page(page); } dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = current_time(dir); d_instantiate(dentry, inode); dget(dentry); return 0; } static void shmem_put_link(void *arg) { mark_page_accessed(arg); put_page(arg); } static const char *shmem_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct page *page = NULL; int error; if (!dentry) { page = find_get_page(inode->i_mapping, 0); if (!page) return ERR_PTR(-ECHILD); if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } } else { error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); unlock_page(page); } set_delayed_call(done, shmem_put_link, page); return page_address(page); } #ifdef CONFIG_TMPFS_XATTR /* * Superblocks without xattr inode operations may get some security.* xattr * support from the LSM "for free". As soon as we have any other xattrs * like ACLs, we also need to implement the security.* handlers at * filesystem level, though. */ /* * Callback for security_inode_init_security() for acquiring xattrs. */ static int shmem_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { struct shmem_inode_info *info = SHMEM_I(inode); const struct xattr *xattr; struct simple_xattr *new_xattr; size_t len; for (xattr = xattr_array; xattr->name != NULL; xattr++) { new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len); if (!new_xattr) return -ENOMEM; len = strlen(xattr->name) + 1; new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, GFP_KERNEL); if (!new_xattr->name) { kvfree(new_xattr); return -ENOMEM; } memcpy(new_xattr->name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN, xattr->name, len); simple_xattr_list_add(&info->xattrs, new_xattr); } return 0; } static int shmem_xattr_handler_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_get(&info->xattrs, name, buffer, size); } static int shmem_xattr_handler_set(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_set(&info->xattrs, name, value, size, flags, NULL); } static const struct xattr_handler shmem_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler shmem_trusted_xattr_handler = { .prefix = XATTR_TRUSTED_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler *shmem_xattr_handlers[] = { #ifdef CONFIG_TMPFS_POSIX_ACL &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, #endif &shmem_security_xattr_handler, &shmem_trusted_xattr_handler, NULL }; static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size); } #endif /* CONFIG_TMPFS_XATTR */ static const struct inode_operations shmem_short_symlink_operations = { .get_link = simple_get_link, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif }; static const struct inode_operations shmem_symlink_inode_operations = { .get_link = shmem_get_link, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif }; static struct dentry *shmem_get_parent(struct dentry *child) { return ERR_PTR(-ESTALE); } static int shmem_match(struct inode *ino, void *vfh) { __u32 *fh = vfh; __u64 inum = fh[2]; inum = (inum << 32) | fh[1]; return ino->i_ino == inum && fh[0] == ino->i_generation; } /* Find any alias of inode, but prefer a hashed alias */ static struct dentry *shmem_find_alias(struct inode *inode) { struct dentry *alias = d_find_alias(inode); return alias ?: d_find_any_alias(inode); } static struct dentry *shmem_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct inode *inode; struct dentry *dentry = NULL; u64 inum; if (fh_len < 3) return NULL; inum = fid->raw[2]; inum = (inum << 32) | fid->raw[1]; inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), shmem_match, fid->raw); if (inode) { dentry = shmem_find_alias(inode); iput(inode); } return dentry; } static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, struct inode *parent) { if (*len < 3) { *len = 3; return FILEID_INVALID; } if (inode_unhashed(inode)) { /* Unfortunately insert_inode_hash is not idempotent, * so as we hash inodes here rather than at creation * time, we need a lock to ensure we only try * to do it once */ static DEFINE_SPINLOCK(lock); spin_lock(&lock); if (inode_unhashed(inode)) __insert_inode_hash(inode, inode->i_ino + inode->i_generation); spin_unlock(&lock); } fh[0] = inode->i_generation; fh[1] = inode->i_ino; fh[2] = ((__u64)inode->i_ino) >> 32; *len = 3; return 1; } static const struct export_operations shmem_export_ops = { .get_parent = shmem_get_parent, .encode_fh = shmem_encode_fh, .fh_to_dentry = shmem_fh_to_dentry, }; enum shmem_param { Opt_gid, Opt_huge, Opt_mode, Opt_mpol, Opt_nr_blocks, Opt_nr_inodes, Opt_size, Opt_uid, Opt_inode32, Opt_inode64, }; static const struct constant_table shmem_param_enums_huge[] = { {"never", SHMEM_HUGE_NEVER }, {"always", SHMEM_HUGE_ALWAYS }, {"within_size", SHMEM_HUGE_WITHIN_SIZE }, {"advise", SHMEM_HUGE_ADVISE }, {} }; const struct fs_parameter_spec shmem_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_enum ("huge", Opt_huge, shmem_param_enums_huge), fsparam_u32oct("mode", Opt_mode), fsparam_string("mpol", Opt_mpol), fsparam_string("nr_blocks", Opt_nr_blocks), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("size", Opt_size), fsparam_u32 ("uid", Opt_uid), fsparam_flag ("inode32", Opt_inode32), fsparam_flag ("inode64", Opt_inode64), {} }; static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) { struct shmem_options *ctx = fc->fs_private; struct fs_parse_result result; unsigned long long size; char *rest; int opt; kuid_t kuid; kgid_t kgid; opt = fs_parse(fc, shmem_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_size: size = memparse(param->string, &rest); if (*rest == '%') { size <<= PAGE_SHIFT; size *= totalram_pages(); do_div(size, 100); rest++; } if (*rest) goto bad_value; ctx->blocks = DIV_ROUND_UP(size, PAGE_SIZE); ctx->seen |= SHMEM_SEEN_BLOCKS; break; case Opt_nr_blocks: ctx->blocks = memparse(param->string, &rest); if (*rest) goto bad_value; ctx->seen |= SHMEM_SEEN_BLOCKS; break; case Opt_nr_inodes: ctx->inodes = memparse(param->string, &rest); if (*rest) goto bad_value; ctx->seen |= SHMEM_SEEN_INODES; break; case Opt_mode: ctx->mode = result.uint_32 & 07777; break; case Opt_uid: kuid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(kuid)) goto bad_value; /* * The requested uid must be representable in the * filesystem's idmapping. */ if (!kuid_has_mapping(fc->user_ns, kuid)) goto bad_value; ctx->uid = kuid; break; case Opt_gid: kgid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(kgid)) goto bad_value; /* * The requested gid must be representable in the * filesystem's idmapping. */ if (!kgid_has_mapping(fc->user_ns, kgid)) goto bad_value; ctx->gid = kgid; break; case Opt_huge: ctx->huge = result.uint_32; if (ctx->huge != SHMEM_HUGE_NEVER && !(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && has_transparent_hugepage())) goto unsupported_parameter; ctx->seen |= SHMEM_SEEN_HUGE; break; case Opt_mpol: if (IS_ENABLED(CONFIG_NUMA)) { mpol_put(ctx->mpol); ctx->mpol = NULL; if (mpol_parse_str(param->string, &ctx->mpol)) goto bad_value; break; } goto unsupported_parameter; case Opt_inode32: ctx->full_inums = false; ctx->seen |= SHMEM_SEEN_INUMS; break; case Opt_inode64: if (sizeof(ino_t) < 8) { return invalfc(fc, "Cannot use inode64 with <64bit inums in kernel\n"); } ctx->full_inums = true; ctx->seen |= SHMEM_SEEN_INUMS; break; } return 0; unsupported_parameter: return invalfc(fc, "Unsupported parameter '%s'", param->key); bad_value: return invalfc(fc, "Bad value for '%s'", param->key); } static int shmem_parse_options(struct fs_context *fc, void *data) { char *options = data; if (options) { int err = security_sb_eat_lsm_opts(options, &fc->security); if (err) return err; } while (options != NULL) { char *this_char = options; for (;;) { /* * NUL-terminate this option: unfortunately, * mount options form a comma-separated list, * but mpol's nodelist may also contain commas. */ options = strchr(options, ','); if (options == NULL) break; options++; if (!isdigit(*options)) { options[-1] = '\0'; break; } } if (*this_char) { char *value = strchr(this_char,'='); size_t len = 0; int err; if (value) { *value++ = '\0'; len = strlen(value); } err = vfs_parse_fs_string(fc, this_char, value, len); if (err < 0) return err; } } return 0; } /* * Reconfigure a shmem filesystem. * * Note that we disallow change from limited->unlimited blocks/inodes while any * are in use; but we must separately disallow unlimited->limited, because in * that case we have no record of how much is already in use. */ static int shmem_reconfigure(struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb); unsigned long inodes; const char *err; spin_lock(&sbinfo->stat_lock); inodes = sbinfo->max_inodes - sbinfo->free_inodes; if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { if (!sbinfo->max_blocks) { err = "Cannot retroactively limit size"; goto out; } if (percpu_counter_compare(&sbinfo->used_blocks, ctx->blocks) > 0) { err = "Too small a size for current use"; goto out; } } if ((ctx->seen & SHMEM_SEEN_INODES) && ctx->inodes) { if (!sbinfo->max_inodes) { err = "Cannot retroactively limit inodes"; goto out; } if (ctx->inodes < inodes) { err = "Too few inodes for current use"; goto out; } } if ((ctx->seen & SHMEM_SEEN_INUMS) && !ctx->full_inums && sbinfo->next_ino > UINT_MAX) { err = "Current inum too high to switch to 32-bit inums"; goto out; } if (ctx->seen & SHMEM_SEEN_HUGE) sbinfo->huge = ctx->huge; if (ctx->seen & SHMEM_SEEN_INUMS) sbinfo->full_inums = ctx->full_inums; if (ctx->seen & SHMEM_SEEN_BLOCKS) sbinfo->max_blocks = ctx->blocks; if (ctx->seen & SHMEM_SEEN_INODES) { sbinfo->max_inodes = ctx->inodes; sbinfo->free_inodes = ctx->inodes - inodes; } /* * Preserve previous mempolicy unless mpol remount option was specified. */ if (ctx->mpol) { mpol_put(sbinfo->mpol); sbinfo->mpol = ctx->mpol; /* transfers initial ref */ ctx->mpol = NULL; } spin_unlock(&sbinfo->stat_lock); return 0; out: spin_unlock(&sbinfo->stat_lock); return invalfc(fc, "%s", err); } static int shmem_show_options(struct seq_file *seq, struct dentry *root) { struct shmem_sb_info *sbinfo = SHMEM_SB(root->d_sb); if (sbinfo->max_blocks != shmem_default_max_blocks()) seq_printf(seq, ",size=%luk", sbinfo->max_blocks << (PAGE_SHIFT - 10)); if (sbinfo->max_inodes != shmem_default_max_inodes()) seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); if (sbinfo->mode != (0777 | S_ISVTX)) seq_printf(seq, ",mode=%03ho", sbinfo->mode); if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbinfo->uid)); if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); /* * Showing inode{64,32} might be useful even if it's the system default, * since then people don't have to resort to checking both here and * /proc/config.gz to confirm 64-bit inums were successfully applied * (which may not even exist if IKCONFIG_PROC isn't enabled). * * We hide it when inode64 isn't the default and we are using 32-bit * inodes, since that probably just means the feature isn't even under * consideration. * * As such: * * +-----------------+-----------------+ * | TMPFS_INODE64=y | TMPFS_INODE64=n | * +------------------+-----------------+-----------------+ * | full_inums=true | show | show | * | full_inums=false | show | hide | * +------------------+-----------------+-----------------+ * */ if (IS_ENABLED(CONFIG_TMPFS_INODE64) || sbinfo->full_inums) seq_printf(seq, ",inode%d", (sbinfo->full_inums ? 64 : 32)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Rightly or wrongly, show huge mount option unmasked by shmem_huge */ if (sbinfo->huge) seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge)); #endif shmem_show_mpol(seq, sbinfo->mpol); return 0; } #endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); free_percpu(sbinfo->ino_batch); percpu_counter_destroy(&sbinfo->used_blocks); mpol_put(sbinfo->mpol); kfree(sbinfo); sb->s_fs_info = NULL; } static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; struct inode *inode; struct shmem_sb_info *sbinfo; int err = -ENOMEM; /* Round up to L1_CACHE_BYTES to resist false sharing */ sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info), L1_CACHE_BYTES), GFP_KERNEL); if (!sbinfo) return -ENOMEM; sb->s_fs_info = sbinfo; #ifdef CONFIG_TMPFS /* * Per default we only allow half of the physical ram per * tmpfs instance, limiting inodes to one per page of lowmem; * but the internal instance is left unlimited. */ if (!(sb->s_flags & SB_KERNMOUNT)) { if (!(ctx->seen & SHMEM_SEEN_BLOCKS)) ctx->blocks = shmem_default_max_blocks(); if (!(ctx->seen & SHMEM_SEEN_INODES)) ctx->inodes = shmem_default_max_inodes(); if (!(ctx->seen & SHMEM_SEEN_INUMS)) ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64); } else { sb->s_flags |= SB_NOUSER; } sb->s_export_op = &shmem_export_ops; sb->s_flags |= SB_NOSEC; #else sb->s_flags |= SB_NOUSER; #endif sbinfo->max_blocks = ctx->blocks; sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes; if (sb->s_flags & SB_KERNMOUNT) { sbinfo->ino_batch = alloc_percpu(ino_t); if (!sbinfo->ino_batch) goto failed; } sbinfo->uid = ctx->uid; sbinfo->gid = ctx->gid; sbinfo->full_inums = ctx->full_inums; sbinfo->mode = ctx->mode; sbinfo->huge = ctx->huge; sbinfo->mpol = ctx->mpol; ctx->mpol = NULL; spin_lock_init(&sbinfo->stat_lock); if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) goto failed; spin_lock_init(&sbinfo->shrinklist_lock); INIT_LIST_HEAD(&sbinfo->shrinklist); sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; sb->s_time_gran = 1; #ifdef CONFIG_TMPFS_XATTR sb->s_xattr = shmem_xattr_handlers; #endif #ifdef CONFIG_TMPFS_POSIX_ACL sb->s_flags |= SB_POSIXACL; #endif uuid_gen(&sb->s_uuid); inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; inode->i_uid = sbinfo->uid; inode->i_gid = sbinfo->gid; sb->s_root = d_make_root(inode); if (!sb->s_root) goto failed; return 0; failed: shmem_put_super(sb); return err; } static int shmem_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, shmem_fill_super); } static void shmem_free_fc(struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; if (ctx) { mpol_put(ctx->mpol); kfree(ctx); } } static const struct fs_context_operations shmem_fs_context_ops = { .free = shmem_free_fc, .get_tree = shmem_get_tree, #ifdef CONFIG_TMPFS .parse_monolithic = shmem_parse_options, .parse_param = shmem_parse_one, .reconfigure = shmem_reconfigure, #endif }; static struct kmem_cache *shmem_inode_cachep; static struct inode *shmem_alloc_inode(struct super_block *sb) { struct shmem_inode_info *info; info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); if (!info) return NULL; return &info->vfs_inode; } static void shmem_free_in_core_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } static void shmem_destroy_inode(struct inode *inode) { if (S_ISREG(inode->i_mode)) mpol_free_shared_policy(&SHMEM_I(inode)->policy); } static void shmem_init_inode(void *foo) { struct shmem_inode_info *info = foo; inode_init_once(&info->vfs_inode); } static void shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); } static void shmem_destroy_inodecache(void) { kmem_cache_destroy(shmem_inode_cachep); } static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, #ifdef CONFIG_TMPFS .write_begin = shmem_write_begin, .write_end = shmem_write_end, #endif #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif .error_remove_page = generic_error_remove_page, }; static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, .get_unmapped_area = shmem_get_unmapped_area, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, .read_iter = shmem_file_read_iter, .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif }; static const struct inode_operations shmem_inode_operations = { .getattr = shmem_getattr, .setattr = shmem_setattr, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, .set_acl = simple_set_acl, #endif }; static const struct inode_operations shmem_dir_inode_operations = { #ifdef CONFIG_TMPFS .create = shmem_create, .lookup = simple_lookup, .link = shmem_link, .unlink = shmem_unlink, .symlink = shmem_symlink, .mkdir = shmem_mkdir, .rmdir = shmem_rmdir, .mknod = shmem_mknod, .rename = shmem_rename2, .tmpfile = shmem_tmpfile, #endif #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, .set_acl = simple_set_acl, #endif }; static const struct inode_operations shmem_special_inode_operations = { #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, .set_acl = simple_set_acl, #endif }; static const struct super_operations shmem_ops = { .alloc_inode = shmem_alloc_inode, .free_inode = shmem_free_in_core_inode, .destroy_inode = shmem_destroy_inode, #ifdef CONFIG_TMPFS .statfs = shmem_statfs, .show_options = shmem_show_options, #endif .evict_inode = shmem_evict_inode, .drop_inode = generic_delete_inode, .put_super = shmem_put_super, #ifdef CONFIG_TRANSPARENT_HUGEPAGE .nr_cached_objects = shmem_unused_huge_count, .free_cached_objects = shmem_unused_huge_scan, #endif }; static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif }; int shmem_init_fs_context(struct fs_context *fc) { struct shmem_options *ctx; ctx = kzalloc(sizeof(struct shmem_options), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->mode = 0777 | S_ISVTX; ctx->uid = current_fsuid(); ctx->gid = current_fsgid(); fc->fs_private = ctx; fc->ops = &shmem_fs_context_ops; return 0; } static struct file_system_type shmem_fs_type = { .owner = THIS_MODULE, .name = "tmpfs", .init_fs_context = shmem_init_fs_context, #ifdef CONFIG_TMPFS .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT, }; int __init shmem_init(void) { int error; shmem_init_inodecache(); error = register_filesystem(&shmem_fs_type); if (error) { pr_err("Could not register tmpfs\n"); goto out2; } shm_mnt = kern_mount(&shmem_fs_type); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); pr_err("Could not kern_mount tmpfs\n"); goto out1; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; else shmem_huge = 0; /* just in case it was patched */ #endif return 0; out1: unregister_filesystem(&shmem_fs_type); out2: shmem_destroy_inodecache(); shm_mnt = ERR_PTR(error); return error; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) static ssize_t shmem_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { static const int values[] = { SHMEM_HUGE_ALWAYS, SHMEM_HUGE_WITHIN_SIZE, SHMEM_HUGE_ADVISE, SHMEM_HUGE_NEVER, SHMEM_HUGE_DENY, SHMEM_HUGE_FORCE, }; int i, count; for (i = 0, count = 0; i < ARRAY_SIZE(values); i++) { const char *fmt = shmem_huge == values[i] ? "[%s] " : "%s "; count += sprintf(buf + count, fmt, shmem_format_huge(values[i])); } buf[count - 1] = '\n'; return count; } static ssize_t shmem_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { char tmp[16]; int huge; if (count + 1 > sizeof(tmp)) return -EINVAL; memcpy(tmp, buf, count); tmp[count] = '\0'; if (count && tmp[count - 1] == '\n') tmp[count - 1] = '\0'; huge = shmem_parse_huge(tmp); if (huge == -EINVAL) return -EINVAL; if (!has_transparent_hugepage() && huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) return -EINVAL; shmem_huge = huge; if (shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; return count; } struct kobj_attribute shmem_enabled_attr = __ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool shmem_huge_enabled(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); loff_t i_size; pgoff_t off; if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (shmem_huge == SHMEM_HUGE_FORCE) return true; if (shmem_huge == SHMEM_HUGE_DENY) return false; switch (sbinfo->huge) { case SHMEM_HUGE_NEVER: return false; case SHMEM_HUGE_ALWAYS: return true; case SHMEM_HUGE_WITHIN_SIZE: off = round_up(vma->vm_pgoff, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); if (i_size >= HPAGE_PMD_SIZE && i_size >> PAGE_SHIFT >= off) return true; fallthrough; case SHMEM_HUGE_ADVISE: /* TODO: implement fadvise() hints */ return (vma->vm_flags & VM_HUGEPAGE); default: VM_BUG_ON(1); return false; } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #else /* !CONFIG_SHMEM */ /* * tiny-shmem: simple shmemfs and tmpfs using ramfs code * * This is intended for small system where the benefits of the full * shmem code (swap-backed and resource-limited) are outweighed by * their complexity. On systems without swap this code should be * effectively equivalent, but much lighter weight. */ static struct file_system_type shmem_fs_type = { .name = "tmpfs", .init_fs_context = ramfs_init_fs_context, .parameters = ramfs_fs_parameters, .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) { BUG_ON(register_filesystem(&shmem_fs_type) != 0); shm_mnt = kern_mount(&shmem_fs_type); BUG_ON(IS_ERR(shm_mnt)); return 0; } int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { return 0; } int shmem_lock(struct file *file, int lock, struct user_struct *user) { return 0; } void shmem_unlock_mapping(struct address_space *mapping) { } #ifdef CONFIG_MMU unsigned long shmem_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); } #endif void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend); } EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations #define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) #endif /* CONFIG_SHMEM */ /* common code */ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags, unsigned int i_flags) { struct inode *inode; struct file *res; if (IS_ERR(mnt)) return ERR_CAST(mnt); if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) return ERR_PTR(-ENOMEM); inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (unlikely(!inode)) { shmem_unacct_size(flags, size); return ERR_PTR(-ENOSPC); } inode->i_flags |= i_flags; inode->i_size = size; clear_nlink(inode); /* It is unlinked */ res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); if (!IS_ERR(res)) res = alloc_file_pseudo(inode, mnt, name, O_RDWR, &shmem_file_operations); if (IS_ERR(res)) iput(inode); return res; } /** * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be * kernel internal. There will be NO LSM permission checks against the * underlying inode. So users of this interface must do LSM checks at a * higher layer. The users are the big_key and shm implementations. LSM * checks are provided at the key or shm level rather than the inode. * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(shm_mnt, name, size, flags, S_PRIVATE); } /** * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(shm_mnt, name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup); /** * shmem_file_setup_with_mnt - get an unlinked file living in tmpfs * @mnt: the tmpfs mount where the file will be created * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(mnt, name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup_with_mnt); /** * shmem_zero_setup - setup a shared anonymous mapping * @vma: the vma to be mmapped is prepared by do_mmap */ int shmem_zero_setup(struct vm_area_struct *vma) { struct file *file; loff_t size = vma->vm_end - vma->vm_start; /* * Cloning a new file under mmap_lock leads to a lock ordering conflict * between XFS directory reading and selinux: since this file is only * accessible to the user through its mapping, use S_PRIVATE flag to * bypass file security, in the same way as shmem_kernel_file_setup(). */ file = shmem_kernel_file_setup("dev/zero", size, vma->vm_flags); if (IS_ERR(file)) return PTR_ERR(file); if (vma->vm_file) fput(vma->vm_file); vma->vm_file = file; vma->vm_ops = &shmem_vm_ops; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < (vma->vm_end & HPAGE_PMD_MASK)) { khugepaged_enter(vma, vma->vm_flags); } return 0; } /** * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", * with any new page allocations done using the specified allocation flags. * But read_cache_page_gfp() uses the ->readpage() method: which does not * suit tmpfs, since it may have pages in swapcache, and needs to find those * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. * * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. */ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { #ifdef CONFIG_SHMEM struct inode *inode = mapping->host; struct page *page; int error; BUG_ON(mapping->a_ops != &shmem_aops); error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL, NULL, NULL); if (error) page = ERR_PTR(error); else unlock_page(page); return page; #else /* * The tiny !SHMEM case uses ramfs without swap */ return read_cache_page_gfp(mapping, index, gfp); #endif } EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/ima.h> #include <linux/dnotify.h> #include <linux/compat.h> #include "internal.h" int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ ret = notify_change(dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { struct inode *inode; long error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = mnt_want_write(path->mnt); if (error) goto out; error = inode_permission(inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = locks_verify_truncate(inode, NULL, length); if (!error) error = security_path_truncate(path); if (!error) error = do_truncate(path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); out: return error; } EXPORT_SYMBOL_GPL(vfs_truncate); long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (!error) { error = vfs_truncate(&path, length); path_put(&path); } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return do_sys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return do_sys_truncate(path, length); } #endif long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; struct fd f; int error; error = -EINVAL; if (length < 0) goto out; error = -EBADF; f = fdget(fd); if (!f.file) goto out; /* explicitly opened as large or we are on 64-bit box */ if (f.file->f_flags & O_LARGEFILE) small = 0; dentry = f.file->f_path.dentry; inode = dentry->d_inode; error = -EINVAL; if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE)) goto out_putf; error = -EINVAL; /* Cannot ftruncate over 2^31 bytes without large file support */ if (small && length > MAX_NON_LFS) goto out_putf; error = -EPERM; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(f.file))) goto out_putf; sb_start_write(inode->i_sb); error = locks_verify_truncate(inode, f.file, length); if (!error) error = security_path_truncate(&f.file->f_path); if (!error) error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length) { return do_sys_ftruncate(fd, length, 1); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length) { return do_sys_ftruncate(fd, length, 1); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return do_sys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return do_sys_ftruncate(fd, length, 0); } #endif /* BITS_PER_LONG == 32 */ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret; if (offset < 0 || len <= 0) return -EINVAL; /* Return error if mode is not supported */ if (mode & ~FALLOC_FL_SUPPORTED_MASK) return -EOPNOTSUPP; /* Punch hole and zero range are mutually exclusive */ if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; /* Punch hole must have keep size set */ if ((mode & FALLOC_FL_PUNCH_HOLE) && !(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* Collapse range should only be used exclusively. */ if ((mode & FALLOC_FL_COLLAPSE_RANGE) && (mode & ~FALLOC_FL_COLLAPSE_RANGE)) return -EINVAL; /* Insert range should only be used exclusively. */ if ((mode & FALLOC_FL_INSERT_RANGE) && (mode & ~FALLOC_FL_INSERT_RANGE)) return -EINVAL; /* Unshare range should only be used with allocate mode. */ if ((mode & FALLOC_FL_UNSHARE_RANGE) && (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * We can only allow pure fallocate on append only files */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wrap through zero too */ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fallocate(f.file, mode, offset, len); fdput(f); } return error; } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. */ static const struct cred *access_override_creds(void) { const struct cred *old_cred; struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-RCY. */ override_cred->non_rcu = 1; old_cred = override_creds(override_cred); /* override_cred() gets its own ref */ put_cred(override_cred); return old_cred; } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (!(flags & AT_EACCESS)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } retry: res = user_path_at(dfd, filename, lookup_flags, &path); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path)) goto out_path_release; } res = inode_permission(inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; /* * This is a rare case where using __mnt_is_readonly() * is OK without a mnt_want/drop_write() pair. Since * no actual write to the fs is performed here, we do * not need to telegraph to that to anyone. * * By doing this, we accept that this access is * inherently racy and know that the fs may change * state before we even see this result. */ if (__mnt_is_readonly(path.mnt)) res = -EROFS; out_path_release: path_put(&path); if (retry_estale(res, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: if (old_cred) revert_creds(old_cred); return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { return do_faccessat(dfd, filename, mode, 0); } SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, int, flags) { return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return do_faccessat(AT_FDCWD, filename, mode, 0); } SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; set_fs_pwd(current->fs, &path); dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); int error; error = -EBADF; if (!f.file) goto out; error = -ENOTDIR; if (!d_can_lookup(f.file->f_path.dentry)) goto out_putf; error = file_permission(f.file, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (error) goto dput_and_out; set_fs_root(current->fs, &path); error = 0; dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; struct iattr newattrs; int error; error = mnt_want_write(path->mnt); if (error) return error; retry_deleg: inode_lock(inode); error = security_path_chmod(path, mode); if (error) goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path->mnt); return error; } int vfs_fchmod(struct file *file, umode_t mode) { audit_file(file); return chmod_common(&file->f_path, mode); } SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { struct fd f = fdget(fd); int err = -EBADF; if (f.file) { err = vfs_fchmod(f.file, mode); fdput(f); } return err; } static int do_fchmodat(int dfd, const char __user *filename, umode_t mode) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (!error) { error = chmod_common(&path, mode); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) { return do_fchmodat(dfd, filename, mode); } SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { return do_fchmodat(AT_FDCWD, filename, mode); } int chown_common(const struct path *path, uid_t user, gid_t group) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; struct iattr newattrs; kuid_t uid; kgid_t gid; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); retry_deleg: newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { if (!uid_valid(uid)) return -EINVAL; newattrs.ia_valid |= ATTR_UID; newattrs.ia_uid = uid; } if (group != (gid_t) -1) { if (!gid_valid(gid)) return -EINVAL; newattrs.ia_valid |= ATTR_GID; newattrs.ia_gid = gid; } inode_lock(inode); if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(inode); error = security_path_chown(path, uid, gid); if (!error) error = notify_change(path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag) { struct path path; int error = -EINVAL; int lookup_flags; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) goto out; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = mnt_want_write(path.mnt); if (error) goto out_release; error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { return do_fchownat(dfd, filename, user, group, flag); } SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, AT_SYMLINK_NOFOLLOW); } int vfs_fchown(struct file *file, uid_t user, gid_t group) { int error; error = mnt_want_write_file(file); if (error) return error; audit_file(file); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); return error; } int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fchown(f.file, user, group); fdput(f); } return error; } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { return ksys_fchown(fd, user, group); } static int do_dentry_open(struct file *f, struct inode *inode, int (*open)(struct inode *, struct file *)) { static const struct file_operations empty_fops = {}; int error; path_get(&f->f_path); f->f_inode = inode; f->f_mapping = inode->i_mapping; f->f_wb_err = filemap_sample_wb_err(f->f_mapping); f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH | FMODE_OPENED; f->f_op = &empty_fops; return 0; } if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) goto cleanup_file; error = __mnt_want_write(f->f_path.mnt); if (unlikely(error)) { put_write_access(inode); goto cleanup_file; } f->f_mode |= FMODE_WRITER; } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } error = security_file_open(f); if (error) goto cleanup_all; error = break_lease(locks_inode(f), f->f_flags); if (error) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (!open) open = f->f_op->open; if (open) { error = open(inode, f); if (error) goto cleanup_all; } f->f_mode |= FMODE_OPENED; if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(inode); if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; f->f_write_hint = WRITE_LIFE_NOT_SET; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); /* NB: we're sure to have correct a_ops only after f_op->open */ if (f->f_flags & O_DIRECT) { if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO) return -EINVAL; } /* * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ if ((f->f_mode & FMODE_WRITE) && filemap_nr_thps(inode->i_mapping)) truncate_pagecache(inode, 0); return 0; cleanup_all: if (WARN_ON_ONCE(error > 0)) error = -EINVAL; fops_put(f->f_op); if (f->f_mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(f->f_path.mnt); } cleanup_file: path_put(&f->f_path); f->f_path.mnt = NULL; f->f_path.dentry = NULL; f->f_inode = NULL; return error; } /** * finish_open - finish opening a file * @file: file pointer * @dentry: pointer to dentry * @open: open callback * @opened: state of open * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. * * NB: the dentry reference is _not_ consumed. If, for example, the dentry is * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry; return do_dentry_open(file, d_backing_inode(dentry), open); } EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer * @dentry: dentry, ERR_PTR(-E...) or NULL (as returned from ->lookup()) * * This can be used to set the result of a lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * * Returns 0 or -E..., which must be the return value of ->atomic_open() after * having called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { if (IS_ERR(dentry)) return PTR_ERR(dentry); file->f_path.dentry = dentry; return 0; } EXPORT_SYMBOL(finish_no_open); char *file_path(struct file *filp, char *buf, int buflen) { return d_path(&filp->f_path, buf, buflen); } EXPORT_SYMBOL(file_path); /** * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized * @cred: credentials to use */ int vfs_open(const struct path *path, struct file *file) { file->f_path = *path; return do_dentry_open(file, d_backing_inode(path->dentry), NULL); } struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; struct file *f; validate_creds(cred); /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(dentry_open); /** * dentry_create - Create and open a file * @path: path to create * @flags: O_ flags * @mode: mode bits for new file * @cred: credentials to use * * Caller must hold the parent directory's lock, and have prepared * a negative dentry, placed in @path->dentry, for the new file. * * Caller sets @path->mnt to the vfsmount of the filesystem where * the new file is to be created. The parent directory and the * negative dentry must reside on the same filesystem instance. * * On success, returns a "struct file *". Otherwise a ERR_PTR * is returned. */ struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred) { struct file *f; int error; validate_creds(cred); f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; error = vfs_create(d_inode(path->dentry->d_parent), path->dentry, mode, true); if (!error) error = vfs_open(path, f); if (unlikely(error)) { fput(f); return ERR_PTR(error); } return f; } EXPORT_SYMBOL(dentry_create); struct file *open_with_fake_path(const struct path *path, int flags, struct inode *inode, const struct cred *cred) { struct file *f = alloc_empty_file_noaccount(flags, cred); if (!IS_ERR(f)) { int error; f->f_path = *path; error = do_dentry_open(f, inode, NULL); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(open_with_fake_path); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) inline struct open_how build_open_how(int flags, umode_t mode) { struct open_how how = { .flags = flags & VALID_OPEN_FLAGS, .mode = mode & S_IALLUGO, }; /* O_PATH beats everything else. */ if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS; /* Modes should only be set for create-like flags. */ if (!WILL_CREATE(how.flags)) how.mode = 0; return how; } inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; u64 strip = FMODE_NONOTIFY | O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), "struct open_flags doesn't yet handle flags > 32 bits"); /* * Strip flags that either shouldn't be set by userspace like * FMODE_NONOTIFY or that aren't relevant in determining struct * open_flags like O_CLOEXEC. */ flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ if (flags & ~VALID_OPEN_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; /* Scoping flags are mutually exclusive. */ if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT)) return -EINVAL; /* Deal with the mode. */ if (WILL_CREATE(flags)) { if (how->mode & ~S_IALLUGO) return -EINVAL; op->mode = how->mode | S_IFREG; } else { if (how->mode != 0) return -EINVAL; op->mode = 0; } /* * In order to ensure programs get explicit errors when trying to use * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we * have to require userspace to explicitly set it. */ if (flags & __O_TMPFILE) { if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; } if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) return -EINVAL; acc_mode = 0; } /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's * always set instead of having to deal with possibly weird behaviour * for malicious applications setting only __O_SYNC. */ if (flags & __O_SYNC) flags |= O_DSYNC; op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ if (flags & O_TRUNC) acc_mode |= MAY_WRITE; /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flags & O_APPEND) acc_mode |= MAY_APPEND; op->acc_mode = acc_mode; op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; if (flags & O_CREAT) { op->intent |= LOOKUP_CREATE; if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL; flags |= O_NOFOLLOW; } } if (flags & O_DIRECTORY) lookup_flags |= LOOKUP_DIRECTORY; if (!(flags & O_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (how->resolve & RESOLVE_NO_XDEV) lookup_flags |= LOOKUP_NO_XDEV; if (how->resolve & RESOLVE_NO_MAGICLINKS) lookup_flags |= LOOKUP_NO_MAGICLINKS; if (how->resolve & RESOLVE_NO_SYMLINKS) lookup_flags |= LOOKUP_NO_SYMLINKS; if (how->resolve & RESOLVE_BENEATH) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } op->lookup_flags = lookup_flags; return 0; } /** * file_open_name - open file and return file pointer * * @name: struct filename containing path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *file_open_name(struct filename *name, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_filp_open(AT_FDCWD, name, &op); } /** * filp_open - open file and return file pointer * * @filename: path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *filp_open(const char *filename, int flags, umode_t mode) { struct filename *name = getname_kernel(filename); struct file *file = ERR_CAST(name); if (!IS_ERR(name)) { file = file_open_name(name, flags, mode); putname(name); } return file; } EXPORT_SYMBOL(filp_open); struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *filename, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); static long do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; int fd = build_open_flags(how, &op); struct filename *tmp; if (fd) return fd; tmp = getname(filename); if (IS_ERR(tmp)) return PTR_ERR(tmp); fd = get_unused_fd_flags(how->flags); if (fd >= 0) { struct file *f = do_filp_open(dfd, tmp, &op); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); } else { fsnotify_open(f); fd_install(fd, f); } } putname(tmp); return fd; } long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_how how = build_open_how(flags, mode); return do_sys_openat2(dfd, filename, &how); } SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(dfd, filename, flags, mode); } SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, struct open_how __user *, how, size_t, usize) { int err; struct open_how tmp; BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0); BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST); if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) return err; /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; return do_sys_openat2(dfd, filename, &tmp); } #ifdef CONFIG_COMPAT /* * Exactly like sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(AT_FDCWD, filename, flags, mode); } /* * Exactly like sys_openat(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(dfd, filename, flags, mode); } #endif #ifndef __alpha__ /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { int flags = O_CREAT | O_WRONLY | O_TRUNC; if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, pathname, flags, mode); } #endif /* * "id" is the POSIX thread ID. We use the * files pointer for this.. */ int filp_close(struct file *filp, fl_owner_t id) { int retval = 0; if (!file_count(filp)) { printk(KERN_ERR "VFS: Close: file count is 0\n"); return 0; } if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id); locks_remove_posix(filp, id); } fput(filp); return retval; } EXPORT_SYMBOL(filp_close); /* * Careful here! We test whether the file pointer is NULL before * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ SYSCALL_DEFINE1(close, unsigned int, fd) { int retval = close_fd(fd); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || retval == -ERESTARTNOINTR || retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; return retval; } /** * close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: reserved for future extensions * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { return __close_range(fd, max_fd, flags); } /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); return 0; } return -EPERM; } /* * Called when an inode is about to be open. * We use this to disallow opening large files on 32bit systems if * the caller didn't specify O_LARGEFILE. On 64bit systems we force * on this flag in sys_open. */ int generic_file_open(struct inode * inode, struct file * filp) { if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(generic_file_open); /* * This is used by subsystems that don't want seekable * file descriptors. The function is not supposed to ever fail, the only * reason it returns an 'int' and not 'void' is so that it can be plugged * directly into file_operations structure. */ int nonseekable_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); return 0; } EXPORT_SYMBOL(nonseekable_open); /* * stream_open is used by subsystems that want stream-like file descriptors. * Such file descriptors are not seekable and don't have notion of position * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). * Contrary to file descriptors of other regular files, .read() and .write() * can run simultaneously. * * stream_open never fails and is marked to return int so that it could be * directly used as file_operations.open . */ int stream_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } EXPORT_SYMBOL(stream_open); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. */ static unsigned int d_hash_shift __read_mostly; static struct hlist_bl_head *dentry_hashtable __read_mostly; static inline struct hlist_bl_head *d_hash(unsigned int hash) { return dentry_hashtable + (hash >> d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } /* Statistics gathering. */ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } struct external_name { union { atomic_t count; struct rcu_head head; } u; unsigned char name[]; }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); name->name.name = name->inline_name; } spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(list_empty(&dentry->d_child))) return; __list_del_entry(&dentry->d_child); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_child.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_child.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_child.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_child.next != &parent->d_subdirs) { next = list_entry(dentry->d_child.next, struct dentry, d_child); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_child.next = next->d_child.next; } } static void __dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; if (!IS_ROOT(dentry)) parent = dentry->d_parent; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); dentry_unlist(dentry, parent); if (parent) spin_unlock(&parent->d_lock); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); spin_lock(&dentry->d_lock); if (dentry->d_flags & DCACHE_SHRINK_LIST) { dentry->d_flags |= DCACHE_MAY_FREE; can_free = false; } spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); cond_resched(); } static struct dentry *__lock_parent(struct dentry *dentry) { struct dentry *parent; rcu_read_lock(); spin_unlock(&dentry->d_lock); again: parent = READ_ONCE(dentry->d_parent); spin_lock(&parent->d_lock); /* * We can't blindly lock dentry until we are sure * that we won't violate the locking order. * Any changes of dentry->d_parent must have * been done with parent->d_lock held, so * spin_lock() above is enough of a barrier * for checking if it's still our child. */ if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); goto again; } rcu_read_unlock(); if (parent != dentry) spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); else parent = NULL; return parent; } static inline struct dentry *lock_parent(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; if (IS_ROOT(dentry)) return NULL; if (likely(spin_trylock(&parent->d_lock))) return parent; return __lock_parent(dentry); } static inline bool retain_dentry(struct dentry *dentry) { WARN_ON(d_in_lookup(dentry)); /* Unreachable? Get rid of it */ if (unlikely(d_unhashed(dentry))) return false; if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) return false; if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) return false; } if (unlikely(dentry->d_flags & DCACHE_DONTCACHE)) return false; /* retain; LRU fodder */ dentry->d_lockref.count--; if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) d_lru_add(dentry); else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED))) dentry->d_flags |= DCACHE_REFERENCED; return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Finish off a dentry we've decided to kill. * dentry->d_lock must be held, returns with it unlocked. * Returns dentry requiring refcount drop, or NULL if we're done. */ static struct dentry *dentry_kill(struct dentry *dentry) __releases(dentry->d_lock) { struct inode *inode = dentry->d_inode; struct dentry *parent = NULL; if (inode && unlikely(!spin_trylock(&inode->i_lock))) goto slow_positive; if (!IS_ROOT(dentry)) { parent = dentry->d_parent; if (unlikely(!spin_trylock(&parent->d_lock))) { parent = __lock_parent(dentry); if (likely(inode || !dentry->d_inode)) goto got_locks; /* negative that became positive */ if (parent) spin_unlock(&parent->d_lock); inode = dentry->d_inode; goto slow_positive; } } __dentry_kill(dentry); return parent; slow_positive: spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); parent = lock_parent(dentry); got_locks: if (unlikely(dentry->d_lockref.count != 1)) { dentry->d_lockref.count--; } else if (likely(!retain_dentry(dentry))) { __dentry_kill(dentry); return parent; } /* we are keeping it, after all */ if (inode) spin_unlock(&inode->i_lock); if (parent) spin_unlock(&parent->d_lock); spin_unlock(&dentry->d_lock); return NULL; } /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; unsigned int d_flags; /* * If we have a d_op->d_delete() operation, we sould not * let the dentry count go to zero, so use "put_or_lock". */ if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) return lockref_put_or_lock(&dentry->d_lockref); /* * .. otherwise, we can try to just decrement the * lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Careful, careful. The reference count went down * to zero, but we don't hold the dentry lock, so * somebody else could get it again, and do another * dput(), and we need to not race with that. * * However, there is a very special and common case * where we don't care, because there is nothing to * do: the dentry is still hashed, it does not have * a 'delete' op, and it's referenced and already on * the LRU list. * * NOTE! Since we aren't locked, these values are * not "stable". However, it is sufficient that at * some point after we dropped the reference the * dentry was hashed and the flags had the proper * value. Other dentry users may have re-gotten * a reference to the dentry and change that, but * our work is done - we can leave the dentry * around with a zero refcount. */ smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED; /* Nothing to do? Dropping the reference was all we needed? */ if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) return true; /* * Not the fast normal case? Get the lock. We've already decremented * the refcount, but we'll need to re-check the situation after * getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; } /* * Re-get the reference we optimistically dropped. We hold the * lock, and we just tested that it was zero, so we can just * set it to 1. */ dentry->d_lockref.count = 1; return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { while (dentry) { might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } /* Slow case: now with the dentry lock held */ rcu_read_unlock(); if (likely(retain_dentry(dentry))) { spin_unlock(&dentry->d_lock); return; } dentry = dentry_kill(dentry); } } EXPORT_SYMBOL(dput); static void __dput_to_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { /* let the owner of the list it's on deal with it */ --dentry->d_lockref.count; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!--dentry->d_lockref.count) d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); if (!retain_dentry(dentry)) __dput_to_list(dentry, list); spin_unlock(&dentry->d_lock); } /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; } static inline void __dget(struct dentry *dentry) { lockref_get(&dentry->d_lockref); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { __dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { struct dentry *dentry; restart: spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { struct dentry *parent = lock_parent(dentry); if (likely(!dentry->d_lockref.count)) { __dentry_kill(dentry); dput(parent); goto restart; } if (parent) spin_unlock(&parent->d_lock); } spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_prune_aliases); /* * Lock a dentry from shrink list. * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry has been disrupted or grabbed, leaving * the caller to kick it off-list. Otherwise, return true and have * that dentry's inode and parent both locked. */ static bool shrink_lock_dentry(struct dentry *dentry) { struct inode *inode; struct dentry *parent; if (dentry->d_lockref.count) return false; inode = dentry->d_inode; if (inode && unlikely(!spin_trylock(&inode->i_lock))) { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (unlikely(dentry->d_lockref.count)) goto out; /* changed inode means that somebody had grabbed it */ if (unlikely(inode != dentry->d_inode)) goto out; } parent = dentry->d_parent; if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock))) return true; spin_unlock(&dentry->d_lock); spin_lock(&parent->d_lock); if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); spin_lock(&dentry->d_lock); goto out; } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (likely(!dentry->d_lockref.count)) return true; spin_unlock(&parent->d_lock); out: if (inode) spin_unlock(&inode->i_lock); return false; } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry, *parent; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!shrink_lock_dentry(dentry)) { bool can_free = false; rcu_read_unlock(); d_shrink_del(dentry); if (dentry->d_lockref.count < 0) can_free = dentry->d_flags & DCACHE_MAY_FREE; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } rcu_read_unlock(); d_shrink_del(dentry); parent = dentry->d_parent; if (parent != dentry) __dput_to_list(parent, list); __dentry_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add and list_lru_del. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent; struct list_head *next; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: next = this_parent->d_subdirs.next; resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ do { next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_subdirs list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) { d_shrink_add(dentry, &data->dispose); data->found++; } } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { if (!dentry->d_lockref.count) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) d_shrink_add(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { struct dentry *parent; spin_lock(&data.victim->d_lock); if (!shrink_lock_dentry(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { rcu_read_unlock(); parent = data.victim->d_parent; if (parent != data.victim) __dput_to_list(parent, &data.dispose); __dentry_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!list_empty(&dentry->d_subdirs)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); WARN_ON(1); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { __dget_dlock(dentry); *victim = dentry; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->u.count, 1); dname = p->name; } else { dname = dentry->d_iname; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ __dget_dlock(parent); dentry->d_parent = parent; list_add(&dentry->d_child, &parent->d_subdirs); if (parent->d_flags & DCACHE_DISCONNECTED) dentry->d_flags |= DCACHE_DISCONNECTED; spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) dentry->d_flags |= DCACHE_NORCU; return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); /* * d_set_fallthru - Mark a dentry as falling through to a lower layer * @dentry - The dentry to mark * * Mark a dentry as falling through to the lower layer (as set with * d_pin_lower()). This flag may be recorded on the medium. */ void d_set_fallthru(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_FALLTHRU; spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_set_fallthru); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_instantiate_anon(struct dentry *dentry, struct inode *inode, bool disconnected) { struct dentry *res; unsigned add_flags; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); if (res) { spin_unlock(&inode->i_lock); dput(dentry); goto out_iput; } /* attach a disconnected dentry */ add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&dentry->d_lock); __d_set_inode_and_type(dentry, inode, add_flags); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&dentry->d_sb->s_roots); hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots); hlist_bl_unlock(&dentry->d_sb->s_roots); } spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); return dentry; out_iput: iput(inode); return res; } struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode) { return __d_instantiate_anon(dentry, inode, true); } EXPORT_SYMBOL(d_instantiate_anon); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct dentry *tmp; struct dentry *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); res = d_find_any_alias(inode); if (res) goto out_iput; tmp = d_alloc_anon(inode->i_sb); if (!tmp) { res = ERR_PTR(-ENOMEM); goto out_iput; } return __d_instantiate_anon(tmp, inode, disconnected); out_iput: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the the case-exact dentry * already exists in in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); static inline bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; seqretry: /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { int tlen; const char *tname; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; } else { if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; } *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned n) { smp_store_release(&dir->i_dir_seq, n + 2); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); void __d_lookup_done(struct dentry *dentry) { struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); wake_up_all(dentry->d_wait); dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); } EXPORT_SYMBOL(__d_lookup_done); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); __d_lookup_done(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); /** * d_exact_alias - find and hash an exact unhashed alias * @entry: dentry to add * @inode: The inode to go with this dentry * * If an unhashed dentry with the same name/parent and desired * inode already exists, hash and return it. Otherwise, return * NULL. * * Parent directory should be locked. */ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { spin_unlock(&alias->d_lock); alias = NULL; } else { __dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); return alias; } spin_unlock(&inode->i_lock); return NULL; } EXPORT_SYMBOL(d_exact_alias); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ memcpy(target->d_iname, dentry->d_name.name, dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; target->d_name.name = target->d_iname; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); target->d_name.name = dentry->d_name.name; dentry->d_name.name = dentry->d_iname; } else { /* * Both are internal. */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); } } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->u.count); dentry->d_name = target->d_name; } else { memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); dentry->d_name.name = dentry->d_iname; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) kfree_rcu(old_name, u.head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); __d_lookup_done(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); list_move(&target->d_child, &target->d_parent->d_subdirs); __d_rehash(target); fsnotify_update_flags(target); } list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(inode, dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } EXPORT_SYMBOL(d_genocide); void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __read_mostly; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLY__ /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ static __always_inline void rep_nop(void) { asm volatile("rep; nop" ::: "memory"); } static __always_inline void cpu_relax(void) { rep_nop(); } #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { INIT_LIST_HEAD(&file->f_ep_links); INIT_LIST_HEAD(&file->f_tfile_llink); } /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(list_empty(&file->f_ep_links))) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_init_file(struct file *file) {} static inline void eventpoll_release(struct file *file) {} #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/spinlock_types.h> struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts * @refs: atomic_t counter field * * The counter saturates at REFCOUNT_SATURATED and will not move once * there. This avoids wrapping the counter and causing 'spurious' * use-after-free bugs. */ typedef struct refcount_struct { atomic_t refs; } refcount_t; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old < 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/ima.h> #include <linux/swap.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; static void file_free_rcu(struct rcu_head *head) { struct file *f = container_of(head, struct file, f_u.fu_rcuhead); put_cred(f->f_cred); kmem_cache_free(filp_cachep, f); } static inline void file_free(struct file *f) { security_file_free(f); if (!(f->f_mode & FMODE_NOACCOUNT)) percpu_counter_dec(&nr_files); call_rcu(&f->f_u.fu_rcuhead, file_free_rcu); } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); /* * Handle nr_files sysctl */ #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } #endif static struct file *__alloc_file(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { file_free_rcu(&f->f_u.fu_rcuhead); return ERR_PTR(error); } atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); eventpoll_init_file(f); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ return f; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = __alloc_file(flags, cred); if (!IS_ERR(f)) percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * Should not be used unless there's a very good reason to do so. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f = __alloc_file(flags, cred); if (!IS_ERR(f)) f->f_mode |= FMODE_NOACCOUNT; return f; } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (IS_ERR(file)) return file; file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); return file; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct qstr this = QSTR_INIT(name, strlen(name)); struct path path; struct file *file; path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this); if (!path.dentry) return ERR_PTR(-ENOMEM); if (!mnt->mnt_sb->s_d_op) d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(mnt); d_instantiate(path.dentry, inode); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); } return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); ima_file_free(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); put_pid(file->f_owner.pid); if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); if (mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(mnt); } dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_u.fu_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_u.fu_rcuhead)); } /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); void fput_many(struct file *file, unsigned int refs) { if (atomic_long_sub_and_test(refs, &file->f_count)) { struct task_struct *task = current; if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_u.fu_rcuhead, ____fput); if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_u.fu_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } } void fput(struct file *file) { fput_many(file, 1); } /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; BUG_ON(!(task->flags & PF_KTHREAD)); __fput(file); } } EXPORT_SYMBOL(fput); EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { atomic_t count; struct ns_common ns; struct mount * root; /* * Traversal and modification of .list is protected by either * - taking namespace_sem for write, OR * - taking namespace_sem for read AND taking .ns_lock. */ struct list_head list; spinlock_t ns_lock; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); extern bool legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { atomic_inc(&ns->count); } extern seqlock_t mount_lock; static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); struct mount cursor; }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | #ifndef _LINUX_HASH_H #define _LINUX_HASH_H /* Fast hashing routine for ints, longs and pointers. (C) 2002 Nadia Yvette Chambers, IBM */ #include <asm/types.h> #include <linux/compiler.h> /* * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and * fs/inode.c. It's not actually prime any more (the previous primes * were actively bad for hashing), but the name remains. */ #if BITS_PER_LONG == 32 #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32 #define hash_long(val, bits) hash_32(val, bits) #elif BITS_PER_LONG == 64 #define hash_long(val, bits) hash_64(val, bits) #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64 #else #error Wordsize not 32 or 64 #endif /* * This hash multiplies the input by a large odd number and takes the * high bits. Since multiplication propagates changes to the most * significant end only, it is essential that the high bits of the * product be used for the hash value. * * Chuck Lever verified the effectiveness of this technique: * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf * * Although a random odd number will do, it turns out that the golden * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice * properties. (See Knuth vol 3, section 6.4, exercise 9.) * * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2, * which is very slightly easier to multiply by and makes no * difference to the hash distribution. */ #define GOLDEN_RATIO_32 0x61C88647 #define GOLDEN_RATIO_64 0x61C8864680B583EBull #ifdef CONFIG_HAVE_ARCH_HASH /* This header may use the GOLDEN_RATIO_xx constants */ #include <asm/hash.h> #endif /* * The _generic versions exist only so lib/test_hash.c can compare * the arch-optimized versions with the generic. * * Note that if you change these, any <asm/hash.h> that aren't updated * to match need to have their HAVE_ARCH_* define values updated so the * self-test will not false-positive. */ #ifndef HAVE_ARCH__HASH_32 #define __hash_32 __hash_32_generic #endif static inline u32 __hash_32_generic(u32 val) { return val * GOLDEN_RATIO_32; } #ifndef HAVE_ARCH_HASH_32 #define hash_32 hash_32_generic #endif static inline u32 hash_32_generic(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); } #ifndef HAVE_ARCH_HASH_64 #define hash_64 hash_64_generic #endif static __always_inline u32 hash_64_generic(u64 val, unsigned int bits) { #if BITS_PER_LONG == 64 /* 64x64-bit multiply is efficient on all 64-bit processors */ return val * GOLDEN_RATIO_64 >> (64 - bits); #else /* Hash 64 bits using only 32x32-bit multiply. */ return hash_32((u32)val ^ __hash_32(val >> 32), bits); #endif } static inline u32 hash_ptr(const void *ptr, unsigned int bits) { return hash_long((unsigned long)ptr, bits); } /* This really should be called fold32_ptr; it does no hashing to speak of. */ static inline u32 hash32_ptr(const void *ptr) { unsigned long val = (unsigned long)ptr; #if BITS_PER_LONG == 64 val ^= (val >> 32); #endif return (u32)val; } #endif /* _LINUX_HASH_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG #define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->close_on_exec); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) { fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); } return NULL; } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline struct file *lookup_fd_rcu(unsigned int fd) { return files_lookup_fd_rcu(current->files, fd); } struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd); struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd); struct task_struct; struct files_struct *get_files_struct(struct task_struct *); void put_files_struct(struct files_struct *fs); int unshare_files(void); struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern int close_fd_get_file(unsigned int fd, struct file **res); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMIOTRACE_H #define _LINUX_MMIOTRACE_H #include <linux/types.h> #include <linux/list.h> struct kmmio_probe; struct pt_regs; typedef void (*kmmio_pre_handler_t)(struct kmmio_probe *, struct pt_regs *, unsigned long addr); typedef void (*kmmio_post_handler_t)(struct kmmio_probe *, unsigned long condition, struct pt_regs *); struct kmmio_probe { /* kmmio internal list: */ struct list_head list; /* start location of the probe point: */ unsigned long addr; /* length of the probe region: */ unsigned long len; /* Called before addr is executed: */ kmmio_pre_handler_t pre_handler; /* Called after addr is executed: */ kmmio_post_handler_t post_handler; void *private; }; extern unsigned int kmmio_count; extern int register_kmmio_probe(struct kmmio_probe *p); extern void unregister_kmmio_probe(struct kmmio_probe *p); extern int kmmio_init(void); extern void kmmio_cleanup(void); #ifdef CONFIG_MMIOTRACE /* kmmio is active by some kmmio_probes? */ static inline int is_kmmio_active(void) { return kmmio_count; } /* Called from page fault handler. */ extern int kmmio_handler(struct pt_regs *regs, unsigned long addr); /* Called from ioremap.c */ extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size, void __iomem *addr); extern void mmiotrace_iounmap(volatile void __iomem *addr); /* For anyone to insert markers. Remember trailing newline. */ extern __printf(1, 2) int mmiotrace_printk(const char *fmt, ...); #else /* !CONFIG_MMIOTRACE: */ static inline int is_kmmio_active(void) { return 0; } static inline int kmmio_handler(struct pt_regs *regs, unsigned long addr) { return 0; } static inline void mmiotrace_ioremap(resource_size_t offset, unsigned long size, void __iomem *addr) { } static inline void mmiotrace_iounmap(volatile void __iomem *addr) { } static inline __printf(1, 2) int mmiotrace_printk(const char *fmt, ...) { return 0; } #endif /* CONFIG_MMIOTRACE */ enum mm_io_opcode { MMIO_READ = 0x1, /* struct mmiotrace_rw */ MMIO_WRITE = 0x2, /* struct mmiotrace_rw */ MMIO_PROBE = 0x3, /* struct mmiotrace_map */ MMIO_UNPROBE = 0x4, /* struct mmiotrace_map */ MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */ }; struct mmiotrace_rw { resource_size_t phys; /* PCI address of register */ unsigned long value; unsigned long pc; /* optional program counter */ int map_id; unsigned char opcode; /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */ unsigned char width; /* size of register access in bytes */ }; struct mmiotrace_map { resource_size_t phys; /* base address in PCI space */ unsigned long virt; /* base virtual address */ unsigned long len; /* mapping size */ int map_id; unsigned char opcode; /* MMIO_PROBE or MMIO_UNPROBE */ }; /* in kernel/trace/trace_mmiotrace.c */ extern void enable_mmiotrace(void); extern void disable_mmiotrace(void); extern void mmio_trace_rw(struct mmiotrace_rw *rw); extern void mmio_trace_mapping(struct mmiotrace_map *map); extern __printf(1, 0) int mmio_trace_printk(const char *fmt, va_list args); #endif /* _LINUX_MMIOTRACE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CLEANCACHE_H #define _LINUX_CLEANCACHE_H #include <linux/fs.h> #include <linux/exportfs.h> #include <linux/mm.h> #define CLEANCACHE_NO_POOL -1 #define CLEANCACHE_NO_BACKEND -2 #define CLEANCACHE_NO_BACKEND_SHARED -3 #define CLEANCACHE_KEY_MAX 6 /* * cleancache requires every file with a page in cleancache to have a * unique key unless/until the file is removed/truncated. For some * filesystems, the inode number is unique, but for "modern" filesystems * an exportable filehandle is required (see exportfs.h) */ struct cleancache_filekey { union { ino_t ino; __u32 fh[CLEANCACHE_KEY_MAX]; u32 key[CLEANCACHE_KEY_MAX]; } u; }; struct cleancache_ops { int (*init_fs)(size_t); int (*init_shared_fs)(uuid_t *uuid, size_t); int (*get_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*put_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); void (*invalidate_inode)(int, struct cleancache_filekey); void (*invalidate_fs)(int); }; extern int cleancache_register_ops(const struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(struct super_block *); extern int __cleancache_get_page(struct page *); extern void __cleancache_put_page(struct page *); extern void __cleancache_invalidate_page(struct address_space *, struct page *); extern void __cleancache_invalidate_inode(struct address_space *); extern void __cleancache_invalidate_fs(struct super_block *); #ifdef CONFIG_CLEANCACHE #define cleancache_enabled (1) static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) { return mapping->host->i_sb->cleancache_poolid >= 0; } static inline bool cleancache_fs_enabled(struct page *page) { return cleancache_fs_enabled_mapping(page->mapping); } #else #define cleancache_enabled (0) #define cleancache_fs_enabled(_page) (0) #define cleancache_fs_enabled_mapping(_page) (0) #endif /* * The shim layer provided by these inline functions allows the compiler * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE * is disabled, to a single global variable check if CONFIG_CLEANCACHE * is enabled but no cleancache "backend" has dynamically enabled it, * and, for the most frequent cleancache ops, to a single global variable * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled * and a cleancache backend has dynamically enabled cleancache, but the * filesystem referenced by that cleancache op has not enabled cleancache. * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially * no measurable performance impact. */ static inline void cleancache_init_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_init_fs(sb); } static inline void cleancache_init_shared_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_init_shared_fs(sb); } static inline int cleancache_get_page(struct page *page) { if (cleancache_enabled && cleancache_fs_enabled(page)) return __cleancache_get_page(page); return -1; } static inline void cleancache_put_page(struct page *page) { if (cleancache_enabled && cleancache_fs_enabled(page)) __cleancache_put_page(page); } static inline void cleancache_invalidate_page(struct address_space *mapping, struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) __cleancache_invalidate_page(mapping, page); } static inline void cleancache_invalidate_inode(struct address_space *mapping) { if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) __cleancache_invalidate_inode(mapping); } static inline void cleancache_invalidate_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_invalidate_fs(sb); } #endif /* _LINUX_CLEANCACHE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <linux/net.h> #include <linux/textsearch.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <net/flow_dissector.h> #include <linux/splice.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif /* The interface for checksum offload between the stack and networking drivers * is as follows... * * A. IP checksum related features * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * The checksum related features are: * * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * B. Checksumming of received packets by device. Indication of checksum * verification is set in skb->ip_summed. Possible values are: * * CHECKSUM_NONE: * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * CHECKSUM_UNNECESSARY: * * The hardware you're dealing with doesn't calculate the full checksum * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY * if their checksums are okay. skb->csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * CHECKSUM_UNNECESSARY is applicable to following protocols: * TCP: IPv6 and IPv4. * UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * GRE: only if the checksum is present in the header. * SCTP: indicates the CRC in SCTP header has been validated. * FCOE: indicates the CRC in FC frame has been validated. * * skb->csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, skb->csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * CHECKSUM_COMPLETE: * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in skb->csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * CHECKSUM_PARTIAL: * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * C. Checksumming on transmit for non-GSO. The stack requests checksum offload * in the skb->ip_summed for a packet. Values are: * * CHECKSUM_PARTIAL: * * The driver is required to checksum the packet as seen by hard_start_xmit() * from skb->csum_start up to the end, and to record/write the checksum at * offset skb->csum_start + skb->csum_offset. A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help or skb_crc32c_help (depending on the value of * csum_not_inet, see item D.) is called to resolve the checksum. * * CHECKSUM_NONE: * * The skb was already checksummed by the protocol, or a checksum is not * required. * * CHECKSUM_UNNECESSARY: * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * CHECKSUM_COMPLETE: * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if CHECKSUM_NONE were set. * * D. Non-IP checksum (CRC) offloads * * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of * offloading the FCOE CRC in a packet. To perform this offload the stack * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * E. Checksumming on output with GSO. * * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { __u32 chain; __u16 mru; }; #endif struct sk_buff_head { /* These two members must be first. */ struct sk_buff *next; struct sk_buff *prev; __u32 qlen; spinlock_t lock; }; struct sk_buff; /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. * * Since GRO uses frags we allocate at least 16 regardless of page * size. */ #if (65536/PAGE_SIZE + 1) < 16 #define MAX_SKB_FRAGS 16UL #else #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) #endif extern int sysctl_max_skb_frags; /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct bio_vec skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->bv_len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->bv_len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->bv_len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->bv_len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->bv_page * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ #define HAVE_HW_TIME_STAMP /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { ktime_t hwtstamp; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* device driver supports TX zero-copy buffers */ SKBTX_DEV_ZEROCOPY = 1 << 3, /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBTX_SHARED_FRAG = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; #define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; refcount_t refcnt; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); static inline void sock_zerocopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } void sock_zerocopy_put(struct ubuf_info *uarg); void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 __unused; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; struct skb_shared_hwtstamps hwtstamps; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /* We divide dataref into two halves. The higher 16 bits hold references * to the payload part of skb->data. The lower 16 bits hold references to * the entire skb->data. A clone of a headerless skb holds the length of * the header in skb->hdr_len. * * All users must obey the rule that the skb->data reference count must be * greater than or equal to the payload reference count. * * Holding a reference to the payload part means that the user does not * care about modifications to the header part of skb->data. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @sk: Socket we are owned by * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in * fragmentation management * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_present: VLAN tag is present * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1; #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ /* private: */ __u32 headers_start[0]; /* public: */ /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; __u8 ignore_df:1; __u8 nf_trace:1; __u8 ip_summed:2; __u8 ooo_okay:1; __u8 l4_hash:1; __u8 sw_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef __BIG_ENDIAN_BITFIELD #define PKT_VLAN_PRESENT_BIT 7 #else #define PKT_VLAN_PRESENT_BIT 0 #endif #define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) /* private: */ __u8 __pkt_vlan_present_offset[0]; /* public: */ __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif __u8 ipvs_property:1; __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; #endif #ifdef CONFIG_NET_REDIRECT __u8 redirected:1; __u8 from_ingress:1; #endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ #endif union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; __be16 vlan_proto; __u16 vlan_tci; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif /* private: */ __u32 headers_end[0]; /* public: */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only useable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /** * skb_rtable - Returns the skb &rtable * @skb: buffer */ static inline struct rtable *skb_rtable(const struct sk_buff *skb) { return (struct rtable *)skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } void skb_release_head_state(struct sk_buff *skb); void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that this didnt happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && fclones->skb2.sk == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } void __skb_get_hash(struct sk_buff *skb); u32 __skb_get_hash_symmetric(const struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, void *data, int hlen_proto); static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) { return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash(skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_TLS_DEVICE to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } #endif /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; return is_zcopy ? skb_uarg(skb) : NULL; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else sock_zerocopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (skb_zcopy_is_nouarg(skb)) { /* no notification callback */ } else if (uarg->callback == sock_zerocopy_callback) { uarg->zerocopy = uarg->zerocopy && zerocopy; sock_zerocopy_put(uarg); } else { uarg->callback(uarg, zerocopy); } skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } } /* Abort a zerocopy operation and revert zckey on error in send syscall */ static inline void skb_zcopy_abort(struct sk_buff *skb) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { sock_zerocopy_put_abort(uarg, false); skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release - release reference to header * @skb: buffer to operate on */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet thats being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); WRITE_ONCE(prev->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, prev->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, next->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; /* * Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ frag->bv_page = page; frag->bv_offset = off; skb_frag_size_set(frag, size); page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_page_desc(skb, i, page, off, size); skb_shinfo(skb)->nr_frags = i + 1; } void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; BUG_ON(skb->len < skb->data_len); return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) { if (len > skb_headlen(skb) && !__pskb_pull_tail(skb, len - skb_headlen(skb))) return NULL; skb->len -= len; return skb->data += len; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) return true; if (unlikely(len > skb->len)) return false; return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline void skb_reset_mac_len(struct sk_buff *skb) { skb->mac_len = skb->network_header - skb->mac_header; } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { skb->inner_transport_header = skb->data - skb->head; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { skb->inner_network_header = skb->data - skb->head; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { skb->inner_mac_header = skb->data - skb->head; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { skb->transport_header = skb->data - skb->head; } /** * skb_reset_transport_header_careful - conditionally reset transport header * @skb: buffer to alter * * Hardened version of skb_reset_transport_header(). * * Returns: true if the operation was a success. */ static inline bool __must_check skb_reset_transport_header_careful(struct sk_buff *skb) { long offset = skb->data - skb->head; if (unlikely(offset != (typeof(skb->transport_header))offset)) return false; if (unlikely(offset == (typeof(skb->transport_header))~0U)) return false; skb->transport_header = offset; return true; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { skb->network_header = skb->data - skb->head; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { return skb->network_header - skb->mac_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { skb->mac_header = skb->data - skb->head; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull(skb, skb_network_offset(skb) + len); } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (!skb_zcopy_is_nouarg(skb) && skb_uarg(skb)->callback == sock_zerocopy_callback) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge - empty a list * @list: list to empty * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb(skb); } void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); void *netdev_alloc_frag(unsigned int fragsz); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *napi_alloc_frag(unsigned int fragsz); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int length, gfp_t gfp_mask); static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length) { return __napi_alloc_skb(napi, length, GFP_ATOMIC); } void napi_consume_skb(struct sk_buff *skb, int budget); void __kfree_skb_flush(void); void __kfree_skb_defer(struct sk_buff *skb); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefor a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); } static inline struct page *dev_alloc_pages(unsigned int order) { return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order); } /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page(gfp_t gfp_mask) { return __dev_alloc_pages(gfp_mask, 0); } static inline struct page *dev_alloc_page(void) { return dev_alloc_pages(0); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->bv_offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->bv_offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->bv_offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->bv_offset = fragfrom->bv_offset; } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Returns the &struct page associated with @frag. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { return frag->bv_page; } /** * __skb_frag_ref - take an addition reference on a paged fragment. * @frag: the paged fragment * * Takes an additional reference on the paged fragment @frag. */ static inline void __skb_frag_ref(skb_frag_t *frag) { get_page(skb_frag_page(frag)); } /** * skb_frag_ref - take an addition reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset. * * Takes an additional reference on the @f'th paged fragment of @skb. */ static inline void skb_frag_ref(struct sk_buff *skb, int f) { __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment * * Releases a reference on the paged fragment @frag. */ static inline void __skb_frag_unref(skb_frag_t *frag) { put_page(skb_frag_page(frag)); } /** * skb_frag_unref - release a reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset * * Releases a reference on the @f'th paged fragment of @skb. */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { __skb_frag_unref(&skb_shinfo(skb)->frags[f]); } /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { struct page *page = skb_frag_page(frag); void *ptr; if (!page) return NULL; ptr = page_address(page); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->bv_page = fragfrom->bv_page; } /** * __skb_frag_set_page - sets the page contained in a paged fragment * @frag: the paged fragment * @page: the page to set * * Sets the fragment @frag to contain @page. */ static inline void __skb_frag_set_page(skb_frag_t *frag, struct page *page) { frag->bv_page = page; } /** * skb_frag_set_page - sets the page contained in a paged fragment of an skb * @skb: the buffer * @f: the fragment offset * @page: the page to set * * Sets the @f'th fragment of @skb to contain @page. */ static inline void skb_frag_set_page(struct sk_buff *skb, int f, struct page *page) { __skb_frag_set_page(&skb_shinfo(skb)->frags[f], page); } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, &csum, from)) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) return 0; __skb_trim(skb, off); return -EFAULT; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpull_rcsum(skb, start, len, 0); } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); static inline void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) { __skb_free_datagram_locked(sk, skb, 0); } int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *data, int hlen, void *buffer) { if (hlen - offset >= len) return data + offset; if (!skb || skb_copy_bits(skb, offset, buffer, len) < 0) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline ktime_t net_invalid_timestamp(void) { return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); /* Using more efficient varaiant than plain call to memcmp(). */ #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 diffs = 0; switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; } return diffs; #else return memcmp(a - meta_len, b - meta_len, meta_len); #endif } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } /* Keeps track of mac header offset relative to skb->head. * It is useful for TSO of Tunneling protocol. e.g. GRE. * For non-tunnel skb it points to skb_mac_header() and for * tunnel skb it points to outer mac header. * Keeps track of level of encapsulation of network headers. */ struct skb_gso_cb { union { int mac_offset; int data_offset; }; int encap_level; __wsum csum; __u16 csum_start; }; #define SKB_GSO_CB_OFFSET 32 #define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_GSO_CB_OFFSET)) static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) { return (skb_mac_header(inner_skb) - inner_skb->head) - SKB_GSO_CB(inner_skb)->mac_offset; } static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) { int new_headroom, headroom; int ret; headroom = skb_headroom(skb); ret = pskb_expand_head(skb, extra, 0, GFP_ATOMIC); if (ret) return ret; new_headroom = skb_headroom(skb); SKB_GSO_CB(skb)->mac_offset += (new_headroom - headroom); return 0; } static inline void gso_reset_checksum(struct sk_buff *skb, __wsum res) { /* Do not update partial checksums if remote checksum is enabled. */ if (skb->remcsum_offload) return; SKB_GSO_CB(skb)->csum = res; SKB_GSO_CB(skb)->csum_start = skb_checksum_start(skb) - skb->head; } /* Compute the checksum for a gso segment. First compute the checksum value * from the start of transport header to SKB_GSO_CB(skb)->csum_start, and * then add in skb->csum (checksum from csum_start to end of packet). * skb->csum and csum_start are then updated to reflect the checksum of the * resultant packet starting from the transport header-- the resultant checksum * is in the res argument (i.e. normally zero or ~ of checksum of a pseudo * header. */ static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) { unsigned char *csum_start = skb_transport_header(skb); int plen = (skb->head + SKB_GSO_CB(skb)->csum_start) - csum_start; __wsum partial = SKB_GSO_CB(skb)->csum; SKB_GSO_CB(skb)->csum = res; SKB_GSO_CB(skb)->csum_start = csum_start - skb->head; return csum_fold(csum_partial(csum_start, plen, partial)); } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { #ifdef DEBUG BUG_ON(skb->ip_summed != CHECKSUM_NONE); #endif } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { #ifdef CONFIG_NET_REDIRECT return skb->redirected; #else return false; #endif } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { #ifdef CONFIG_NET_REDIRECT skb->redirected = 1; skb->from_ingress = from_ingress; if (skb->from_ingress) skb->tstamp = 0; #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { #ifdef CONFIG_NET_REDIRECT skb->redirected = 0; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { return skb->csum_not_inet; } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. */ #include <linux/serial_8250.h> #include <linux/serial_reg.h> #include <linux/dmaengine.h> #include "../serial_mctrl_gpio.h" struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); /* Filter function */ dma_filter_fn fn; /* Parameter to the filter function */ void *rx_param; void *tx_param; struct dma_slave_config rxconf; struct dma_slave_config txconf; struct dma_chan *rxchan; struct dma_chan *txchan; /* Device address base for DMA operations */ phys_addr_t rx_dma_addr; phys_addr_t tx_dma_addr; /* DMA address of the buffer in memory */ dma_addr_t rx_addr; dma_addr_t tx_addr; dma_cookie_t rx_cookie; dma_cookie_t tx_cookie; void *rx_buf; size_t rx_size; size_t tx_size; unsigned char tx_running; unsigned char tx_err; unsigned char rx_running; }; struct old_serial_port { unsigned int uart; unsigned int baud_base; unsigned int port; unsigned int irq; upf_t flags; unsigned char io_type; unsigned char __iomem *iomem_base; unsigned short iomem_reg_shift; }; struct serial8250_config { const char *name; unsigned short fifo_size; unsigned short tx_loadsz; unsigned char fcr; unsigned char rxtrig_bytes[UART_FCR_R_TRIG_MAX_STATE]; unsigned int flags; }; #define UART_CAP_FIFO (1 << 8) /* UART has FIFO */ #define UART_CAP_EFR (1 << 9) /* UART has EFR */ #define UART_CAP_SLEEP (1 << 10) /* UART has IER sleep */ #define UART_CAP_AFE (1 << 11) /* MCR-based hw flow control */ #define UART_CAP_UUE (1 << 12) /* UART needs IER bit 6 set (Xscale) */ #define UART_CAP_RTOIE (1 << 13) /* UART needs IER bit 4 set (Xscale, Tegra) */ #define UART_CAP_HFIFO (1 << 14) /* UART has a "hidden" FIFO */ #define UART_CAP_RPM (1 << 15) /* Runtime PM is active while idle */ #define UART_CAP_IRDA (1 << 16) /* UART supports IrDA line discipline */ #define UART_CAP_MINI (1 << 17) /* Mini UART on BCM283X family lacks: * STOP PARITY EPAR SPAR WLEN5 WLEN6 */ #define UART_BUG_QUOT (1 << 0) /* UART has buggy quot LSB */ #define UART_BUG_TXEN (1 << 1) /* UART has buggy TX IIR status */ #define UART_BUG_NOMSR (1 << 2) /* UART has buggy MSR status bits (Au1x00) */ #define UART_BUG_THRE (1 << 3) /* UART has buggy THRE reassertion */ #define UART_BUG_TXRACE (1 << 5) /* UART Tx fails to set remote DR */ #ifdef CONFIG_SERIAL_8250_SHARE_IRQ #define SERIAL8250_SHARE_IRQS 1 #else #define SERIAL8250_SHARE_IRQS 0 #endif #define SERIAL8250_PORT_FLAGS(_base, _irq, _flags) \ { \ .iobase = _base, \ .irq = _irq, \ .uartclk = 1843200, \ .iotype = UPIO_PORT, \ .flags = UPF_BOOT_AUTOCONF | (_flags), \ } #define SERIAL8250_PORT(_base, _irq) SERIAL8250_PORT_FLAGS(_base, _irq, 0) static inline int serial_in(struct uart_8250_port *up, int offset) { return up->port.serial_in(&up->port, offset); } static inline void serial_out(struct uart_8250_port *up, int offset, int value) { up->port.serial_out(&up->port, offset, value); } /* * For the 16C950 */ static void serial_icr_write(struct uart_8250_port *up, int offset, int value) { serial_out(up, UART_SCR, offset); serial_out(up, UART_ICR, value); } static unsigned int __maybe_unused serial_icr_read(struct uart_8250_port *up, int offset) { unsigned int value; serial_icr_write(up, UART_ACR, up->acr | UART_ACR_ICRRD); serial_out(up, UART_SCR, offset); value = serial_in(up, UART_ICR); serial_icr_write(up, UART_ACR, up->acr); return value; } void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p); static inline int serial_dl_read(struct uart_8250_port *up) { return up->dl_read(up); } static inline void serial_dl_write(struct uart_8250_port *up, int value) { up->dl_write(up, value); } static inline bool serial8250_set_THRI(struct uart_8250_port *up) { if (up->ier & UART_IER_THRI) return false; up->ier |= UART_IER_THRI; serial_out(up, UART_IER, up->ier); return true; } static inline bool serial8250_clear_THRI(struct uart_8250_port *up) { if (!(up->ier & UART_IER_THRI)) return false; up->ier &= ~UART_IER_THRI; serial_out(up, UART_IER, up->ier); return true; } struct uart_8250_port *serial8250_get_port(int line); void serial8250_rpm_get(struct uart_8250_port *p); void serial8250_rpm_put(struct uart_8250_port *p); void serial8250_rpm_get_tx(struct uart_8250_port *p); void serial8250_rpm_put_tx(struct uart_8250_port *p); int serial8250_em485_config(struct uart_port *port, struct serial_rs485 *rs485); void serial8250_em485_start_tx(struct uart_8250_port *p); void serial8250_em485_stop_tx(struct uart_8250_port *p); void serial8250_em485_destroy(struct uart_8250_port *p); /* MCR <-> TIOCM conversion */ static inline int serial8250_TIOCM_to_MCR(int tiocm) { int mcr = 0; if (tiocm & TIOCM_RTS) mcr |= UART_MCR_RTS; if (tiocm & TIOCM_DTR) mcr |= UART_MCR_DTR; if (tiocm & TIOCM_OUT1) mcr |= UART_MCR_OUT1; if (tiocm & TIOCM_OUT2) mcr |= UART_MCR_OUT2; if (tiocm & TIOCM_LOOP) mcr |= UART_MCR_LOOP; return mcr; } static inline int serial8250_MCR_to_TIOCM(int mcr) { int tiocm = 0; if (mcr & UART_MCR_RTS) tiocm |= TIOCM_RTS; if (mcr & UART_MCR_DTR) tiocm |= TIOCM_DTR; if (mcr & UART_MCR_OUT1) tiocm |= TIOCM_OUT1; if (mcr & UART_MCR_OUT2) tiocm |= TIOCM_OUT2; if (mcr & UART_MCR_LOOP) tiocm |= TIOCM_LOOP; return tiocm; } /* MSR <-> TIOCM conversion */ static inline int serial8250_MSR_to_TIOCM(int msr) { int tiocm = 0; if (msr & UART_MSR_DCD) tiocm |= TIOCM_CAR; if (msr & UART_MSR_RI) tiocm |= TIOCM_RNG; if (msr & UART_MSR_DSR) tiocm |= TIOCM_DSR; if (msr & UART_MSR_CTS) tiocm |= TIOCM_CTS; return tiocm; } static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { serial_out(up, UART_MCR, value); if (up->gpios) mctrl_gpio_set(up->gpios, serial8250_MCR_to_TIOCM(value)); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { int mctrl; mctrl = serial_in(up, UART_MCR); if (up->gpios) { unsigned int mctrl_gpio = 0; mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); mctrl |= serial8250_TIOCM_to_MCR(mctrl_gpio); } return mctrl; } #if defined(__alpha__) && !defined(CONFIG_PCI) /* * Digital did something really horribly wrong with the OUT1 and OUT2 * lines on at least some ALPHA's. The failure mode is that if either * is cleared, the machine locks up with endless interrupts. */ #define ALPHA_KLUDGE_MCR (UART_MCR_OUT2 | UART_MCR_OUT1) #else #define ALPHA_KLUDGE_MCR 0 #endif #ifdef CONFIG_SERIAL_8250_PNP int serial8250_pnp_init(void); void serial8250_pnp_exit(void); #else static inline int serial8250_pnp_init(void) { return 0; } static inline void serial8250_pnp_exit(void) { } #endif #ifdef CONFIG_SERIAL_8250_FINTEK int fintek_8250_probe(struct uart_8250_port *uart); #else static inline int fintek_8250_probe(struct uart_8250_port *uart) { return 0; } #endif #ifdef CONFIG_ARCH_OMAP1 static inline int is_omap1_8250(struct uart_8250_port *pt) { int res; switch (pt->port.mapbase) { case OMAP1_UART1_BASE: case OMAP1_UART2_BASE: case OMAP1_UART3_BASE: res = 1; break; default: res = 0; break; } return res; } static inline int is_omap1510_8250(struct uart_8250_port *pt) { if (!cpu_is_omap1510()) return 0; return is_omap1_8250(pt); } #else static inline int is_omap1_8250(struct uart_8250_port *pt) { return 0; } static inline int is_omap1510_8250(struct uart_8250_port *pt) { return 0; } #endif #ifdef CONFIG_SERIAL_8250_DMA extern int serial8250_tx_dma(struct uart_8250_port *); extern void serial8250_tx_dma_flush(struct uart_8250_port *); extern int serial8250_rx_dma(struct uart_8250_port *); extern void serial8250_rx_dma_flush(struct uart_8250_port *); extern int serial8250_request_dma(struct uart_8250_port *); extern void serial8250_release_dma(struct uart_8250_port *); static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; return dma && dma->tx_running; } #else static inline int serial8250_tx_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_tx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_rx_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_rx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_request_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_release_dma(struct uart_8250_port *p) { } static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) { return false; } #endif static inline int ns16550a_goto_highspeed(struct uart_8250_port *up) { unsigned char status; status = serial_in(up, 0x04); /* EXCR2 */ #define PRESL(x) ((x) & 0x30) if (PRESL(status) == 0x10) { /* already in high speed mode */ return 0; } else { status &= ~0xB0; /* Disable LOCK, mask out PRESL[01] */ status |= 0x10; /* 1.625 divisor for baud_base --> 921600 */ serial_out(up, 0x04, status); } return 1; } static inline int serial_index(struct uart_port *port) { return port->minor - 64; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } /** * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list * @inode: inode to be removed * @wb: bdi_writeback @inode is being removed from * * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and * clear %WB_has_dirty_io if all are empty afterwards. */ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_bh(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(wb, work); spin_unlock_bh(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (page) { memcg_css = mem_cgroup_css_from_page(page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct inode *inode; struct bdi_writeback *new_wb; struct rcu_head rcu_head; struct work_struct work; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING is visible under i_lock, the eviction path owns * the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & I_FREEING)) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to * pages actually under writeback. */ xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } xas_set(&xas, 0); xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); inc_wb_stat(new_wb, WB_WRITEBACK); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. The specific list * @inode was on is ignored and the inode is put on ->b_dirty which * is always correct including from ->b_dirty_time. The transfer * preserves @inode->dirtied_when ordering. */ if (!list_empty(&inode->i_io_list)) { struct inode *pos; inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (switched) { wb_wakeup(new_wb); wb_put(old_wb); } wb_put(new_wb); iput(inode); kfree(isw); atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) { struct inode_switch_wbs_context *isw = container_of(rcu_head, struct inode_switch_wbs_context, rcu_head); /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); queue_work(isw_wq, &isw->work); } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); goto out_free; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); isw->inode = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out * * @bytes from @page are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested * @inode: inode to test for congestion (may be NULL) * @cong_bits: mask of WB_[a]sync_congested bits to test * * Tests whether @inode is congested. @cong_bits is the mask of congestion * bits to test and the return value is the mask of set bits. * * If cgroup writeback is enabled for @inode, the congestion state is * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg * associated with @inode is congested; otherwise, the root wb's congestion * state is used. * * @inode is allowed to be NULL as this function is often called on * mapping->host which is NULL for the swapper space. */ int inode_congested(struct inode *inode, int cong_bits) { /* * Once set, ->i_wb never becomes NULL while the inode is alive. * Start transaction iff ->i_wb is visible. */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; struct wb_lock_cookie lock_cookie = {}; bool congested; wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } EXPORT_SYMBOL_GPL(inode_congested); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * If @nr is zero, the caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. */ if (!nr) { unsigned long filepages, headroom, dirty, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, &writeback); nr = dirty * 10 / 8; } /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = nr; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } #define EXPIRE_DIRTY_ATIME 0x0001 /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ static void __inode_wait_for_writeback(struct inode *inode) __releases(inode->i_lock) __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } /* * Wait for writeback on an inode to complete. Caller must have inode pinned. */ void inode_wait_for_writeback(struct inode *inode) { spin_lock(&inode->i_lock); __inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { DEFINE_WAIT(wait); wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); int sleep; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); sleep = inode->i_state & I_SYNC; spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wqh, &wait); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * writeback is not making progress due to locked * buffers. Skip this inode for now. */ redirty_tail_locked(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); } } /* * Write out an inode and its dirty pages. Do not update the writeback list * linkage. That is left to the caller. The caller is also responsible for * setting I_SYNC flag and calling inode_sync_complete() to clear it. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Some filesystems may redirty the inode during the writeback * due to delalloc, clear dirty metadata flags right before * write_inode() */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty pages. Either the caller has an active reference * on the inode or the inode has I_WILL_FREE set. * * This function is designed to be called for writing back one inode which * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() * and does more profound writeback list handling in writeback_sb_inodes(). */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { if (wbc->sync_mode != WB_SYNC_ALL) goto out; /* * It's a data-integrity sync. We must wait. Since callers hold * inode reference or inode has I_WILL_FREE set, it cannot go * away under us. */ __inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * Skip inode if it is clean and we have no outstanding writeback in * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this * function since flusher thread may be doing for example sync in * parallel and if we move the inode, it could get skipped. So here we * make sure inode is on some writeback list and leave it there unless * we have completely cleaned the inode. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If inode is clean, remove it from writeback lists. Otherwise don't * touch it. See comment above for explanation. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_io_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ spin_unlock(&inode->i_lock); requeue_io(inode, wb); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!trylock_super(sb)) { /* * trylock_super() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; /* * Kupdate and background works are special and we want to * include all inodes that need writing. Livelock avoidance is * handled by these works yielding to any other work so we are * safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); wb_update_bandwidth(wb, wb_start); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress) continue; /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) break; /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); spin_lock(&wb->list_lock); } spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_bh(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_bh(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(wb, work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } /* * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, * write back the whole world. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) blk_schedule_flush_plug(current); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); if (dirtytime_expire_interval) schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { if (dirtytime_expire_interval) schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) { if (dirtytime_expire_interval) mod_delayed_work(system_wq, &dirtytime_work, 0); else cancel_delayed_work_sync(&dirtytime_work); } return ret; } /** * __mark_inode_dirty - internal function * * @inode: inode to mark * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) * * Mark an inode as dirty. Callers should use mark_inode_dirty or * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * * CAREFUL! We mark it dirty unconditionally, but move it onto the * dirty list only if it is hashed or if it refers to a blockdev. * If it was not hashed, it will never be added to the dirty list * even if it is later hashed, as it will have been marked dirty already. * * In short, make sure you hash any inodes _before_ you start marking * them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime; trace_writeback_mark_inode_dirty(inode, flags); /* * Don't do this for I_DIRTY_PAGES - that doesn't actually * dirty the inode itself */ if (flags & (I_DIRTY_INODE | I_DIRTY_TIME)) { trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags); trace_writeback_dirty_inode(inode, flags); } if (flags & I_DIRTY_INODE) flags &= ~I_DIRTY_TIME; dirtytime = flags & I_DIRTY_TIME; /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if (((inode->i_state & flags) == flags) || (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); if (flags & I_DIRTY_INODE) inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock_inode; } if (inode->i_state & I_FREEING) goto out_unlock_inode; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct bdi_writeback *wb; struct list_head *dirty_list; bool wakeup_bdi = false; wb = locked_inode_to_wb_and_lock_list(inode); WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) && !test_bit(WB_registered, &wb->state), "bdi-%s not registered\n", bdi_dev_name(wb->bdi)); inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); spin_unlock(&wb->list_lock); trace_writeback_dirty_inode_enqueue(inode); return; } } out_unlock_inode: spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode - write an inode and its pages to disk. * @inode: the inode to sync * @wbc: controls the writeback mode * * sync_inode() will write an inode and its pages to disk. It will also * correctly update the inode on its superblock's dirty inode lists and will * update inode->i_state. * * The caller must have a ref on the inode. */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { return writeback_single_inode(inode, wbc); } EXPORT_SYMBOL(sync_inode); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return sync_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; }; enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_VM_WRITEBACK_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_DEBUG_VM_VMACACHE #define count_vm_vmacache_event(x) count_vm_event(x) #else #define count_vm_vmacache_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_state_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_stat[item]); atomic_long_add(x, &vm_numa_stat[item]); } static inline unsigned long global_numa_state(enum numa_stat_item item) { long x = atomic_long_read(&vm_numa_stat[item]); return x; } static inline unsigned long zone_numa_state_snapshot(struct zone *zone, enum numa_stat_item item) { long x = atomic_long_read(&zone->vm_numa_stat[item]); int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; return x; } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #endif /* _LINUX_VMSTAT_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old, prev = old; \ CODE \ old.lock_count = cmpxchg64_relaxed(&lockref->lock_count, \ old.lock_count, \ new.lock_count); \ if (likely(old.lock_count == prev.lock_count)) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ int lockref_get_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_not_zero - Decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count would become zero */ int lockref_put_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count--; if (old.count <= 1) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 1) { lockref->count--; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_put_not_zero); /** * lockref_get_or_lock - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero * and we got the lock instead. */ int lockref_get_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; if (old.count <= 0) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 0) return 0; lockref->count++; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_get_or_lock); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return an error. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ int lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return 0; lockref->count--; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ int lockref_get_not_dead(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count < 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count >= 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | // SPDX-License-Identifier: GPL-2.0-only /* * Lock-less NULL terminated single linked list * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/llist.h> /** * llist_add_batch - add several linked entries in batch * @new_first: first entry in batch to be added * @new_last: last entry in batch to be added * @head: the head for your lock-less list * * Return whether list is empty before adding. */ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head) { struct llist_node *first; do { new_last->next = first = READ_ONCE(head->first); } while (cmpxchg(&head->first, first, new_first) != first); return !first; } EXPORT_SYMBOL_GPL(llist_add_batch); /** * llist_del_first - delete the first entry of lock-less list * @head: the head for your lock-less list * * If list is empty, return NULL, otherwise, return the first entry * deleted, this is the newest added one. * * Only one llist_del_first user can be used simultaneously with * multiple llist_add users without lock. Because otherwise * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, * llist_add) sequence in another user may change @head->first->next, * but keep @head->first. If multiple consumers are needed, please * use llist_del_all or use lock between consumers. */ struct llist_node *llist_del_first(struct llist_head *head) { struct llist_node *entry, *old_entry, *next; entry = smp_load_acquire(&head->first); for (;;) { if (entry == NULL) return NULL; old_entry = entry; next = READ_ONCE(entry->next); entry = cmpxchg(&head->first, old_entry, next); if (entry == old_entry) break; } return entry; } EXPORT_SYMBOL_GPL(llist_del_first); /** * llist_reverse_order - reverse order of a llist chain * @head: first item of the list to be reversed * * Reverse the order of a chain of llist entries and return the * new first entry. */ struct llist_node *llist_reverse_order(struct llist_node *head) { struct llist_node *new_head = NULL; while (head) { struct llist_node *tmp = head; head = head->next; tmp->next = new_head; new_head = tmp; } return new_head; } EXPORT_SYMBOL_GPL(llist_reverse_order); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/mmdebug.h> #include <linux/mmzone.h> #include <linux/stddef.h> #include <linux/linkage.h> #include <linux/topology.h> struct vm_area_struct; /* * In case of changes, please don't forget to update * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c */ /* Plain integer GFP bitmasks. Do not use this directly. */ #define ___GFP_DMA 0x01u #define ___GFP_HIGHMEM 0x02u #define ___GFP_DMA32 0x04u #define ___GFP_MOVABLE 0x08u #define ___GFP_RECLAIMABLE 0x10u #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u #define ___GFP_ZERO 0x100u #define ___GFP_ATOMIC 0x200u #define ___GFP_DIRECT_RECLAIM 0x400u #define ___GFP_KSWAPD_RECLAIM 0x800u #define ___GFP_WRITE 0x1000u #define ___GFP_NOWARN 0x2000u #define ___GFP_RETRY_MAYFAIL 0x4000u #define ___GFP_NOFAIL 0x8000u #define ___GFP_NORETRY 0x10000u #define ___GFP_MEMALLOC 0x20000u #define ___GFP_COMP 0x40000u #define ___GFP_NOMEMALLOC 0x80000u #define ___GFP_HARDWALL 0x100000u #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #ifdef CONFIG_LOCKDEP #define ___GFP_NOLOCKDEP 0x800000u #else #define ___GFP_NOLOCKDEP 0 #endif /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) * * Do not put any conditional on these. If necessary modify the definitions * without the underscores and use them consistently. The definitions here may * be used in bit comparisons. */ #define __GFP_DMA ((__force gfp_t)___GFP_DMA) #define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) #define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) /** * DOC: Page mobility and placement hints * * Page mobility and placement hints * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due * to external fragmentation. * * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be * moved by page migration during memory compaction or can be reclaimed. * * %__GFP_RECLAIMABLE is used for slab allocations that specify * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. * * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, * these pages will be spread between local zones to avoid all the dirty * pages being in one zone (fair zone allocation policy). * * %__GFP_HARDWALL enforces the cpuset memory allocation policy. * * %__GFP_THISNODE forces the allocation to be satisfied from the requested * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) /** * DOC: Watermark modifiers * * Watermark modifiers -- controls access to emergency reserves * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. * For example, creating an IO context to clean pages. * * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is * high priority. Users are typically interrupt handlers. This may be * used in conjunction with %__GFP_HIGH * * %__GFP_MEMALLOC allows access to all memory. This should only be used when * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). * Users of this flag have to be extremely careful to not deplete the reserve * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. * Usage of a pre-allocated pool (e.g. mempool) should be always considered * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. */ #define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /** * DOC: Reclaim modifiers * * Reclaim modifiers * ~~~~~~~~~~~~~~~~~ * Please note that all the following flags are only applicable to sleepable * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). * * %__GFP_IO can start physical IO. * * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the * allocator recursing into the filesystem which might already be holding * locks. * * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. * This flag can be cleared to avoid unnecessary delays when a fallback * option is available. * * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when * the low watermark is reached and have it reclaim pages until the high * watermark is reached. A caller may wish to clear this flag when fallback * options are available and the reclaim is likely to disrupt the system. The * canonical example is THP allocation where a fallback is cheap but * reclaim/compaction may cause indirect stalls. * * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * * The default allocator behavior depends on the request size. We have a concept * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). * !costly allocations are too essential to fail so they are implicitly * non-failing by default (with some exceptions like OOM victims might fail so * the caller still has to check for failures) while costly requests try to be * not disruptive and back off even without invoking the OOM killer. * The following three modifiers might be used to override some of these * implicit rules * * %__GFP_NORETRY: The VM implementation will try only very lightweight * memory direct reclaim to get some memory under memory pressure (thus * it can sleep). It will avoid disruptive actions like OOM killer. The * caller must handle the failure which is quite likely to happen under * heavy memory pressure. The flag is suitable when failure can easily be * handled at small cost, such as reduced throughput * * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim * procedures that have previously failed if there is some indication * that progress has been made else where. It can wait for other * tasks to attempt high level approaches to freeing memory such as * compaction (which removes fragmentation) and page-out. * There is still a definite limit to the number of retries, but it is * a larger limit than with %__GFP_NORETRY. * Allocations with this flag may fail, but only when there is * genuinely little unused memory. While these allocations do not * directly trigger the OOM killer, their failure indicates that * the system is likely to need to use the OOM killer soon. The * caller must handle failure, but can reasonably do so by failing * a higher-level request, or completing it only in a much less * efficient manner. * If the allocation does fail, and the caller is in a position to * free some non-essential memory, doing so could benefit the system * as a whole. * * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller * cannot handle allocation failures. The allocation could block * indefinitely but will never return with failure. Testing for * failure is pointless. * New users should be evaluated carefully (and the flag should be * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless * loop around allocator. * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) #define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /** * DOC: Action modifiers * * Action modifiers * ~~~~~~~~~~~~~~~~ * * %__GFP_NOWARN suppresses allocation failure reports. * * %__GFP_COMP address compound page metadata. * * %__GFP_ZERO returns a zeroed page on success. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ #define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** * DOC: Useful GFP flag combinations * * Useful GFP flag combinations * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear * %__GFP_FOO flags as necessary. * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower * watermark is applied to allow access to "atomic reserves". * The current implementation doesn't support NMI and few other strict * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. * * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is * accounted to kmemcg. * * %GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. * Please try to avoid using this flag directly and instead use * memalloc_noio_{save,restore} to mark the whole scope which cannot * perform any IO with a short explanation why. All allocation requests * will inherit GFP_NOIO implicitly. * * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. * Please try to avoid using this flag directly and instead use * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't * recurse into the FS layer with a short explanation why. All allocation * requests will inherit GFP_NOFS implicitly. * * %GFP_USER is for userspace allocations that also need to be directly * accessibly by the kernel or hardware. It is typically used by hardware * for buffers that are mapped to userspace (e.g. graphics) that hardware * still must DMA to. cpuset limits are enforced for these allocations. * * %GFP_DMA exists for historical reasons and should be avoided where possible. * The flags indicates that the caller requires that the lowest zone be * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but * it would require careful auditing as some users really require it and * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit * address. * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot * move once in use. An example may be a hardware allocation that maps * data directly into userspace but has no addressing limitations. * * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not * need direct access to but can use kmap() when access is required. They * are expected to be movable via page reclaim or page migration. Typically, * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. * * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They * are compound allocations that will generally fail quickly if memory is not * available and will not wake kswapd/kcompactd on failure. The _LIGHT * version does not attempt reclaim/compaction at all and is by default used * in page fault path, while the non-light is used by khugepaged. */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } /** * gfpflags_normal_context - is gfp_flags a normal sleepable context? * @gfp_flags: gfp_flags to test * * Test whether @gfp_flags indicates that the allocation is from the * %current context and allowed to sleep. * * An allocation being allowed to block doesn't mean it owns the %current * context. When direct reclaim path tries to allocate memory, the * allocation context is nested inside whatever %current was doing at the * time of the original allocation. The nested allocation may be allowed * to block but modifying anything %current owns can corrupt the outer * context's expectations. * * %true result from this function indicates that the allocation context * can sleep and use anything that's associated with %current. */ static inline bool gfpflags_normal_context(const gfp_t gfp_flags) { return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == __GFP_DIRECT_RECLAIM; } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets * optimized to &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { return 0; } #endif struct page * __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, nodemask_t *nodemask); static inline struct page * __alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) { return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); return __alloc_pages(gfp_mask, order, nid); } /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node(nid, gfp_mask, order); } #ifdef CONFIG_NUMA extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); static inline struct page * alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_current(gfp_mask, order); } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); extern void free_unref_page(struct page *page); extern void free_unref_page_list(struct list_head *list); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); extern void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask); extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else static inline bool pm_suspended_storage(void) { return false; } #endif /* CONFIG_PM_SLEEP */ /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif void free_contig_range(unsigned long pfn, unsigned int nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ extern void init_cma_reserved_pageblock(struct page *page); #endif #endif /* __LINUX_GFP_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGEMAP_H #define _LINUX_PAGEMAP_H /* * Copyright 1995 Linus Torvalds */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/gfp.h> #include <linux/bitops.h> #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> struct pagevec; /* * Bits in mapping->flags. */ enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_THP_SUPPORT = 6, /* THPs supported */ }; /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set * @error: the error to set in the mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */ static inline void mapping_set_error(struct address_space *mapping, int error) { if (likely(!error)) return; /* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error); /* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_clear_unevictable(struct address_space *mapping) { clear_bit(AS_UNEVICTABLE, &mapping->flags); } static inline bool mapping_unevictable(struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_set_exiting(struct address_space *mapping) { set_bit(AS_EXITING, &mapping->flags); } static inline int mapping_exiting(struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } static inline void mapping_set_no_writeback_tags(struct address_space *mapping) { set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline int mapping_use_writeback_tags(struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { m->gfp_mask = mask; } static inline bool mapping_thp_support(struct address_space *mapping) { return test_bit(AS_THP_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); #else return 0; #endif } static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_thp_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(1); #endif } static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_thp_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(1); #endif } void release_pages(struct page **pages, int nr); /* * speculatively take a reference to a page. * If the page is free (_refcount == 0), then _refcount is untouched, and 0 * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned. * * This function must be called inside the same rcu_read_lock() section as has * been used to lookup the page in the pagecache radix-tree (or page table): * this allows allocators to use a synchronize_rcu() to stabilize _refcount. * * Unless an RCU grace period has passed, the count of all pages coming out * of the allocator must be considered unstable. page_count may return higher * than expected, and put_page must be able to do the right thing when the * page has been finished with, no matter what it is subsequently allocated * for (because put_page is what is used here to drop an invalid speculative * reference). * * This is the interesting part of the lockless pagecache (and lockless * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) * has the following pattern: * 1. find page in radix tree * 2. conditionally increment refcount * 3. check the page is still in pagecache (if no, goto 1) * * Remove-side that cares about stability of _refcount (eg. reclaim) has the * following (with the i_pages lock held): * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) * B. remove page from pagecache * C. free the page * * There are 2 critical interleavings that matter: * - 2 runs before A: in this case, A sees elevated refcount and bails out * - A runs before 2: in this case, 2 sees zero refcount and retries; * subsequently, B will complete and 1 will find no page, causing the * lookup to return NULL. * * It is possible that between 1 and 2, the page is removed then the exact same * page is inserted into the same position in pagecache. That's OK: the * old find_get_page using a lock could equally have run before or after * such a re-insertion, depending on order that locks are granted. * * Lookups racing against pagecache insertion isn't a big problem: either 1 * will find the page or it will not. Likewise, the old find_get_page could run * either before the insertion or afterwards, depending on timing. */ static inline int __page_cache_add_speculative(struct page *page, int count) { #ifdef CONFIG_TINY_RCU # ifdef CONFIG_PREEMPT_COUNT VM_BUG_ON(!in_atomic() && !irqs_disabled()); # endif /* * Preempt must be disabled here - we rely on rcu_read_lock doing * this for us. * * Pagecache won't be truncated from interrupt context, so if we have * found a page in the radix tree here, we have pinned its refcount by * disabling preempt, and hence no need for the "speculative get" that * SMP requires. */ VM_BUG_ON_PAGE(page_count(page) == 0, page); page_ref_add(page, count); #else if (unlikely(!page_ref_add_unless(page, count, 0))) { /* * Either the page has been freed, or will be freed. * In either case, retry here and the caller should * do the right thing (see comments above). */ return 0; } #endif VM_BUG_ON_PAGE(PageTail(page), page); return 1; } static inline int page_cache_get_speculative(struct page *page) { return __page_cache_add_speculative(page, 1); } static inline int page_cache_add_speculative(struct page *page, int count) { return __page_cache_add_speculative(page, count); } /** * attach_page_private - Attach private data to a page. * @page: Page to attach data to. * @data: Data to attach to page. * * Attaching private data to a page increments the page's reference count. * The data must be detached before the page will be freed. */ static inline void attach_page_private(struct page *page, void *data) { get_page(page); set_page_private(page, (unsigned long)data); SetPagePrivate(page); } /** * detach_page_private - Detach private data from a page. * @page: Page to detach data from. * * Removes the data that was previously attached to the page and decrements * the refcount on the page. * * Return: Data that was attached to the page. */ static inline void *detach_page_private(struct page *page) { void *data = (void *)page_private(page); if (!PagePrivate(page)) return NULL; ClearPagePrivate(page); set_page_private(page, 0); put_page(page); return data; } #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else static inline struct page *__page_cache_alloc(gfp_t gfp) { return alloc_pages(gfp, 0); } #endif static inline struct page *page_cache_alloc(struct address_space *x) { return __page_cache_alloc(mapping_gfp_mask(x)); } static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(void *, struct page *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); #define FGP_ACCESSED 0x00000001 #define FGP_LOCK 0x00000002 #define FGP_CREAT 0x00000004 #define FGP_WRITE 0x00000008 #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */ static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, int fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */ static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK, 0); } /** * find_lock_head - Locate, pin and lock a pagecache page. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, its head page is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page which is !PageTail, or %NULL if there is no page * in the cache for this index. */ static inline struct page *find_lock_head(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0); } /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */ static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask); } /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Same as grab_cache_page(), but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); } /* Does this page contain this index? */ static inline bool thp_contains(struct page *head, pgoff_t index) { /* HugeTLBfs indexes the page cache in units of hpage_size */ if (PageHuge(head)) return head->index == index; return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); } /* * Given the page we found in the page cache, return the page corresponding * to this index in the file */ static inline struct page *find_subpage(struct page *head, pgoff_t index) { /* HugeTLBfs wants the head page regardless */ if (PageHuge(head)) return head; return head + (index & (thp_nr_pages(head) - 1)); } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages(struct address_space *mapping, pgoff_t *start, unsigned int nr_pages, struct page **pages) { return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, pages); } unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, nr_pages, pages); } struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags); /* * Returns locked page at given index in given cache, creating it if needed. */ static inline struct page *grab_cache_page(struct address_space *mapping, pgoff_t index) { return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { return read_cache_page(mapping, index, NULL, data); } /* * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_index(struct page *page) { pgoff_t pgoff; if (likely(!PageTransTail(page))) return page->index; /* * We don't initialize ->index for tail pages: calculate based on * head page */ pgoff = compound_head(page)->index; pgoff += page - compound_head(page); return pgoff; } extern pgoff_t hugetlb_basepage_index(struct page *page); /* * Get the offset in PAGE_SIZE (even for hugetlb pages). * (TODO: hugetlb pages should have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_pgoff(struct page *page) { if (unlikely(PageHuge(page))) return hugetlb_basepage_index(page); return page_to_index(page); } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { return ((loff_t)page->index) << PAGE_SHIFT; } static inline loff_t page_file_offset(struct page *page) { return ((loff_t)page_index(page)) << PAGE_SHIFT; } extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { pgoff_t pgoff; if (unlikely(is_vm_hugetlb_page(vma))) return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; } struct wait_page_key { struct page *page; int bit_nr; int page_match; }; struct wait_page_queue { struct page *page; int bit_nr; wait_queue_entry_t wait; }; static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { if (wait_page->page != key->page) return false; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return false; return true; } extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); /* * Return true if the page was successfully locked */ static inline int trylock_page(struct page *page) { page = compound_head(page); return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); } /* * lock_page may only be called if we have the page's inode pinned. */ static inline void lock_page(struct page *page) { might_sleep(); if (!trylock_page(page)) __lock_page(page); } /* * lock_page_killable is like lock_page but can be interrupted by fatal * signals. It returns 0 if it locked the page and -EINTR if it was * killed while waiting. */ static inline int lock_page_killable(struct page *page) { might_sleep(); if (!trylock_page(page)) return __lock_page_killable(page); return 0; } /* * lock_page_async - Lock the page, unless this would block. If the page * is already locked, then queue a callback when the page becomes unlocked. * This callback can then retry the operation. * * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page * was already locked and the callback defined in 'wait' was queued. */ static inline int lock_page_async(struct page *page, struct wait_page_queue *wait) { if (!trylock_page(page)) return __lock_page_async(page, wait); return 0; } /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __lock_page_or_retry(). */ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { might_sleep(); return trylock_page(page) || __lock_page_or_retry(page, mm, flags); } /* * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc., * and should not be used directly. */ extern void wait_on_page_bit(struct page *page, int bit_nr); extern int wait_on_page_bit_killable(struct page *page, int bit_nr); /* * Wait for a page to be unlocked. * * This must be called with the caller "holding" the page, * ie with increased "page->count" so that the page won't * go away during the wait.. */ static inline void wait_on_page_locked(struct page *page) { if (PageLocked(page)) wait_on_page_bit(compound_head(page), PG_locked); } static inline int wait_on_page_locked_killable(struct page *page) { if (!PageLocked(page)) return 0; return wait_on_page_bit_killable(compound_head(page), PG_locked); } extern void put_and_wait_on_page_locked(struct page *page); void wait_on_page_writeback(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue */ extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. */ static inline int fault_in_pages_writeable(char __user *uaddr, int size) { char __user *end = uaddr + size - 1; if (unlikely(size == 0)) return 0; if (unlikely(uaddr > end)) return -EFAULT; /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. */ do { if (unlikely(__put_user(0, uaddr) != 0)) return -EFAULT; uaddr += PAGE_SIZE; } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) return __put_user(0, end); return 0; } static inline int fault_in_pages_readable(const char __user *uaddr, int size) { volatile char c; const char __user *end = uaddr + size - 1; if (unlikely(size == 0)) return 0; if (unlikely(uaddr > end)) return -EFAULT; do { if (unlikely(__get_user(c, uaddr) != 0)) return -EFAULT; uaddr += PAGE_SIZE; } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) { return __get_user(c, end); } (void)c; return 0; } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); extern void __delete_from_page_cache(struct page *page, void *shadow); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: * the page is new, so we can just run __SetPageLocked() against it. */ static inline int add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int error; __SetPageLocked(page); error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); if (unlikely(error)) __ClearPageLocked(page); return error; } /** * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which * implement the ->readahead method should call readahead_page() or * readahead_page_batch() in a loop and attempt to start I/O against * each page in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. */ struct readahead_control { struct file *file; struct address_space *mapping; /* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; }; #define DEFINE_READAHEAD(rac, f, m, i) \ struct readahead_control rac = { \ .file = f, \ .mapping = m, \ ._index = i, \ } #define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct file_ra_state *, struct page *, unsigned long req_count); /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ static inline void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, mapping, index); page_cache_sync_ra(&ractl, ra, req_count); } /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @page: The page at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct page *page, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, mapping, index); page_cache_async_ra(&ractl, ra, page, req_count); } /** * readahead_page - Get the next page to read. * @rac: The current readahead request. * * Context: The page is locked and has an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: A pointer to the next page, or %NULL if we are done. */ static inline struct page *readahead_page(struct readahead_control *rac) { struct page *page; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; if (!rac->_nr_pages) { rac->_batch_count = 0; return NULL; } page = xa_load(&rac->mapping->i_pages, rac->_index); VM_BUG_ON_PAGE(!PageLocked(page), page); rac->_batch_count = thp_nr_pages(page); return page; } static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz) { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct page *page; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; rac->_batch_count = 0; xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, page)) continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); /* * The page cache isn't using multi-index entries yet, * so the xas cursor needs to be manually moved to the * next index. This can be removed once the page cache * is converted. */ if (PageHead(page)) xas_set(&xas, rac->_index + rac->_batch_count); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * readahead_page_batch - Get a batch of pages to read. * @rac: The current readahead request. * @array: An array of pointers to struct page. * * Context: The pages are locked and have an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: The number of pages placed in the array. 0 indicates the request * is complete. */ #define readahead_page_batch(rac, array) \ __readahead_batch(rac, array, ARRAY_SIZE(array)) /** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_pos(struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } /** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_length(struct readahead_control *rac) { return (loff_t)rac->_nr_pages * PAGE_SIZE; } /** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ static inline pgoff_t readahead_index(struct readahead_control *rac) { return rac->_index; } /** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ static inline unsigned int readahead_count(struct readahead_control *rac) { return rac->_nr_pages; } static inline unsigned long dir_pages(struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; } /** * page_mkwrite_check_truncate - check if page was truncated * @page: the page to check * @inode: the inode to check the page against * * Returns the number of bytes in the page up to EOF, * or -EFAULT if the page was truncated. */ static inline int page_mkwrite_check_truncate(struct page *page, struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; int offset = offset_in_page(size); if (page->mapping != inode->i_mapping) return -EFAULT; /* page is wholly inside EOF */ if (page->index < index) return PAGE_SIZE; /* page is wholly past EOF */ if (page->index > index || !offset) return -EFAULT; /* page is partially inside EOF */ return offset; } /** * i_blocks_per_page - How many blocks fit in this page. * @inode: The inode which contains the blocks. * @page: The page (head page if the page is a THP). * * If the block size is larger than the size of this page, return zero. * * Context: The caller should hold a refcount on the page to prevent it * from being split. * Return: The number of filesystem blocks covered by this page. */ static inline unsigned int i_blocks_per_page(struct inode *inode, struct page *page) { return thp_size(page) >> inode->i_blkbits; } #endif /* _LINUX_PAGEMAP_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/kernel.h> /* * This is largely generic for little-endian machines, but the * optimal byte mask counting is probably going to be something * that is architecture-specific. If you have a reliably fast * bit count instruction, that might be better than the multiply * and shift, for example. */ struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } #ifdef CONFIG_64BIT /* * Jan Achrenius on G+: microoptimized version of * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" * that works for the bytemasks without having to * mask them first. */ static inline long count_masked_bytes(unsigned long mask) { return mask*0x0001020304050608ul >> 56; } #else /* 32-bit case */ /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline long count_masked_bytes(long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) static inline unsigned long find_zero(unsigned long mask) { return count_masked_bytes(mask); } /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret, dummy; asm( "1:\tmov %2,%0\n" "2:\n" ".section .fixup,\"ax\"\n" "3:\t" "lea %2,%1\n\t" "and %3,%1\n\t" "mov (%1),%0\n\t" "leal %2,%%ecx\n\t" "andl %4,%%ecx\n\t" "shll $3,%%ecx\n\t" "shr %%cl,%0\n\t" "jmp 2b\n" ".previous\n" _ASM_EXTABLE(1b, 3b) :"=&r" (ret),"=&c" (dummy) :"m" (*(unsigned long *)addr), "i" (-sizeof(unsigned long)), "i" (sizeof(unsigned long)-1)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned index = MAJOR(dev); unsigned i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned index = MAJOR(dev); unsigned i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); if (IS_ERR(dir)) return PTR_ERR(dir); return 0; } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/thread_info.h> DECLARE_PER_CPU(int, __preempt_count); /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) /* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ static __always_inline int preempt_count(void) { return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { int old, new; do { old = raw_cpu_read_4(__preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old); } /* * must be macros to avoid header recursion hell */ #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* * We fold the NEED_RESCHED bit into the preempt count such that * preempt_enable() can decrement and test for needing to reschedule with a * single instruction. * * We invert the actual bit, so that when the decrement hits 0 we know we both * need to resched (the bit is cleared) and can resched (no preempt count). */ static __always_inline void set_preempt_need_resched(void) { raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* * The various preempt_count add/sub methods */ static __always_inline void __preempt_count_add(int val) { raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { raw_cpu_add_4(__preempt_count, -val); } /* * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule * a decrement which hits zero means we have no preempt_count and should * reschedule. */ static __always_inline bool __preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule_thunk(void); # define __preempt_schedule() \ asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); # define __preempt_schedule_notrace() \ asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; unsigned int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX struct mem_cgroup_id { int id; refcount_t ref; }; /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremented by the number of pages. This counter is used * to trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_NTARGETS, }; struct memcg_vmstats_percpu { long stat[MEMCG_NR_STAT]; unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ unsigned int generation; }; struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; /* * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. */ struct memcg_shrinker_map { struct rcu_head rcu; unsigned long map[]; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; /* Legacy local VM stats */ struct lruvec_stat __percpu *lruvec_stat_local; /* Subtree VM stats (batched updates) */ struct lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; struct memcg_shrinker_map __rcu *shrinker_map; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; enum memcg_kmem_state { KMEM_NONE, KMEM_ALLOCATED, KMEM_ONLINE, }; #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define MEMCG_PADDING(name) struct memcg_padding name; #else #define MEMCG_PADDING(name) #endif /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ /* Range enforcement for interrupt charges */ struct work_struct high_work; unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; int swappiness; /* OOM-Killer disable */ int oom_kill_disable; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; /* taken only while moving_account > 0 */ spinlock_t move_lock; unsigned long move_lock_flags; MEMCG_PADDING(_pad1_); atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #endif MEMCG_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; struct task_struct *move_lock_task; /* Legacy local VM stats and events */ struct memcg_vmstats_percpu __percpu *vmstats_local; /* Subtree VM stats and events (batched updates) */ struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ #define MEMCG_CHARGE_BATCH 32U extern struct mem_cgroup *root_mem_cgroup; static __always_inline bool memcg_stat_item_in_bytes(int idx) { if (idx == MEMCG_PERCPU_B) return true; return vmstat_item_in_bytes(idx); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; if (mem_cgroup_disabled()) return; /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_protected calculation is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. */ return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg); } static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { if (!mem_cgroup_supports_protection(memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) { if (!mem_cgroup_supports_protection(memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); static struct mem_cgroup_per_node * mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) { return memcg->nodeinfo[nid]; } /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @memcg & * @node combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { percpu_ref_get(&objcg->refcnt); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { percpu_ref_put(&objcg->refcnt); } /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released: * e.g. acquire the rcu_read_lock or css_set_lock. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { return READ_ONCE(objcg->memcg); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); int mem_cgroup_scan_tasks(struct mem_cgroup *, int (*)(struct task_struct *, void *), void *); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root or the memory * controller is in legacy no-hierarchy mode. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { if (!memcg->memory.parent) return NULL; return mem_cgroup_from_counter(memcg->memory.parent, memory); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; if (!root->use_hierarchy) return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return !!(memcg->css.flags & CSS_ONLINE); } /* * For memory reclaim. */ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); unsigned long mem_cgroup_size(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { long x = atomic_long_read(&memcg->vmstats[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { long x = 0; int cpu; for_each_possible_cpu(cpu) x += per_cpu(memcg->vmstats_local->stat[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_state(memcg, idx, val); local_irq_restore(flags); } /** * mod_memcg_page_state - update page state statistics * @page: the page * @idx: page state item to account * @val: number of pages (positive or negative) * * The @page must be locked or the caller must use lock_page_memcg() * to prevent double accounting when the page is concurrently being * moved to another memcg: * * lock_page(page) or lock_page_memcg(page) * if (TestClearPageState(page)) * mod_memcg_page_state(page, state, -1); * unlock_page(page) or unlock_page_memcg(page) * * Kernel pages are an exception to this, since they'll never move. */ static inline void __mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) __mod_memcg_state(page->mem_cgroup, idx, val); } static inline void mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); x = atomic_long_read(&pn->lruvec_stat[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x = 0; int cpu; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); for_each_possible_cpu(cpu) x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); void mod_memcg_obj_state(void *p, int idx, int val); static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_slab_state(p, idx, val); local_irq_restore(flags); } static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_page_state(page, idx, val); local_irq_restore(flags); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { unsigned long flags; local_irq_save(flags); __count_memcg_events(memcg, idx, count); local_irq_restore(flags); } static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, 1); rcu_read_unlock(); } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || event == MEMCG_SWAP_FAIL; atomic_long_inc(&memcg->memory_events_local[event]); if (!swap_event) cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); if (swap_event) cgroup_file_notify(&memcg->swap_events_file); else cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *head, unsigned int nr); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 struct mem_cgroup; static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) { return false; } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; } static inline void mem_cgroup_uncharge(struct page *page) { } static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) { return NULL; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { return 0; } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline struct mem_cgroup *lock_page_memcg(struct page *page) { return NULL; } static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } static inline void unlock_page_memcg(struct page *page) { } static inline void mem_cgroup_handle_over_high(void) { } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { return 0; } static inline void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void __mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { } static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_memcg_obj_state(void *p, int idx, int val) { } static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline void split_page_memcg(struct page *head, unsigned int nr) { } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_page_event(struct page *page, int idx) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG */ /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, -1); } static inline void __inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, 1); } static inline void __dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, -1); } static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, 1); } static inline void __dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, -1); } static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, 1); } static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, -1); } static inline void inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, 1); } static inline void dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, -1); } static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, 1); } static inline void dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, -1); } static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { if (mem_cgroup_disabled()) return; if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { if (time_before(jiffies, memcg->socket_pressure)) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; } extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; } static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } #endif #ifdef CONFIG_MEMCG_KMEM int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages); void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still * check if the cache is valid (it is either valid or NULL). * the slab_mutex must be held when looping through those caches */ #define for_each_memcg_cache_index(_idx) \ for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_enabled()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge_page(page, order); } static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages) { if (memcg_kmem_enabled()) return __memcg_kmem_charge(memcg, gfp, nr_pages); return 0; } static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge(memcg, nr_pages); } /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function * will return -1 when this is not a kmem-limited memcg. */ static inline int memcg_cache_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_obj(void *p); #else static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) static inline bool memcg_kmem_enabled(void) { return false; } static inline int memcg_cache_id(struct mem_cgroup *memcg) { return -1; } static inline void memcg_get_cache_ids(void) { } static inline void memcg_put_cache_ids(void) { } static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; } #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_MM_H #define _LINUX_SCHED_MM_H #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> /* * Routines for handling mm_structs */ extern struct mm_struct *mm_alloc(void); /** * mmgrab() - Pin a &struct mm_struct. * @mm: The &struct mm_struct to pin. * * Make sure that @mm will not get freed even after the owning task * exits. This doesn't guarantee that the associated address space * will still exist later on and mmget_not_zero() has to be used before * accessing it. * * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * * See also <Documentation/vm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) { atomic_inc(&mm->mm_count); } extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is * required by the membarrier system call before returning to * user-space, after storing to rq->curr. */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. * * Make sure that the address space of the given &struct mm_struct doesn't * go away. This does not protect against parts of the address space being * modified or freed, however. * * Never use this function to pin this address space for an * unbounded/indefinite amount of time. * * Use mmput() to release the reference acquired by mmget(). * * See also <Documentation/vm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) { atomic_inc(&mm->mm_users); } static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); #ifdef CONFIG_MMU /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ void mmput_async(struct mm_struct *); #endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* * Grab a reference to a task's mm, if it is not already going away * and ptrace_may_access with the mode parameter passed to it * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct on exit() */ extern void exit_mm_release(struct task_struct *, struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct on exec() */ extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); #else static inline void mm_update_next_owner(struct mm_struct *mm) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) { bool ret; /* * need RCU to access ->real_parent if CLONE_VM was used along with * CLONE_PARENT. * * We check real_parent->mm == tsk->mm because CLONE_VFORK does not * imply CLONE_VM * * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus * ->real_parent is not necessarily the task doing vfork(), so in * theory we can't rely on task_lock() if we want to dereference it. * * And in this case we can't trust the real_parent->mm == tsk->mm * check, it can be false negative. But we do not care, if init or * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); ret = tsk->vfork_done && rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; } /* * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; } return flags; } #ifdef CONFIG_LOCKDEP extern void __fs_reclaim_acquire(void); extern void __fs_reclaim_release(void); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else static inline void __fs_reclaim_acquire(void) { } static inline void __fs_reclaim_release(void) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate * * Similar to might_sleep() and other annotations, this can be used in functions * that might allocate, but often don't. Compiles to nothing without * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. */ static inline void might_alloc(gfp_t gfp_mask) { fs_reclaim_acquire(gfp_mask); fs_reclaim_release(gfp_mask); might_sleep_if(gfpflags_allow_blocking(gfp_mask)); } /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. * All further allocations will implicitly drop __GFP_IO flag and so * they are safe for the IO critical section from the allocation recursion * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * * This function is safe to be used from any context. */ static inline unsigned int memalloc_noio_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOIO; current->flags |= PF_MEMALLOC_NOIO; return flags; } /** * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; } /** * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. * * This functions marks the beginning of the GFP_NOFS allocation scope. * All further allocations will implicitly drop __GFP_FS flag and so * they are safe for the FS critical section from the allocation recursion * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * * This function is safe to be used from any context. */ static inline unsigned int memalloc_nofs_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOFS; current->flags |= PF_MEMALLOC_NOFS; return flags; } /** * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags; } static inline unsigned int memalloc_noreclaim_save(void) { unsigned int flags = current->flags & PF_MEMALLOC; current->flags |= PF_MEMALLOC; return flags; } static inline void memalloc_noreclaim_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC) | flags; } #ifdef CONFIG_CMA static inline unsigned int memalloc_nocma_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOCMA; current->flags |= PF_MEMALLOC_NOCMA; return flags; } static inline void memalloc_nocma_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags; } #else static inline unsigned int memalloc_nocma_save(void) { return 0; } static inline void memalloc_nocma_restore(unsigned int flags) { } #endif #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { struct mem_cgroup *old; if (in_interrupt()) { old = this_cpu_read(int_active_memcg); this_cpu_write(int_active_memcg, memcg); } else { old = current->active_memcg; current->active_memcg = memcg; } return old; } #else static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { return NULL; } #endif #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include <asm/membarrier.h> #endif static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return; sync_core_before_usermode(); } extern void membarrier_exec_mmap(struct mm_struct *mm); #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { } #endif static inline void membarrier_exec_mmap(struct mm_struct *mm) { } static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } #endif #endif /* _LINUX_SCHED_MM_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_CONTEXT_H #define _ASM_X86_MMU_CONTEXT_H #include <asm/desc.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/pkeys.h> #include <trace/events/tlb.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> extern atomic64_t last_mm_ctx_id; #ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { } #endif /* !CONFIG_PARAVIRT_XXL */ #ifdef CONFIG_PERF_EVENTS DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); void cr4_update_pce(void *ignored); #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. */ struct ldt_struct { /* * Xen requires page-aligned LDTs with special permissions. This is * needed to prevent us from installing evil descriptors such as * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; unsigned int nr_entries; /* * If PTI is in use, then the entries array is not mapped while we're * in user mode. The whole array will be aliased at the addressed * given by ldt_slot_va(slot). We use two slots so that we can allocate * and map, and enable a new LDT without invalidating the mapping * of an older, still-in-use LDT. * * slot will be -1 if this LDT doesn't have an alias mapping. */ int slot; }; /* * Used for LDT copy/destruction. */ static inline void init_new_context_ldt(struct mm_struct *mm) { mm->context.ldt = NULL; init_rwsem(&mm->context.ldt_usr_sem); } int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ static inline void init_new_context_ldt(struct mm_struct *mm) { } static inline int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm) { return 0; } static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL extern void load_mm_ldt(struct mm_struct *mm); extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else static inline void load_mm_ldt(struct mm_struct *mm) { clear_LDT(); } static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { DEBUG_LOCKS_WARN_ON(preemptible()); } #endif extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); /* * Init a new mm. Used on mm copies, like at fork() * and on mm's that are brand-new, like at execve(). */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mutex_init(&mm->context.lock); mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } #endif init_new_context_ldt(mm); return 0; } static inline void destroy_context(struct mm_struct *mm) { destroy_context_ldt(mm); } extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); #define switch_mm_irqs_off switch_mm_irqs_off #define activate_mm(prev, next) \ do { \ paravirt_activate_mm((prev), (next)); \ switch_mm((prev), (next), NULL); \ } while (0); #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ lazy_load_gs(0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ do { \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) #endif static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; #endif } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 static inline bool is_64bit_mm(struct mm_struct *mm) { return !IS_ENABLED(CONFIG_IA32_EMULATION) || !(mm->context.ia32_compat == TIF_IA32); } #else static inline bool is_64bit_mm(struct mm_struct *mm) { return false; } #endif static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other * processes or any way to tell *which * PKRU in a threaded * process we could use. * * So do not enforce things if the VMA is not from the current * mm, or if we are in a kernel thread. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { /* pkeys never affect instruction fetches */ if (execute) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return __pkru_allows_pkey(vma_pkey(vma), write); } unsigned long __get_current_cr3_fast(void); #endif /* _ASM_X86_MMU_CONTEXT_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 | // SPDX-License-Identifier: GPL-2.0 /* * Workingset detection * * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner */ #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/writeback.h> #include <linux/shmem_fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/swap.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/mm.h> /* * Double CLOCK lists * * Per node, two clock lists are maintained for file pages: the * inactive and the active list. Freshly faulted pages start out at * the head of the inactive list and page reclaim scans pages from the * tail. Pages that are accessed multiple times on the inactive list * are promoted to the active list, to protect them from reclaim, * whereas active pages are demoted to the inactive list when the * active list grows too big. * * fault ------------------------+ * | * +--------------+ | +-------------+ * reclaim <- | inactive | <-+-- demotion | active | <--+ * +--------------+ +-------------+ | * | | * +-------------- promotion ------------------+ * * * Access frequency and refault distance * * A workload is thrashing when its pages are frequently used but they * are evicted from the inactive list every time before another access * would have promoted them to the active list. * * In cases where the average access distance between thrashing pages * is bigger than the size of memory there is nothing that can be * done - the thrashing set could never fit into memory under any * circumstance. * * However, the average access distance could be bigger than the * inactive list, yet smaller than the size of memory. In this case, * the set could fit into memory if it weren't for the currently * active pages - which may be used more, hopefully less frequently: * * +-memory available to cache-+ * | | * +-inactive------+-active----+ * a b | c d e f g h i | J K L M N | * +---------------+-----------+ * * It is prohibitively expensive to accurately track access frequency * of pages. But a reasonable approximation can be made to measure * thrashing on the inactive list, after which refaulting pages can be * activated optimistically to compete with the existing active pages. * * Approximating inactive page access frequency - Observations: * * 1. When a page is accessed for the first time, it is added to the * head of the inactive list, slides every existing inactive page * towards the tail by one slot, and pushes the current tail page * out of memory. * * 2. When a page is accessed for the second time, it is promoted to * the active list, shrinking the inactive list by one slot. This * also slides all inactive pages that were faulted into the cache * more recently than the activated page towards the tail of the * inactive list. * * Thus: * * 1. The sum of evictions and activations between any two points in * time indicate the minimum number of inactive pages accessed in * between. * * 2. Moving one inactive page N page slots towards the tail of the * list requires at least N inactive page accesses. * * Combining these: * * 1. When a page is finally evicted from memory, the number of * inactive pages accessed while the page was in cache is at least * the number of page slots on the inactive list. * * 2. In addition, measuring the sum of evictions and activations (E) * at the time of a page's eviction, and comparing it to another * reading (R) at the time the page faults back into memory tells * the minimum number of accesses while the page was not cached. * This is called the refault distance. * * Because the first access of the page was the fault and the second * access the refault, we combine the in-cache distance with the * out-of-cache distance to get the complete minimum access distance * of this page: * * NR_inactive + (R - E) * * And knowing the minimum access distance of a page, we can easily * tell if the page would be able to stay in cache assuming all page * slots in the cache were available: * * NR_inactive + (R - E) <= NR_inactive + NR_active * * which can be further simplified to * * (R - E) <= NR_active * * Put into words, the refault distance (out-of-cache) can be seen as * a deficit in inactive list space (in-cache). If the inactive list * had (R - E) more page slots, the page would not have been evicted * in between accesses, but activated instead. And on a full system, * the only thing eating into inactive list space is active pages. * * * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given * time there is actually a good chance that pages on the active list * are no longer in active use. * * So when a refault distance of (R - E) is observed and there are at * least (R - E) active pages, the refaulting page is activated * optimistically in the hope that (R - E) active pages are actually * used less frequently than the refaulting page - or even not used at * all anymore. * * That means if inactive cache is refaulting with a suitable refault * distance, we assume the cache workingset is transitioning and put * pressure on the current active list. * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. * * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * * Refaulting active pages * * If on the other hand the refaulting pages have recently been * deactivated, it means that the active list is no longer protecting * actively used cache from reclaim. The cache is NOT transitioning to * a different workingset; the existing workingset is thrashing in the * space allocated to the page cache. * * * Implementation * * For each node's LRU lists, a counter for inactive evictions and * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible * refault distance will immediately activate the refaulting page. */ #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* * Eviction timestamps need to be able to cover the full range of * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group * evictions into coarser buckets by shaving off lower timestamp bits. */ static unsigned int bucket_order __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, bool workingset) { eviction >>= bucket_order; eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; eviction = (eviction << 1) | workingset; return xa_mk_value(eviction); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp, bool *workingsetp) { unsigned long entry = xa_to_value(shadow); int memcgid, nid; bool workingset; workingset = entry & 1; entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); entry >>= MEM_CGROUP_ID_SHIFT; *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; *workingsetp = workingset; } /** * workingset_age_nonresident - age non-resident entries as LRU ages * @lruvec: the lruvec that was aged * @nr_pages: the number of pages to count * * As in-memory pages are aged, non-resident pages need to be aged as * well, in order for the refault distances later on to be comparable * to the in-memory dimensions. This function allows reclaim and LRU * operations to drive the non-resident aging along in parallel. */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a * round-robin fashion. That means that each cgroup has an LRU * order that is composed of the LRU orders of its child * cgroups; and every page has an LRU position not just in the * cgroup that owns it, but in all of that group's ancestors. * * So when the physical inactive list of a leaf cgroup ages, * the virtual inactive lists of all its parents, including * the root cgroup's, age as well. */ do { atomic_long_add(nr_pages, &lruvec->nonresident_age); } while ((lruvec = parent_lruvec(lruvec))); } /** * workingset_eviction - note the eviction of a page from memory * @target_memcg: the cgroup that is causing the reclaim * @page: the page being evicted * * Returns a shadow entry to be stored in @page->mapping->i_pages in place * of the evicted @page so that a later refault can be detected. */ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = page_pgdat(page); unsigned long eviction; struct lruvec *lruvec; int memcgid; /* Page is fully exclusive and pins page->mem_cgroup */ VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); lruvec = mem_cgroup_lruvec(target_memcg, pgdat); workingset_age_nonresident(lruvec, thp_nr_pages(page)); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); eviction = atomic_long_read(&lruvec->nonresident_age); return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node and the memcg whose memory * pressure caused the eviction. */ void workingset_refault(struct page *page, void *shadow) { bool file = page_is_file_lru(page); struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; unsigned long workingset_size; struct pglist_data *pgdat; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; bool workingset; int memcgid; unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might * have been deleted since the page's eviction. * * Note that in rare events the ID could have been recycled * for a new cgroup that refaults a shared page. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging * algorithm's job to shake out the minimum access frequency * for the active cache. * * XXX: On !CONFIG_MEMCG, this will always return NULL; it * would be better if the root_mem_cgroup existed in all * configurations instead. */ eviction_memcg = mem_cgroup_from_id(memcgid); if (!mem_cgroup_disabled() && !eviction_memcg) goto out; eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the * nonresident_age to lap a shadow entry in the field, which * can then result in a false small refault distance, leading * to a false activation should this old entry actually * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; /* * The activation decision for this page is made at the level * where the eviction occurred, as that is where the LRU order * during page reclaim is being determined. * * However, the cgroup that will own the page is the one that * is actually experiencing the refault event. */ memcg = page_memcg(page); lruvec = mem_cgroup_lruvec(memcg, pgdat); inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if * all the memory was available to the workingset. Whether * workingset competition needs to consider anon or not depends * on having swap. */ workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); if (!file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_FILE); } if (mem_cgroup_get_nr_swap_pages(memcg) > 0) { workingset_size += lruvec_page_state(eviction_lruvec, NR_ACTIVE_ANON); if (file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_ANON); } } if (refault_distance > workingset_size) goto out; SetPageActive(page); workingset_age_nonresident(lruvec, thp_nr_pages(page)); inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file); /* Page was active prior to eviction */ if (workingset) { SetPageWorkingset(page); /* XXX: Move to lru_cache_add() when it supports new vs putback */ spin_lock_irq(&page_pgdat(page)->lru_lock); lru_note_cost_page(page); spin_unlock_irq(&page_pgdat(page)->lru_lock); inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file); } out: rcu_read_unlock(); } /** * workingset_activation - note a page activation * @page: page that is being activated */ void workingset_activation(struct page *page) { struct mem_cgroup *memcg; struct lruvec *lruvec; rcu_read_lock(); /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. * * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); workingset_age_nonresident(lruvec, thp_nr_pages(page)); out: rcu_read_unlock(); } /* * Shadow entries reflect the share of the working set that does not * fit into memory, so their number depends on the access pattern of * the workload. In most cases, they will refault or get reclaimed * along with the inode, but a (malicious) workload that streams * through files with a total size several times that of available * memory, while preventing the inodes from being reclaimed, can * create excessive amounts of shadow nodes. To keep a lid on this, * track shadow nodes and reclaim them when they grow way past the * point where they would still be useful. */ static struct list_lru shadow_nodes; void workingset_update_node(struct xa_node *node) { /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. * * Avoid acquiring the list_lru lock when the nodes are * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); __inc_lruvec_slab_state(node, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); __dec_lruvec_slab_state(node, WORKINGSET_NODES); } } } static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long max_nodes; unsigned long nodes; unsigned long pages; nodes = list_lru_shrink_count(&shadow_nodes, sc); /* * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. * * The size of the active list converges toward 100% of * overall page cache as memory grows, with only a tiny * inactive list. Assume the total cache size for that. * * Nodes might be sparsely populated, with only one shadow * entry in the extreme case. Obviously, we cannot keep one * node for every eligible shadow entry, so compromise on a * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ #ifdef CONFIG_MEMCG if (sc->memcg) { struct lruvec *lruvec; int i; lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) pages += lruvec_page_state_local(lruvec, NR_LRU_BASE + i); pages += lruvec_page_state_local( lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; pages += lruvec_page_state_local( lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT; } else #endif pages = node_present_pages(sc->nid); max_nodes = pages >> (XA_CHUNK_SHIFT - 3); if (!nodes) return SHRINK_EMPTY; if (nodes <= max_nodes) return 0; return nodes - max_nodes; } static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) __must_hold(lru_lock) { struct xa_node *node = container_of(item, struct xa_node, private_list); struct address_space *mapping; int ret; /* * Page cache insertions and deletions synchronously maintain * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { spin_unlock_irq(lru_lock); ret = LRU_RETRY; goto out; } list_lru_isolate(lru, item); __dec_lruvec_slab_state(node, WORKINGSET_NODES); spin_unlock(lru_lock); /* * The nodes should only contain one or more shadow entries, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; mapping->nrexceptional -= node->nr_values; xa_delete_node(node, workingset_update_node); __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM); out_invalid: xa_unlock_irq(&mapping->i_pages); ret = LRU_REMOVED_RETRY; out: cond_resched(); spin_lock_irq(lru_lock); return ret; } static unsigned long scan_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { /* list_lru lock nests inside the IRQ-safe i_pages lock */ return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, NULL); } static struct shrinker workingset_shadow_shrinker = { .count_objects = count_shadow_nodes, .scan_objects = scan_shadow_nodes, .seeks = 0, /* ->count reports only fully expendable nodes */ .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, }; /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. */ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { unsigned int timestamp_bits; unsigned int max_order; int ret; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* * Calculate the eviction bucket size to cover the longest * actionable refault distance, which is currently half of * memory (totalram_pages/2). However, memory hotplug may add * some more pages at runtime, so keep working with up to * double the initial memory by using totalram_pages as-is. */ timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT; max_order = fls_long(totalram_pages() - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); ret = prealloc_shrinker(&workingset_shadow_shrinker); if (ret) goto err; ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, &workingset_shadow_shrinker); if (ret) goto err_list_lru; register_shrinker_prepared(&workingset_shadow_shrinker); return 0; err_list_lru: free_prealloced_shrinker(&workingset_shadow_shrinker); err: return ret; } module_init(workingset_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0-or-later /* delayacct.c - per-task delay accounting * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 */ #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/slab.h> #include <linux/taskstats.h> #include <linux/time.h> #include <linux/sysctl.h> #include <linux/delayacct.h> #include <linux/module.h> int delayacct_on __read_mostly = 1; /* Delay accounting turned on/off */ EXPORT_SYMBOL_GPL(delayacct_on); struct kmem_cache *delayacct_cache; static int __init delayacct_setup_disable(char *str) { delayacct_on = 0; return 1; } __setup("nodelayacct", delayacct_setup_disable); void delayacct_init(void) { delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT); delayacct_tsk_init(&init_task); } void __delayacct_tsk_init(struct task_struct *tsk) { tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL); if (tsk->delays) raw_spin_lock_init(&tsk->delays->lock); } /* * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count) { s64 ns = ktime_get_ns() - *start; unsigned long flags; if (ns > 0) { raw_spin_lock_irqsave(lock, flags); *total += ns; (*count)++; raw_spin_unlock_irqrestore(lock, flags); } } void __delayacct_blkio_start(void) { current->delays->blkio_start = ktime_get_ns(); } /* * We cannot rely on the `current` macro, as we haven't yet switched back to * the process being woken. */ void __delayacct_blkio_end(struct task_struct *p) { struct task_delay_info *delays = p->delays; u64 *total; u32 *count; if (p->delays->flags & DELAYACCT_PF_SWAPIN) { total = &delays->swapin_delay; count = &delays->swapin_count; } else { total = &delays->blkio_delay; count = &delays->blkio_count; } delayacct_end(&delays->lock, &delays->blkio_start, total, count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { u64 utime, stime, stimescaled, utimescaled; unsigned long long t2, t3; unsigned long flags, t1; s64 tmp; task_cputime(tsk, &utime, &stime); tmp = (s64)d->cpu_run_real_total; tmp += utime + stime; d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; task_cputime_scaled(tsk, &utimescaled, &stimescaled); tmp = (s64)d->cpu_scaled_run_real_total; tmp += utimescaled + stimescaled; d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; /* * No locking available for sched_info (and too expensive to add one) * Mitigate by taking snapshot of values */ t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; t3 = tsk->se.sum_exec_runtime; d->cpu_count += t1; tmp = (s64)d->cpu_delay_total + t2; d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp; tmp = (s64)d->cpu_run_virtual_total + t3; d->cpu_run_virtual_total = (tmp < (s64)d->cpu_run_virtual_total) ? 0 : tmp; /* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */ raw_spin_lock_irqsave(&tsk->delays->lock, flags); tmp = d->blkio_delay_total + tsk->delays->blkio_delay; d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp; tmp = d->swapin_delay_total + tsk->delays->swapin_delay; d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; } __u64 __delayacct_blkio_ticks(struct task_struct *tsk) { __u64 ret; unsigned long flags; raw_spin_lock_irqsave(&tsk->delays->lock, flags); ret = nsec_to_clock_t(tsk->delays->blkio_delay + tsk->delays->swapin_delay); raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return ret; } void __delayacct_freepages_start(void) { current->delays->freepages_start = ktime_get_ns(); } void __delayacct_freepages_end(void) { delayacct_end( ¤t->delays->lock, ¤t->delays->freepages_start, ¤t->delays->freepages_delay, ¤t->delays->freepages_count); } void __delayacct_thrashing_start(void) { current->delays->thrashing_start = ktime_get_ns(); } void __delayacct_thrashing_end(void) { delayacct_end(¤t->delays->lock, ¤t->delays->thrashing_start, ¤t->delays->thrashing_delay, ¤t->delays->thrashing_count); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TASK_WORK_H #define _LINUX_TASK_WORK_H #include <linux/list.h> #include <linux/sched.h> typedef void (*task_work_func_t)(struct callback_head *); static inline void init_task_work(struct callback_head *twork, task_work_func_t func) { twork->func = func; } enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, }; int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t); bool task_work_cancel(struct task_struct *task, struct callback_head *cb); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) { task_work_run(); } #endif /* _LINUX_TASK_WORK_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <net/busy_poll.h> /* * LOCKING: * There are three level of locking required by epoll : * * 1) epmutex (mutex) * 2) ep->mtx (mutex) * 3) ep->lock (rwlock) * * The acquire order is the one listed above, from 1 to 3. * We need a rwlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need * a spinlock. During the event transfer loop (from kernel to * user space) we could end up sleeping due a copy_to_user(), so * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). * Then we also need a global mutex to serialize eventpoll_release_file() * and ep_free(). * This mutex is acquired by ep_free() during the epoll file * cleanup path and it is also acquired by eventpoll_release_file() * if a file has been pushed inside an epoll set and it is then * close()d without a previous call to epoll_ctl(EPOLL_CTL_DEL). * It is also acquired when inserting an epoll fd onto another epoll * fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two * simultaneous inserts (A into B and B into A) from racing and * constructing a cycle without either insert observing that it is * going to. * It is necessary to acquire multiple "ep->mtx"es at once in the * case when one epoll fd is added to another. In this case, we * always acquire the locks in the order of nesting (i.e. after * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired * before e2->mtx). Since we disallow cycles of epoll file * descriptors, this ensures that the mutexes are well-ordered. In * order to communicate this nesting to lockdep, when walking a tree * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global * mutex "epmutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. * Events that require holding "epmutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee * a better scalability. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) struct epoll_filefd { struct file *file; int fd; } __packed; /* * Structure used to track possible nested calls, for too deep recursions * and loop cycles. */ struct nested_call_node { struct list_head llink; void *cookie; void *ctx; }; /* * This structure is used as collector for nested calls, to check for * maximum recursion dept and loop cycles. */ struct nested_calls { struct list_head tasks_call_list; spinlock_t lock; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* List header used to link this structure to the eventpoll ready list */ struct list_head rdllink; /* * Works together "struct eventpoll"->ovflist in keeping the * single linked chain of items. */ struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; /* Number of active wait queue attached to poll operations */ int nwait; /* List containing poll wait queues */ struct list_head pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct list_head fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ rwlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_scan_ready_list is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct list_head llink; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* Used by the ep_send_events() function as callback private data */ struct ep_send_events_data { int maxevents; struct epoll_event __user *events; int res; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* * This mutex is used to serialize ep_free() and eventpoll_release_file(). */ static DEFINE_MUTEX(epmutex); static u64 loop_check_gen = 0; /* Used to check for epoll file descriptor inclusion loops */ static struct nested_calls poll_loop_ncalls; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __read_mostly; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __read_mostly; /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epmutex. */ static LIST_HEAD(tfile_check_list); #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, { } }; #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; static inline int is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Setup the structure that is used as key for the RB tree */ static inline void ep_set_ffd(struct epoll_filefd *ffd, struct file *file, int fd) { ffd->file = file; ffd->fd = fd; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_filefd *p1, struct epoll_filefd *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* Tells us if the item is currently linked */ static inline int ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /* Get the "struct epitem" from an epoll queue wrapper */ static inline struct epitem *ep_item_from_epqueue(poll_table *p) { return container_of(p, struct ep_pqueue, pt)->epi; } /* Initialize the poll safe wake up structure */ static void ep_nested_calls_init(struct nested_calls *ncalls) { INIT_LIST_HEAD(&ncalls->tasks_call_list); spin_lock_init(&ncalls->lock); } /** * ep_events_available - Checks if ready events might be available. * * @ep: Pointer to the eventpoll context. * * Returns: Returns a value different than zero if ready events are available, * or zero otherwise. */ static inline int ep_events_available(struct eventpoll *ep) { return !list_empty_careful(&ep->rdllist) || READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_timeout(start_time); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static void ep_busy_loop(struct eventpoll *ep, int nonblock) { unsigned int napi_id = READ_ONCE(ep->napi_id); if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep); } static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) { if (ep->napi_id) ep->napi_id = 0; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep; unsigned int napi_id; struct socket *sock; struct sock *sk; int err; if (!net_busy_loop_on()) return; sock = sock_from_file(epi->ffd.file, &err); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); ep = epi->ep; /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } #else static inline void ep_busy_loop(struct eventpoll *ep, int nonblock) { } static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) { } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } #endif /* CONFIG_NET_RX_BUSY_POLL */ /** * ep_call_nested - Perform a bound (possibly) nested call, by checking * that the recursion limit is not exceeded, and that * the same nested call (by the meaning of same cookie) is * no re-entered. * * @ncalls: Pointer to the nested_calls structure to be used for this call. * @nproc: Nested call core function pointer. * @priv: Opaque data to be passed to the @nproc callback. * @cookie: Cookie to be used to identify this nested call. * @ctx: This instance context. * * Returns: Returns the code returned by the @nproc callback, or -1 if * the maximum recursion limit has been exceeded. */ static int ep_call_nested(struct nested_calls *ncalls, int (*nproc)(void *, void *, int), void *priv, void *cookie, void *ctx) { int error, call_nests = 0; unsigned long flags; struct list_head *lsthead = &ncalls->tasks_call_list; struct nested_call_node *tncur; struct nested_call_node tnode; spin_lock_irqsave(&ncalls->lock, flags); /* * Try to see if the current task is already inside this wakeup call. * We use a list here, since the population inside this set is always * very much limited. */ list_for_each_entry(tncur, lsthead, llink) { if (tncur->ctx == ctx && (tncur->cookie == cookie || ++call_nests > EP_MAX_NESTS)) { /* * Ops ... loop detected or maximum nest level reached. * We abort this wake by breaking the cycle itself. */ error = -1; goto out_unlock; } } /* Add the current task and cookie to the list */ tnode.ctx = ctx; tnode.cookie = cookie; list_add(&tnode.llink, lsthead); spin_unlock_irqrestore(&ncalls->lock, flags); /* Call the nested function */ error = (*nproc)(priv, cookie, call_nests); /* Remove the current task from the list */ spin_lock_irqsave(&ncalls->lock, flags); list_del(&tnode.llink); out_unlock: spin_unlock_irqrestore(&ncalls->lock, flags); return error; } /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to * avoid stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * If it is cleared by POLLFREE, it should be rcu-safe. * If we read NULL we need a barrier paired with * smp_store_release() in ep_poll_callback(), otherwise * we rely on whead->lock. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held (or "epmutex" if called from * ep_free). */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct list_head *lsthead = &epi->pwqlist; struct eppoll_entry *pwq; while (!list_empty(lsthead)) { pwq = list_first_entry(lsthead, struct eppoll_entry, llink); list_del(&pwq->llink); ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /** * ep_scan_ready_list - Scans the ready list in a way that makes possible for * the scan code, to call f_op->poll(). Also allows for * O(NumReady) performance. * * @ep: Pointer to the epoll private data structure. * @sproc: Pointer to the scan callback. * @priv: Private opaque data passed to the @sproc callback. * @depth: The current depth of recursive f_op->poll calls. * @ep_locked: caller already holds ep->mtx * * Returns: The same integer error code returned by the @sproc callback. */ static __poll_t ep_scan_ready_list(struct eventpoll *ep, __poll_t (*sproc)(struct eventpoll *, struct list_head *, void *), void *priv, int depth, bool ep_locked) { __poll_t res; struct epitem *epi, *nepi; LIST_HEAD(txlist); lockdep_assert_irqs_enabled(); /* * We need to lock this because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ if (!ep_locked) mutex_lock_nested(&ep->mtx, depth); /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ write_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, &txlist); WRITE_ONCE(ep->ovflist, NULL); write_unlock_irq(&ep->lock); /* * Now call the callback function. */ res = (*sproc)(ep, &txlist, priv); write_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { /* * We need to check if the item is already in the list. * During the "sproc" callback execution time, items are * queued into ->ovflist but the "txlist" might already * contain them, and the list_splice() below takes care of them. */ if (!ep_is_linked(epi)) { /* * ->ovflist is LIFO, so we have to reverse it in order * to keep in FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } /* * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after * releasing the lock, events will be queued in the normal way inside * ep->rdllist. */ WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); /* * Quickly re-inject items left on "txlist". */ list_splice(&txlist, &ep->rdllist); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } write_unlock_irq(&ep->lock); if (!ep_locked) mutex_unlock(&ep->mtx); return res; } static void epi_rcu_free(struct rcu_head *head) { struct epitem *epi = container_of(head, struct epitem, rcu); kmem_cache_free(epi_cache, epi); } /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. */ static int ep_remove(struct eventpoll *ep, struct epitem *epi) { struct file *file = epi->ffd.file; lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. */ ep_unregister_pollwait(ep, epi); /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); list_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); rb_erase_cached(&epi->rbn, &ep->rbr); write_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ call_rcu(&epi->rcu, epi_rcu_free); atomic_long_dec(&ep->user->epoll_watches); return 0; } static void ep_free(struct eventpoll *ep) { struct rb_node *rbp; struct epitem *epi; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); /* * We need to lock this because we could be hit by * eventpoll_release_file() while we're freeing the "struct eventpoll". * We do not need to hold "ep->mtx" here because the epoll file * is on the way to be removed and no one has references to it * anymore. The only hit might come from eventpoll_release_file() but * holding "epmutex" is sufficient here. */ mutex_lock(&epmutex); /* * Walks through the whole tree by unregistering poll callbacks. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } /* * Walks through the whole tree by freeing each "struct epitem". At this * point we are sure no poll callbacks will be lingering around, and also by * holding "epmutex" we can be sure that no file cleanup code will hit * us during this operation. So we can avoid the lock on "ep->lock". * We do not need to lock ep->mtx, either, we only do it to prevent * a lockdep warning. */ mutex_lock(&ep->mtx); while ((rbp = rb_first_cached(&ep->rbr)) != NULL) { epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); cond_resched(); } mutex_unlock(&ep->mtx); mutex_unlock(&epmutex); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); kfree(ep); } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_free(ep); return 0; } static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv); static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt); /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct eventpoll *ep; bool locked; pt->_key = epi->event.events; if (!is_file_epoll(epi->ffd.file)) return vfs_poll(epi->ffd.file, pt) & epi->event.events; ep = epi->ffd.file->private_data; poll_wait(epi->ffd.file, &ep->poll_wait, pt); locked = pt && (pt->_qproc == ep_ptable_queue_proc); return ep_scan_ready_list(epi->ffd.file->private_data, ep_read_events_proc, &depth, depth, locked) & epi->event.events; } static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv) { struct epitem *epi, *tmp; poll_table pt; int depth = *(int *)priv; init_poll_funcptr(&pt, NULL); depth++; list_for_each_entry_safe(epi, tmp, head, rdllink) { if (ep_item_poll(epi, &pt, depth)) { return EPOLLIN | EPOLLRDNORM; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } return 0; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { struct eventpoll *ep = file->private_data; int depth = 0; /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ return ep_scan_ready_list(ep, ep_read_events_proc, &depth, depth, false); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, }; /* * This is called from eventpoll_release() to unlink files from the eventpoll * interface. We need to have this facility to cleanup correctly files that are * closed without being removed from the eventpoll interface. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi, *next; /* * We don't want to get "file->f_lock" because it is not * necessary. It is not necessary because we're in the "struct file" * cleanup path, and this means that no one is using this file anymore. * So, for example, epoll_ctl() cannot hit here since if we reach this * point, the file counter already went to zero and fget() would fail. * The only hit might come from ep_free() but by holding the mutex * will correctly serialize the operation. We do need to acquire * "ep->mtx" after "epmutex" because ep_remove() requires it when called * from anywhere but ep_free(). * * Besides, ep_remove() acquires the lock, so we can't hold it here. */ mutex_lock(&epmutex); list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) { ep = epi->ep; mutex_lock_nested(&ep->mtx, 0); ep_remove(ep, epi); mutex_unlock(&ep->mtx); } mutex_unlock(&epmutex); } static int ep_alloc(struct eventpoll **pep) { int error; struct user_struct *user; struct eventpoll *ep; user = get_current_user(); error = -ENOMEM; ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (unlikely(!ep)) goto free_uid; mutex_init(&ep->mtx); rwlock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = user; *pep = ep; return 0; free_uid: free_uid(user); return error; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; struct epoll_filefd ffd; ep_set_ffd(&ffd, file, fd); for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ /** * Adds a new entry to the tail of the list in a lockless way, i.e. * multiple CPUs are allowed to call this function concurrently. * * Beware: it is necessary to prevent any other modifications of the * existing list until all changes are completed, in other words * concurrent list_add_tail_lockless() calls should be protected * with a read lock, where write lock acts as a barrier which * makes sure all list_add_tail_lockless() calls are fully * completed. * * Also an element can be locklessly added to the list only in one * direction i.e. either to the tail either to the head, otherwise * concurrent access will corrupt the list. * * Returns %false if element has been already added to the list, %true * otherwise. */ static inline bool list_add_tail_lockless(struct list_head *new, struct list_head *head) { struct list_head *prev; /* * This is simple 'new->next = head' operation, but cmpxchg() * is used in order to detect that same element has been just * added to the list from another CPU: the winner observes * new->next == new. */ if (cmpxchg(&new->next, new, head) != new) return false; /* * Initially ->next of a new element must be updated with the head * (we are inserting to the tail) and only then pointers are atomically * exchanged. XCHG guarantees memory ordering, thus ->next should be * updated before pointers are actually swapped and pointers are * swapped before prev->next is updated. */ prev = xchg(&head->prev, new); /* * It is safe to modify prev->next and new->prev, because a new element * is added only to the tail and new->next is updated before XCHG. */ prev->next = new; new->prev = prev; return true; } /** * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, * i.e. multiple CPUs are allowed to call this function concurrently. * * Returns %false if epi element has been already chained, %true otherwise. */ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; /* Fast preliminary check */ if (epi->next != EP_UNACTIVE_PTR) return false; /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; /* Atomically exchange tail */ epi->next = xchg(&ep->ovflist, epi); return true; } /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. * * This callback takes a read lock in order not to content with concurrent * events from another file descriptors, thus all modifications to ->rdllist * or ->ovflist are lockless. Read lock is paired with the write lock from * ep_scan_ready_list(), which stops all list modifications and guarantees * that lists state is seen correctly. * * Another thing worth to mention is that ep_poll_callback() can be called * concurrently for the same @epi from different CPUs if poll table was inited * with several wait queues entries. Plural wakeup from different CPUs of a * single wait queue is serialized by wq.lock, but the case when multiple wait * queues are used should be detected accordingly. This is detected using * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; read_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { if (chain_epi_lockless(epi)) ep_pm_stay_awake_rcu(epi); } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } if (sync) wake_up_sync(&ep->wq); else wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: read_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * If we race with ep_remove_wait_queue() it can miss * ->whead = NULL and do another remove_wait_queue() after * us, so we can't use __remove_wait_queue(). */ list_del_init(&wait->entry); /* * ->whead != NULL protects us from the race with ep_free() * or ep_remove(), ep_remove_wait_queue() takes whead->lock * held by the caller. Once we nullify it, nothing protects * ep/epi or even wait. */ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct epitem *epi = ep_item_from_epqueue(pt); struct eppoll_entry *pwq; if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) { init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); list_add_tail(&pwq->llink, &epi->pwqlist); epi->nwait++; } else { /* We have to signal that an error occurred */ epi->nwait = -1; } } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate * from a single file of interest. For example, we allow 1000 paths of length * 1, to emanate from each file of interest. This essentially represents the * potential wakeup paths, which need to be limited in order to avoid massive * uncontrolled wakeup storms. The common use case should be a single ep which * is connected to n file sources. In this case each file source has 1 path * of length 1. Thus, the numbers below should be more than sufficient. These * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify * and delete can't add additional paths. Protected by the epmutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count[PATH_ARR_SIZE]; static int path_count_inc(int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(void) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) path_count[i] = 0; } static int reverse_path_check_proc(void *priv, void *cookie, int call_nests) { int error = 0; struct file *file = priv; struct file *child_file; struct epitem *epi; /* CTL_DEL can remove links here, but that can't increase our count */ rcu_read_lock(); list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) { child_file = epi->ep->file; if (is_file_epoll(child_file)) { if (list_empty(&child_file->f_ep_links)) { if (path_count_inc(call_nests)) { error = -1; break; } } else { error = ep_call_nested(&poll_loop_ncalls, reverse_path_check_proc, child_file, child_file, current); } if (error != 0) break; } else { printk(KERN_ERR "reverse_path_check_proc: " "file is not an ep!\n"); } } rcu_read_unlock(); return error; } /** * reverse_path_check - The tfile_check_list is list of file *, which have * links that are proposed to be newly added. We need to * make sure that those added links don't add too many * paths such that we will spend all our time waking up * eventpoll objects. * * Returns: Returns zero if the proposed links don't create too many paths, * -1 otherwise. */ static int reverse_path_check(void) { int error = 0; struct file *current_file; /* let's call this for all tfiles */ list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) { path_count_init(); error = ep_call_nested(&poll_loop_ncalls, reverse_path_check_proc, current_file, current_file, current); if (error) break; } return error; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } /* * Must be called with "mtx" held. */ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, struct file *tfile, int fd, int full_check) { int error, pwake = 0; __poll_t revents; long user_watches; struct epitem *epi; struct ep_pqueue epq; lockdep_assert_irqs_enabled(); user_watches = atomic_long_read(&ep->user->epoll_watches); if (unlikely(user_watches >= max_user_watches)) return -ENOSPC; if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL))) return -ENOMEM; /* Item initialization follow here ... */ INIT_LIST_HEAD(&epi->rdllink); INIT_LIST_HEAD(&epi->fllink); INIT_LIST_HEAD(&epi->pwqlist); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; epi->nwait = 0; epi->next = EP_UNACTIVE_PTR; if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) goto error_create_wakeup_source; } else { RCU_INIT_POINTER(epi->ws, NULL); } /* Add the current item to the list of active epoll hook for this file */ spin_lock(&tfile->f_lock); list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); spin_unlock(&tfile->f_lock); /* * Add the current item to the RB tree. All RB tree operations are * protected by "mtx", and ep_insert() is called with "mtx" held. */ ep_rbtree_insert(ep, epi); /* now check if we've created too many backpaths */ error = -EINVAL; if (full_check && reverse_path_check()) goto error_remove_epi; /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* * We have to check if something went wrong during the poll wait queue * install process. Namely an allocation for a wait queue failed due * high memory pressure. */ error = -ENOMEM; if (epi->nwait < 0) goto error_unregister; /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); atomic_long_inc(&ep->user->epoll_watches); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; error_unregister: ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); spin_unlock(&tfile->f_lock); rb_erase_cached(&epi->rbn, &ep->rbr); /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist * list, since that is used/cleaned only inside a section bound by "mtx". * And ep_insert() is called with "mtx" held. */ write_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); error_create_wakeup_source: kmem_cache_free(epi_cache, epi); return error; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { write_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head, void *priv) { struct ep_send_events_data *esed = priv; __poll_t revents; struct epitem *epi, *tmp; struct epoll_event __user *uevent = esed->events; struct wakeup_source *ws; poll_table pt; init_poll_funcptr(&pt, NULL); esed->res = 0; /* * We can loop without lock because we are passed a task private list. * Items cannot vanish during the loop because ep_scan_ready_list() is * holding "mtx" during this call. */ lockdep_assert_held(&ep->mtx); list_for_each_entry_safe(epi, tmp, head, rdllink) { if (esed->res >= esed->maxevents) break; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws * below). * * This could be rearranged to delay the deactivation of epi->ws * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, ep_scan_ready_list() * is holding ep->mtx, so no operations coming from userspace * can change the item. */ revents = ep_item_poll(epi, &pt, 1); if (!revents) continue; if (__put_user(revents, &uevent->events) || __put_user(epi->event.data, &uevent->data)) { list_add(&epi->rdllink, head); ep_pm_stay_awake(epi); if (!esed->res) esed->res = -EFAULT; return 0; } esed->res++; uevent++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; else if (!(epi->event.events & EPOLLET)) { /* * If this file has been added with Level * Trigger mode, we need to insert back inside * the ready list, so that the next call to * epoll_wait() will check again the events * availability. At this point, no one can insert * into ep->rdllist besides us. The epoll_ctl() * callers are locked out by * ep_scan_ready_list() holding "mtx" and the * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } return 0; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct ep_send_events_data esed; esed.maxevents = maxevents; esed.events = events; ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false); return esed.res; } static inline struct timespec64 ep_set_mstimeout(long ms) { struct timespec64 now, ts = { .tv_sec = ms / MSEC_PER_SEC, .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC), }; ktime_get_ts64(&now); return timespec64_add_safe(now, ts); } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } /** * ep_poll - Retrieves ready events, and delivers them to the caller supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * milliseconds. If the @timeout is zero, the function will not block, * while if the @timeout is less than zero, the function will block * until at least one event has been retrieved (or an error * occurred). * * Returns: Returns the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, long timeout) { int res = 0, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout > 0) { struct timespec64 end_time = ep_set_mstimeout(timeout); slack = select_estimate_accuracy(&end_time); to = &expires; *to = timespec64_to_ktime(end_time); } else if (timeout == 0) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. We still need * lock because we could race and not see an epi being added * to the ready list while in irq callback. Thus incorrectly * returning 0 back to userspace. */ timed_out = 1; write_lock_irq(&ep->lock); eavail = ep_events_available(ep); write_unlock_irq(&ep->lock); goto send_events; } fetch_events: if (!ep_events_available(ep)) ep_busy_loop(ep, timed_out); eavail = ep_events_available(ep); if (eavail) goto send_events; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ ep_reset_busy_poll_napi_id(ep); do { /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; write_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_scan_ready_list() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) { if (signal_pending(current)) res = -EINTR; else __add_wait_queue_exclusive(&ep->wq, &wait); } write_unlock_irq(&ep->lock); if (!eavail && !res) timed_out = !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = 1; } while (0); __set_current_state(TASK_RUNNING); if (!list_empty_careful(&wait.entry)) { write_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, it * means that the thread was woken up after its timeout expired * before it could reacquire the lock. Thus, when wait.entry is * empty, it needs to harvest events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); write_unlock_irq(&ep->lock); } send_events: if (fatal_signal_pending(current)) { /* * Always short-circuit for fatal signals to allow * threads to make a timely exit without the chance of * finding more events available and fetching * repeatedly. */ res = -EINTR; } /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of * more luck. */ if (!res && eavail && !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; return res; } /** * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested() * API, to verify that adding an epoll file inside another * epoll structure, does not violate the constraints, in * terms of closed loops, or too deep chains (which can * result in excessive stack usage). * * @priv: Pointer to the epoll file to be currently checked. * @cookie: Original cookie for this call. This is the top-of-the-chain epoll * data structure pointer. * @call_nests: Current dept of the @ep_call_nested() call stack. * * Returns: Returns zero if adding the epoll @file inside current epoll * structure @ep does not violate the constraints, or -1 otherwise. */ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) { int error = 0; struct file *file = priv; struct eventpoll *ep = file->private_data; struct eventpoll *ep_tovisit; struct rb_node *rbp; struct epitem *epi; mutex_lock_nested(&ep->mtx, call_nests + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit->gen == loop_check_gen) continue; error = ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, epi->ffd.file, ep_tovisit, current); if (error != 0) break; } else { /* * If we've reached a file that is not associated with * an ep, then we need to check if the newly added * links are going to add too many wakeup paths. We do * this by adding it to the tfile_check_list, if it's * not already there, and calling reverse_path_check() * during ep_insert(). */ if (list_empty(&epi->ffd.file->f_tfile_llink)) { if (get_file_rcu(epi->ffd.file)) list_add(&epi->ffd.file->f_tfile_llink, &tfile_check_list); } } } mutex_unlock(&ep->mtx); return error; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@file) * another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ep: Pointer to the epoll private data structure. * @file: Pointer to the epoll file to be checked. * * Returns: Returns zero if adding the epoll @file inside current epoll * structure @ep does not violate the constraints, or -1 otherwise. */ static int ep_loop_check(struct eventpoll *ep, struct file *file) { return ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, file, ep, current); } static void clear_tfile_check_list(void) { struct file *file; /* first clear the tfile_check_list */ while (!list_empty(&tfile_check_list)) { file = list_first_entry(&tfile_check_list, struct file, f_tfile_llink); list_del_init(&file->f_tfile_llink); fput(file); } INIT_LIST_HEAD(&tfile_check_list); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error, fd; struct eventpoll *ep = NULL; struct file *file; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC)); if (fd < 0) { error = fd; goto out_free_ep; } file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC)); if (IS_ERR(file)) { error = PTR_ERR(file); goto out_free_fd; } ep->file = file; fd_install(fd, file); return fd; out_free_fd: put_unused_fd(fd); out_free_ep: ep_free(ep); return error; } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } static inline int epoll_mutex_lock(struct mutex *mutex, int depth, bool nonblock) { if (!nonblock) { mutex_lock_nested(mutex, depth); return 0; } if (mutex_trylock(mutex)) return 0; return -EAGAIN; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { int error; int full_check = 0; struct fd f, tf; struct eventpoll *ep; struct epitem *epi; struct eventpoll *tep = NULL; error = -EBADF; f = fdget(epfd); if (!f.file) goto error_return; /* Get the "struct file *" for the target file */ tf = fdget(fd); if (!tf.file) goto error_fput; /* The target file descriptor must support poll */ error = -EPERM; if (!file_can_poll(tf.file)) goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * We have to check that the file structure underneath the file descriptor * the user passed to us _is_ an eventpoll file. And also we do not permit * adding an epoll file descriptor inside itself. */ error = -EINVAL; if (f.file == tf.file || !is_file_epoll(f.file)) goto error_tgt_fput; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) goto error_tgt_fput; } /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = f.file->private_data; /* * When we insert an epoll file descriptor, inside another epoll file * descriptor, there is the change of creating closed loops, which are * better be handled here, than in more critical paths. While we are * checking for loops we also determine the list of files reachable * and hang them on the tfile_check_list, so we can check that we * haven't created too many possible wakeup paths. * * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when * the epoll file descriptor is attaching directly to a wakeup source, * unless the epoll file descriptor is nested. The purpose of taking the * 'epmutex' on add is to prevent complex toplogies such as loops and * deep wakeup paths from forming in parallel through multiple * EPOLL_CTL_ADD operations. */ error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (!list_empty(&f.file->f_ep_links) || ep->gen == loop_check_gen || is_file_epoll(tf.file)) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epmutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; full_check = 1; if (is_file_epoll(tf.file)) { error = -ELOOP; if (ep_loop_check(ep, tf.file) != 0) goto error_tgt_fput; } else { get_file(tf.file); list_add(&tf.file->f_tfile_llink, &tfile_check_list); } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; if (is_file_epoll(tf.file)) { tep = tf.file->private_data; error = epoll_mutex_lock(&tep->mtx, 1, nonblock); if (error) { mutex_unlock(&ep->mtx); goto error_tgt_fput; } } } } /* * Try to lookup the file inside our RB tree, Since we grabbed "mtx" * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ epi = ep_find(ep, tf.file, fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(ep, epds, tf.file, fd, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) error = ep_remove(ep, epi); else error = -ENOENT; break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } if (tep != NULL) mutex_unlock(&tep->mtx); mutex_unlock(&ep->mtx); error_tgt_fput: if (full_check) { clear_tfile_check_list(); loop_check_gen++; mutex_unlock(&epmutex); } fdput(tf); error_fput: fdput(f); error_return: return error; } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, int timeout) { int error; struct fd f; struct eventpoll *ep; /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(events, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* Get the "struct file *" for the eventpoll file */ f = fdget(epfd); if (!f.file) return -EBADF; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ error = -EINVAL; if (!is_file_epoll(f.file)) goto error_fput; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = f.file->private_data; /* Time to fish for events ... */ error = ep_poll(ep, events, maxevents, timeout); error_fput: fdput(f); return error; } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { return do_epoll_wait(epfd, events, maxevents, timeout); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(error == -EINTR); return error; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * Initialize the structure used to perform epoll file descriptor * inclusion loops checks. */ ep_nested_calls_init(&poll_loop_ncalls); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/dcache.h> #include <linux/fs.h> #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/srcu.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" /* * Clear all of the marks on an inode when it is being evicted from core */ void __fsnotify_inode_delete(struct inode *inode) { fsnotify_clear_marks_by_inode(inode); } EXPORT_SYMBOL_GPL(__fsnotify_inode_delete); void __fsnotify_vfsmount_delete(struct vfsmount *mnt) { fsnotify_clear_marks_by_mount(mnt); } /** * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @sb: superblock being unmounted. * * Called during unmount with no locks held, so needs to be safe against * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block. */ static void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We cannot __iget() an inode in state I_FREEING, * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); continue; } /* * If i_count is zero, the inode cannot have any watches and * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. * However, we should have been called /after/ evict_inodes * removed all zero refcount inodes, in any case. Test to * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); /* for each watch, send FS_UNMOUNT and then remove it */ fsnotify_inode(inode, FS_UNMOUNT); fsnotify_inode_delete(inode); iput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); } void fsnotify_sb_delete(struct super_block *sb) { fsnotify_unmount_inodes(sb); fsnotify_clear_marks_by_sb(sb); /* Wait for outstanding object references from connectors */ wait_var_event(&sb->s_fsnotify_connectors, !atomic_long_read(&sb->s_fsnotify_connectors)); } /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void fsnotify_set_children_dentry_flags(struct inode *inode) { struct dentry *alias; if (!S_ISDIR(inode->i_mode)) return; spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } /* * Lazily clear false positive PARENT_WATCHED flag for child whose parent had * stopped watching children. */ static void fsnotify_clear_child_dentry_flag(struct inode *pinode, struct dentry *dentry) { spin_lock(&dentry->d_lock); /* * d_lock is a sufficient barrier to prevent observing a non-watched * parent state from before the fsnotify_set_children_dentry_flags() * or fsnotify_update_flags() call that had set PARENT_WATCHED. */ if (!fsnotify_inode_watches_children(pinode)) dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&dentry->d_lock); } /* Are inode/sb/mount interested in parent and name info with this event? */ static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt, __u32 mask) { __u32 marks_mask = 0; /* We only send parent/name to inode/sb/mount for events on non-dir */ if (mask & FS_ISDIR) return false; /* * All events that are possible on child can also may be reported with * parent/name info to inode/sb/mount. Otherwise, a watching parent * could result in events reported with unexpected name info to sb/mount. */ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask); marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask); if (mnt) marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask); /* Did they subscribe for this event with parent/name info? */ return mask & marks_mask; } /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with * parent and name info. * * Notify only the child without name info if parent is not watching and * inode/sb/mount are not interested in events with parent and name info. */ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); struct mount *mnt = path ? real_mount(path->mnt) : NULL; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; struct qstr *file_name = NULL; int ret = 0; /* * Do inode/sb/mount care about parent and name info on non-dir? * Do they care about any event at all? */ if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched) return 0; parent = NULL; parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ parent = dget_parent(dentry); p_inode = parent->d_inode; p_mask = fsnotify_inode_watches_children(p_inode); if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry); /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. * The parent interest in ACCESS/MODIFY events does not apply to special * files, where read/write are not on the filesystem of the parent and * events can provide an undesirable side-channel for information * exfiltration. */ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS && !(data_type == FSNOTIFY_EVENT_PATH && d_is_special(dentry) && (mask & (FS_ACCESS | FS_MODIFY))); if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; if (parent_interested) mask |= FS_EVENT_ON_CHILD; } notify: ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0); if (file_name) release_dentry_name_snapshot(&name); dput(parent); return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); static int fsnotify_handle_inode_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct inode *inode = fsnotify_data_inode(data, data_type); const struct fsnotify_ops *ops = group->ops; if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; if (WARN_ON_ONCE(!inode && !dir)) return 0; if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; /* Check interest of this mark in case event was sent with two marks */ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS)) return 0; return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie); } static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info); int ret; if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) || WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; /* * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. * The only ->handle_inode_event() backend that supports FS_RENAME is * dnotify, where it means file was renamed within same parent. */ if (mask & FS_RENAME) { struct dentry *moved = fsnotify_data_dentry(data, data_type); if (dir != moved->d_parent->d_inode) return 0; } if (parent_mark) { ret = fsnotify_handle_inode_event(group, parent_mark, mask, data, data_type, dir, name, 0); if (ret) return ret; } if (!inode_mark) return 0; /* * Some events can be sent on both parent dir and child marks (e.g. * FS_ATTRIB). If both parent dir and child are watching, report the * event once to parent dir with name (if interested) and once to child * without name (if interested). * * In any case regardless whether the parent is watching or not, the * child watcher is expecting an event without the FS_EVENT_ON_CHILD * flag. The file name is expected if and only if this is a directory * event. */ mask &= ~FS_EVENT_ON_CHILD; if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) { dir = NULL; name = NULL; } return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type, dir, name, cookie); } static int send_to_group(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignore_mask = 0; bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { fsnotify_foreach_iter_mark_type(iter_info, mark, type) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mark->ignore_mask = 0; } } /* Are any of the group marks interested in this event? */ fsnotify_foreach_iter_mark_type(iter_info, mark, type) { group = mark->group; marks_mask |= mark->mask; marks_ignore_mask |= fsnotify_effective_ignore_mask(mark, is_dir, type); } pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { return group->ops->handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } return fsnotify_handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (conn) node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; if (mark) node = srcu_dereference(mark->obj_list.next, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } /* * iter_info is a multi head priority queue of marks. * Pick a subset of marks from queue heads, all with the same group * and set the report_mask to a subset of the selected marks. * Returns false if there are no more groups to iterate. */ static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; struct fsnotify_mark *mark; int type; /* Choose max prio group among groups of all queue heads */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) max_prio_group = mark->group; } if (!max_prio_group) return false; /* Set the report mask for marks from same group as max prio group */ iter_info->current_group = max_prio_group; iter_info->report_mask = 0; fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) { /* * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode * is watching children and interested in this event, * which is an event possible on child. * But is *this mark* watching children? */ if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD) && !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) continue; fsnotify_iter_set_report_type(iter_info, type); } } return true; } /* * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *mark; int type; /* * We cannot use fsnotify_foreach_iter_mark_type() here because we * may need to advance a mark of type X that belongs to current_group * but was not selected for reporting. */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } } /* * fsnotify - This is the main call to fsnotify. * * The VFS calls into hook specific functions in linux/fsnotify.h. * Those functions then in turn call here. Here will call out to all of the * registered fsnotify_group. Those groups can then use the notification event * in whatever means they feel necessary. * * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - * If @dir and @inode are both non-NULL, event may be * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; __u32 test_mask, marks_mask; if (path) mnt = real_mount(path->mnt); if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ if (mask & FS_RENAME) { moved = fsnotify_data_dentry(data, data_type); inode2 = moved->d_parent->d_inode; inode2_type = FSNOTIFY_ITER_TYPE_INODE2; } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ inode2 = dir; inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. * However, if we do not walk the lists, we do not have to do * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ if (!sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && (!inode2 || !inode2->i_fsnotify_marks)) return 0; marks_mask = sb->s_fsnotify_mask; if (mnt) marks_mask |= mnt->mnt_fsnotify_mask; if (inode) marks_mask |= inode->i_fsnotify_mask; if (inode2) marks_mask |= inode2->i_fsnotify_mask; /* * If this is a modify event we may need to clear some ignore masks. * In that case, the object with ignore masks will have the FS_MODIFY * event in its mask. * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sb->s_fsnotify_marks); if (mnt) { iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (inode2) { iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark * ignore masks are properly reflected for mount/sb mark notifications. * That's why this traversal is so complicated... */ while (fsnotify_iter_select_report_types(&iter_info)) { ret = send_to_group(mask, data, data_type, dir, file_name, cookie, &iter_info); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; fsnotify_iter_next(&iter_info); } ret = 0; out: srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx); return ret; } EXPORT_SYMBOL_GPL(fsnotify); static __init int fsnotify_init(void) { int ret; BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) panic("initializing fsnotify_mark_srcu"); fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector, SLAB_PANIC); return 0; } core_initcall(fsnotify_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> #include <linux/gfp.h> #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key); #define percpu_counter_init(fbc, value, gfp) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init(fbc, value, gfp, &__key); \ }) void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { fbc->count = amount; return 0; } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { preempt_disable(); fbc->count += amount; preempt_enable(); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } static inline void percpu_counter_sync(struct percpu_counter *fbc) { } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | // SPDX-License-Identifier: GPL-2.0-or-later /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/minmax.h> #if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ !defined(find_next_and_bit) /* * This is a common helper function for find_next_bit, find_next_zero_bit, and * find_next_and_bit. The differences are: * - The "invert" argument, which is XORed with each fetched word before * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ static unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { unsigned long tmp, mask; if (unlikely(start >= nbits)) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; /* Handle 1st word. */ mask = BITMAP_FIRST_WORD_MASK(start); if (le) mask = swab(mask); tmp &= mask; start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; } if (le) tmp = swab(tmp); return min(start + __ffs(tmp), nbits); } #endif #ifndef find_next_bit /* * Find the next set bit in a memory region. */ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_bit); #endif #ifndef find_next_zero_bit unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } EXPORT_SYMBOL(find_next_zero_bit); #endif #if !defined(find_next_and_bit) unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_and_bit); #endif #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx]) return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx] != ~0UL) return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_zero_bit); #endif #ifndef find_last_bit unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(find_last_bit); #endif #ifdef __BIG_ENDIAN #ifndef find_next_zero_bit_le unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif #ifndef find_next_bit_le unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 1); } EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { offset = find_next_bit(addr, size, offset); if (offset == size) return size; offset = round_down(offset, 8); *clump = bitmap_get_value8(addr, offset); return offset; } EXPORT_SYMBOL(find_next_clump8); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 | // SPDX-License-Identifier: GPL-2.0 /* * gendisk handling */ #include <linux/module.h> #include <linux/ctype.h> #include <linux/fs.h> #include <linux/genhd.h> #include <linux/kdev_t.h> #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/kobj_map.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/log2.h> #include <linux/pm_runtime.h> #include <linux/badblocks.h> #include "blk.h" static DEFINE_MUTEX(block_class_lock); static struct kobject *block_depr; /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) /* For extended devt allocation. ext_devt_lock prevents look up * results from going away underneath its user. */ static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr); static void disk_alloc_events(struct gendisk *disk); static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); /* * Set disk capacity and notify if the size is not currently zero and will not * be set to zero. Returns true if a uevent was sent, otherwise false. */ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) { sector_t capacity = get_capacity(disk); set_capacity(disk, size); revalidate_disk_size(disk, true); if (capacity != size && capacity != 0 && size != 0) { char *envp[] = { "RESIZE=1", NULL }; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); return true; } return false; } EXPORT_SYMBOL_GPL(set_capacity_and_notify); /* * Format the device name of the indicated disk into the supplied buffer and * return a pointer to that same buffer for convenience. */ char *disk_name(struct gendisk *hd, int partno, char *buf) { if (!partno) snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name); else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno); else snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno); return buf; } const char *bdevname(struct block_device *bdev, char *buf) { return disk_name(bdev->bd_disk, bdev->bd_partno, buf); } EXPORT_SYMBOL(bdevname); static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) { int cpu; memset(stat, 0, sizeof(struct disk_stats)); for_each_possible_cpu(cpu) { struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu); int group; for (group = 0; group < NR_STAT_GROUPS; group++) { stat->nsecs[group] += ptr->nsecs[group]; stat->sectors[group] += ptr->sectors[group]; stat->ios[group] += ptr->ios[group]; stat->merges[group] += ptr->merges[group]; } stat->io_ticks += ptr->io_ticks; } } static unsigned int part_in_flight(struct hd_struct *part) { unsigned int inflight = 0; int cpu; for_each_possible_cpu(cpu) { inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) + part_stat_local_read_cpu(part, in_flight[1], cpu); } if ((int)inflight < 0) inflight = 0; return inflight; } static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) { int cpu; inflight[0] = 0; inflight[1] = 0; for_each_possible_cpu(cpu) { inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu); inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu); } if ((int)inflight[0] < 0) inflight[0] = 0; if ((int)inflight[1] < 0) inflight[1] = 0; } struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl); if (unlikely(partno < 0 || partno >= ptbl->len)) return NULL; return rcu_dereference(ptbl->part[partno]); } /** * disk_get_part - get partition * @disk: disk to look partition from * @partno: partition number * * Look for partition @partno from @disk. If found, increment * reference count and return it. * * CONTEXT: * Don't care. * * RETURNS: * Pointer to the found partition on success, NULL if not found. */ struct hd_struct *disk_get_part(struct gendisk *disk, int partno) { struct hd_struct *part; rcu_read_lock(); part = __disk_get_part(disk, partno); if (part) get_device(part_to_dev(part)); rcu_read_unlock(); return part; } /** * disk_part_iter_init - initialize partition iterator * @piter: iterator to initialize * @disk: disk to iterate over * @flags: DISK_PITER_* flags * * Initialize @piter so that it iterates over partitions of @disk. * * CONTEXT: * Don't care. */ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk, unsigned int flags) { struct disk_part_tbl *ptbl; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); piter->disk = disk; piter->part = NULL; if (flags & DISK_PITER_REVERSE) piter->idx = ptbl->len - 1; else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) piter->idx = 0; else piter->idx = 1; piter->flags = flags; rcu_read_unlock(); } EXPORT_SYMBOL_GPL(disk_part_iter_init); /** * disk_part_iter_next - proceed iterator to the next partition and return it * @piter: iterator of interest * * Proceed @piter to the next partition and return it. * * CONTEXT: * Don't care. */ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) { struct disk_part_tbl *ptbl; int inc, end; /* put the last partition */ disk_put_part(piter->part); piter->part = NULL; /* get part_tbl */ rcu_read_lock(); ptbl = rcu_dereference(piter->disk->part_tbl); /* determine iteration parameters */ if (piter->flags & DISK_PITER_REVERSE) { inc = -1; if (piter->flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) end = -1; else end = 0; } else { inc = 1; end = ptbl->len; } /* iterate to the next partition */ for (; piter->idx != end; piter->idx += inc) { struct hd_struct *part; part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; get_device(part_to_dev(part)); piter->part = part; if (!part_nr_sects_read(part) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) { put_device(part_to_dev(part)); piter->part = NULL; continue; } piter->idx += inc; break; } rcu_read_unlock(); return piter->part; } EXPORT_SYMBOL_GPL(disk_part_iter_next); /** * disk_part_iter_exit - finish up partition iteration * @piter: iter of interest * * Called when iteration is over. Cleans up @piter. * * CONTEXT: * Don't care. */ void disk_part_iter_exit(struct disk_part_iter *piter) { disk_put_part(piter->part); piter->part = NULL; } EXPORT_SYMBOL_GPL(disk_part_iter_exit); static inline int sector_in_part(struct hd_struct *part, sector_t sector) { return part->start_sect <= sector && sector < part->start_sect + part_nr_sects_read(part); } /** * disk_map_sector_rcu - map sector to partition * @disk: gendisk of interest * @sector: sector to map * * Find out which partition @sector maps to on @disk. This is * primarily used for stats accounting. * * CONTEXT: * RCU read locked. The returned partition pointer is always valid * because its refcount is grabbed except for part0, which lifetime * is same with the disk. * * RETURNS: * Found partition on success, part0 is returned if no partition matches * or the matched partition is being deleted. */ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { struct disk_part_tbl *ptbl; struct hd_struct *part; int i; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); part = rcu_dereference(ptbl->last_lookup); if (part && sector_in_part(part, sector) && hd_struct_try_get(part)) goto out_unlock; for (i = 1; i < ptbl->len; i++) { part = rcu_dereference(ptbl->part[i]); if (part && sector_in_part(part, sector)) { /* * only live partition can be cached for lookup, * so use-after-free on cached & deleting partition * can be avoided */ if (!hd_struct_try_get(part)) break; rcu_assign_pointer(ptbl->last_lookup, part); goto out_unlock; } } part = &disk->part0; out_unlock: rcu_read_unlock(); return part; } /** * disk_has_partitions * @disk: gendisk of interest * * Walk through the partition table and check if valid partition exists. * * CONTEXT: * Don't care. * * RETURNS: * True if the gendisk has at least one valid non-zero size partition. * Otherwise false. */ bool disk_has_partitions(struct gendisk *disk) { struct disk_part_tbl *ptbl; int i; bool ret = false; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); /* Iterate partitions skipping the whole device at index 0 */ for (i = 1; i < ptbl->len; i++) { if (rcu_dereference(ptbl->part[i])) { ret = true; break; } } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(disk_has_partitions); /* * Can be deleted altogether. Later. * */ #define BLKDEV_MAJOR_HASH_SIZE 255 static struct blk_major_name { struct blk_major_name *next; int major; char name[16]; } *major_names[BLKDEV_MAJOR_HASH_SIZE]; /* index in the above - for now: assume no multimajor ranges */ static inline int major_to_index(unsigned major) { return major % BLKDEV_MAJOR_HASH_SIZE; } #ifdef CONFIG_PROC_FS void blkdev_show(struct seq_file *seqf, off_t offset) { struct blk_major_name *dp; mutex_lock(&block_class_lock); for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); mutex_unlock(&block_class_lock); } #endif /* CONFIG_PROC_FS */ /** * register_blkdev - register a new block device * * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If * @major = 0, try to allocate any unused major number. * @name: the name of the new block device as a zero terminated string * * The @name must be unique within the system. * * The return value depends on the @major input parameter: * * - if a major device number was requested in range [1..BLKDEV_MAJOR_MAX-1] * then the function returns zero on success, or a negative error code * - if any unused major number was requested with @major = 0 parameter * then the return value is the allocated major number in range * [1..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise * * See Documentation/admin-guide/devices.txt for the list of allocated * major numbers. */ int register_blkdev(unsigned int major, const char *name) { struct blk_major_name **n, *p; int index, ret = 0; mutex_lock(&block_class_lock); /* temporary */ if (major == 0) { for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) { if (major_names[index] == NULL) break; } if (index == 0) { printk("%s: failed to get major for %s\n", __func__, name); ret = -EBUSY; goto out; } major = index; ret = major; } if (major >= BLKDEV_MAJOR_MAX) { pr_err("%s: major requested (%u) is greater than the maximum (%u) for %s\n", __func__, major, BLKDEV_MAJOR_MAX-1, name); ret = -EINVAL; goto out; } p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL); if (p == NULL) { ret = -ENOMEM; goto out; } p->major = major; strlcpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); for (n = &major_names[index]; *n; n = &(*n)->next) { if ((*n)->major == major) break; } if (!*n) *n = p; else ret = -EBUSY; if (ret < 0) { printk("register_blkdev: cannot get major %u for %s\n", major, name); kfree(p); } out: mutex_unlock(&block_class_lock); return ret; } EXPORT_SYMBOL(register_blkdev); void unregister_blkdev(unsigned int major, const char *name) { struct blk_major_name **n; struct blk_major_name *p = NULL; int index = major_to_index(major); mutex_lock(&block_class_lock); for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; if (!*n || strcmp((*n)->name, name)) { WARN_ON(1); } else { p = *n; *n = p->next; } mutex_unlock(&block_class_lock); kfree(p); } EXPORT_SYMBOL(unregister_blkdev); static struct kobj_map *bdev_map; /** * blk_mangle_minor - scatter minor numbers apart * @minor: minor number to mangle * * Scatter consecutively allocated @minor number apart if MANGLE_DEVT * is enabled. Mangling twice gives the original value. * * RETURNS: * Mangled value. * * CONTEXT: * Don't care. */ static int blk_mangle_minor(int minor) { #ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT int i; for (i = 0; i < MINORBITS / 2; i++) { int low = minor & (1 << i); int high = minor & (1 << (MINORBITS - 1 - i)); int distance = MINORBITS - 1 - 2 * i; minor ^= low | high; /* clear both bits */ low <<= distance; /* swap the positions */ high >>= distance; minor |= low | high; /* and set */ } #endif return minor; } /** * blk_alloc_devt - allocate a dev_t for a partition * @part: partition to allocate dev_t for * @devt: out parameter for resulting dev_t * * Allocate a dev_t for block device. * * RETURNS: * 0 on success, allocated dev_t is returned in *@devt. -errno on * failure. * * CONTEXT: * Might sleep. */ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) { struct gendisk *disk = part_to_disk(part); int idx; /* in consecutive minor range? */ if (part->partno < disk->minors) { *devt = MKDEV(disk->major, disk->first_minor + part->partno); return 0; } /* allocate ext devt */ idr_preload(GFP_KERNEL); spin_lock_bh(&ext_devt_lock); idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT); spin_unlock_bh(&ext_devt_lock); idr_preload_end(); if (idx < 0) return idx == -ENOSPC ? -EBUSY : idx; *devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); return 0; } /** * blk_free_devt - free a dev_t * @devt: dev_t to free * * Free @devt which was allocated using blk_alloc_devt(). * * CONTEXT: * Might sleep. */ void blk_free_devt(dev_t devt) { if (devt == MKDEV(0, 0)) return; if (MAJOR(devt) == BLOCK_EXT_MAJOR) { spin_lock_bh(&ext_devt_lock); idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); spin_unlock_bh(&ext_devt_lock); } } /* * We invalidate devt by assigning NULL pointer for devt in idr. */ void blk_invalidate_devt(dev_t devt) { if (MAJOR(devt) == BLOCK_EXT_MAJOR) { spin_lock_bh(&ext_devt_lock); idr_replace(&ext_devt_idr, NULL, blk_mangle_minor(MINOR(devt))); spin_unlock_bh(&ext_devt_lock); } } static char *bdevt_str(dev_t devt, char *buf) { if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { char tbuf[BDEVT_SIZE]; snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); } else snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); return buf; } /* * Register device numbers dev..(dev+range-1) * range must be nonzero * The hash chain is sorted on range, so that subranges can override. */ void blk_register_region(dev_t devt, unsigned long range, struct module *module, struct kobject *(*probe)(dev_t, int *, void *), int (*lock)(dev_t, void *), void *data) { kobj_map(bdev_map, devt, range, module, probe, lock, data); } EXPORT_SYMBOL(blk_register_region); void blk_unregister_region(dev_t devt, unsigned long range) { kobj_unmap(bdev_map, devt, range); } EXPORT_SYMBOL(blk_unregister_region); static struct kobject *exact_match(dev_t devt, int *partno, void *data) { struct gendisk *p = data; return &disk_to_dev(p)->kobj; } static int exact_lock(dev_t devt, void *data) { struct gendisk *p = data; if (!get_disk_and_module(p)) return -1; return 0; } static void disk_scan_partitions(struct gendisk *disk) { struct block_device *bdev; if (!get_capacity(disk) || !disk_part_scan_enabled(disk)) return; set_bit(GD_NEED_PART_SCAN, &disk->state); bdev = blkdev_get_by_dev(disk_devt(disk), FMODE_READ, NULL); if (!IS_ERR(bdev)) blkdev_put(bdev, FMODE_READ); } static void register_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups) { struct device *ddev = disk_to_dev(disk); struct disk_part_iter piter; struct hd_struct *part; int err; ddev->parent = parent; dev_set_name(ddev, "%s", disk->disk_name); /* delay uevents, until we scanned partition table */ dev_set_uevent_suppress(ddev, 1); if (groups) { WARN_ON(ddev->groups); ddev->groups = groups; } if (device_add(ddev)) return; if (!sysfs_deprecated) { err = sysfs_create_link(block_depr, &ddev->kobj, kobject_name(&ddev->kobj)); if (err) { device_del(ddev); return; } } /* * avoid probable deadlock caused by allocating memory with * GFP_KERNEL in runtime_resume callback of its all ancestor * devices */ pm_runtime_set_memalloc_noio(ddev, true); disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); if (disk->flags & GENHD_FL_HIDDEN) return; disk_scan_partitions(disk); /* announce disk after possible partitions are created */ dev_set_uevent_suppress(ddev, 0); kobject_uevent(&ddev->kobj, KOBJ_ADD); /* announce possible partitions */ disk_part_iter_init(&piter, disk, 0); while ((part = disk_part_iter_next(&piter))) kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD); disk_part_iter_exit(&piter); if (disk->queue->backing_dev_info->dev) { err = sysfs_create_link(&ddev->kobj, &disk->queue->backing_dev_info->dev->kobj, "bdi"); WARN_ON(err); } } /** * __device_add_disk - add disk information to kernel list * @parent: parent device for the disk * @disk: per-device partitioning information * @groups: Additional per-device sysfs groups * @register_queue: register the queue if set to true * * This function registers the partitioning information in @disk * with the kernel. * * FIXME: error handling */ static void __device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, bool register_queue) { dev_t devt; int retval; /* * The disk queue should now be all set with enough information about * the device for the elevator code to pick an adequate default * elevator if one is needed, that is, for devices requesting queue * registration. */ if (register_queue) elevator_init_mq(disk->queue); /* minors == 0 indicates to use ext devt from part0 and should * be accompanied with EXT_DEVT flag. Make sure all * parameters make sense. */ WARN_ON(disk->minors && !(disk->major || disk->first_minor)); WARN_ON(!disk->minors && !(disk->flags & (GENHD_FL_EXT_DEVT | GENHD_FL_HIDDEN))); disk->flags |= GENHD_FL_UP; retval = blk_alloc_devt(&disk->part0, &devt); if (retval) { WARN_ON(1); return; } disk->major = MAJOR(devt); disk->first_minor = MINOR(devt); disk_alloc_events(disk); if (disk->flags & GENHD_FL_HIDDEN) { /* * Don't let hidden disks show up in /proc/partitions, * and don't bother scanning for partitions either. */ disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; disk->flags |= GENHD_FL_NO_PART_SCAN; } else { struct backing_dev_info *bdi = disk->queue->backing_dev_info; struct device *dev = disk_to_dev(disk); int ret; /* Register BDI before referencing it from bdev */ dev->devt = devt; ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); WARN_ON(ret); bdi_set_owner(bdi, dev); blk_register_region(disk_devt(disk), disk->minors, NULL, exact_match, exact_lock, disk); } register_disk(parent, disk, groups); if (register_queue) blk_register_queue(disk); /* * Take an extra ref on queue which will be put on disk_release() * so that it sticks around as long as @disk is there. */ WARN_ON_ONCE(!blk_get_queue(disk->queue)); disk_add_events(disk); blk_integrity_add(disk); } void device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups) { __device_add_disk(parent, disk, groups, true); } EXPORT_SYMBOL(device_add_disk); void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk) { __device_add_disk(parent, disk, NULL, false); } EXPORT_SYMBOL(device_add_disk_no_queue_reg); static void invalidate_partition(struct gendisk *disk, int partno) { struct block_device *bdev; bdev = bdget_disk(disk, partno); if (!bdev) return; fsync_bdev(bdev); __invalidate_device(bdev, true); /* * Unhash the bdev inode for this device so that it gets evicted as soon * as last inode reference is dropped. */ remove_inode_hash(bdev->bd_inode); bdput(bdev); } /** * del_gendisk - remove the gendisk * @disk: the struct gendisk to remove * * Removes the gendisk and all its associated resources. This deletes the * partitions associated with the gendisk, and unregisters the associated * request_queue. * * This is the counter to the respective __device_add_disk() call. * * The final removal of the struct gendisk happens when its refcount reaches 0 * with put_disk(), which should be called after del_gendisk(), if * __device_add_disk() was used. * * Drivers exist which depend on the release of the gendisk to be synchronous, * it should not be deferred. * * Context: can sleep */ void del_gendisk(struct gendisk *disk) { struct disk_part_iter piter; struct hd_struct *part; might_sleep(); blk_integrity_del(disk); disk_del_events(disk); /* * Block lookups of the disk until all bdevs are unhashed and the * disk is marked as dead (GENHD_FL_UP cleared). */ down_write(&disk->lookup_sem); /* invalidate stuff */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE); while ((part = disk_part_iter_next(&piter))) { invalidate_partition(disk, part->partno); delete_partition(part); } disk_part_iter_exit(&piter); invalidate_partition(disk, 0); set_capacity(disk, 0); disk->flags &= ~GENHD_FL_UP; up_write(&disk->lookup_sem); if (!(disk->flags & GENHD_FL_HIDDEN)) sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); if (disk->queue) { /* * Unregister bdi before releasing device numbers (as they can * get reused and we'd get clashes in sysfs). */ if (!(disk->flags & GENHD_FL_HIDDEN)) bdi_unregister(disk->queue->backing_dev_info); blk_unregister_queue(disk); } else { WARN_ON(1); } if (!(disk->flags & GENHD_FL_HIDDEN)) blk_unregister_region(disk_devt(disk), disk->minors); /* * Remove gendisk pointer from idr so that it cannot be looked up * while RCU period before freeing gendisk is running to prevent * use-after-free issues. Note that the device number stays * "in-use" until we really free the gendisk. */ blk_invalidate_devt(disk_devt(disk)); kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); part_stat_set_all(&disk->part0, 0); disk->part0.stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); } EXPORT_SYMBOL(del_gendisk); /* sysfs access to bad-blocks list. */ static ssize_t disk_badblocks_show(struct device *dev, struct device_attribute *attr, char *page) { struct gendisk *disk = dev_to_disk(dev); if (!disk->bb) return sprintf(page, "\n"); return badblocks_show(disk->bb, page, 0); } static ssize_t disk_badblocks_store(struct device *dev, struct device_attribute *attr, const char *page, size_t len) { struct gendisk *disk = dev_to_disk(dev); if (!disk->bb) return -ENXIO; return badblocks_store(disk->bb, page, len, 0); } /** * get_gendisk - get partitioning information for a given device * @devt: device to get partitioning information for * @partno: returned partition index * * This function gets the structure containing partitioning * information for the given device @devt. * * Context: can sleep */ struct gendisk *get_gendisk(dev_t devt, int *partno) { struct gendisk *disk = NULL; might_sleep(); if (MAJOR(devt) != BLOCK_EXT_MAJOR) { struct kobject *kobj; kobj = kobj_lookup(bdev_map, devt, partno); if (kobj) disk = dev_to_disk(kobj_to_dev(kobj)); } else { struct hd_struct *part; spin_lock_bh(&ext_devt_lock); part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); if (part && get_disk_and_module(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } spin_unlock_bh(&ext_devt_lock); } if (!disk) return NULL; /* * Synchronize with del_gendisk() to not return disk that is being * destroyed. */ down_read(&disk->lookup_sem); if (unlikely((disk->flags & GENHD_FL_HIDDEN) || !(disk->flags & GENHD_FL_UP))) { up_read(&disk->lookup_sem); put_disk_and_module(disk); disk = NULL; } else { up_read(&disk->lookup_sem); } return disk; } /** * bdget_disk - do bdget() by gendisk and partition number * @disk: gendisk of interest * @partno: partition number * * Find partition @partno from @disk, do bdget() on it. * * CONTEXT: * Don't care. * * RETURNS: * Resulting block_device on success, NULL on failure. */ struct block_device *bdget_disk(struct gendisk *disk, int partno) { struct hd_struct *part; struct block_device *bdev = NULL; part = disk_get_part(disk, partno); if (part) bdev = bdget_part(part); disk_put_part(part); return bdev; } EXPORT_SYMBOL(bdget_disk); /* * print a full list of all partitions - intended for places where the root * filesystem can't be mounted and thus to give the victim some idea of what * went wrong */ void __init printk_all_partitions(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); struct disk_part_iter piter; struct hd_struct *part; char name_buf[BDEVNAME_SIZE]; char devt_buf[BDEVT_SIZE]; /* * Don't show empty devices or things that have been * suppressed */ if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)) continue; /* * Note, unlike /proc/partitions, I am showing the * numbers in hex - the same format as the root= * option takes. */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) { bool is_part0 = part == &disk->part0; printk("%s%s %10llu %s %s", is_part0 ? "" : " ", bdevt_str(part_devt(part), devt_buf), (unsigned long long)part_nr_sects_read(part) >> 1 , disk_name(disk, part->partno, name_buf), part->info ? part->info->uuid : ""); if (is_part0) { if (dev->parent && dev->parent->driver) printk(" driver: %s\n", dev->parent->driver->name); else printk(" (driver?)\n"); } else printk("\n"); } disk_part_iter_exit(&piter); } class_dev_iter_exit(&iter); } #ifdef CONFIG_PROC_FS /* iterator */ static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos) { loff_t skip = *pos; struct class_dev_iter *iter; struct device *dev; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return ERR_PTR(-ENOMEM); seqf->private = iter; class_dev_iter_init(iter, &block_class, NULL, &disk_type); do { dev = class_dev_iter_next(iter); if (!dev) return NULL; } while (skip--); return dev_to_disk(dev); } static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos) { struct device *dev; (*pos)++; dev = class_dev_iter_next(seqf->private); if (dev) return dev_to_disk(dev); return NULL; } static void disk_seqf_stop(struct seq_file *seqf, void *v) { struct class_dev_iter *iter = seqf->private; /* stop is called even after start failed :-( */ if (iter) { class_dev_iter_exit(iter); kfree(iter); seqf->private = NULL; } } static void *show_partition_start(struct seq_file *seqf, loff_t *pos) { void *p; p = disk_seqf_start(seqf, pos); if (!IS_ERR_OR_NULL(p) && !*pos) seq_puts(seqf, "major minor #blocks name\n\n"); return p; } static int show_partition(struct seq_file *seqf, void *v) { struct gendisk *sgp = v; struct disk_part_iter piter; struct hd_struct *part; char buf[BDEVNAME_SIZE]; /* Don't show non-partitionable removeable devices or empty devices */ if (!get_capacity(sgp) || (!disk_max_parts(sgp) && (sgp->flags & GENHD_FL_REMOVABLE))) return 0; if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) return 0; /* show the full disk and all non-0 size partitions of it */ disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) seq_printf(seqf, "%4d %7d %10llu %s\n", MAJOR(part_devt(part)), MINOR(part_devt(part)), (unsigned long long)part_nr_sects_read(part) >> 1, disk_name(sgp, part->partno, buf)); disk_part_iter_exit(&piter); return 0; } static const struct seq_operations partitions_op = { .start = show_partition_start, .next = disk_seqf_next, .stop = disk_seqf_stop, .show = show_partition }; #endif static struct kobject *base_probe(dev_t devt, int *partno, void *data) { if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0) /* Make old-style 2.4 aliases work */ request_module("block-major-%d", MAJOR(devt)); return NULL; } static int __init genhd_device_init(void) { int error; block_class.dev_kobj = sysfs_dev_block_kobj; error = class_register(&block_class); if (unlikely(error)) return error; bdev_map = kobj_map_init(base_probe, &block_class_lock); blk_dev_init(); register_blkdev(BLOCK_EXT_MAJOR, "blkext"); /* create top-level block dir */ if (!sysfs_deprecated) block_depr = kobject_create_and_add("block", NULL); return 0; } subsys_initcall(genhd_device_init); static ssize_t disk_range_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", disk->minors); } static ssize_t disk_ext_range_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", disk_max_parts(disk)); } static ssize_t disk_removable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0)); } static ssize_t disk_hidden_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", (disk->flags & GENHD_FL_HIDDEN ? 1 : 0)); } static ssize_t disk_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0); } ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); return sprintf(buf, "%llu\n", (unsigned long long)part_nr_sects_read(p)); } ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); struct request_queue *q = part_to_disk(p)->queue; struct disk_stats stat; unsigned int inflight; part_stat_read_all(p, &stat); if (queue_is_mq(q)) inflight = blk_mq_in_flight(q, p); else inflight = part_in_flight(p); return sprintf(buf, "%8lu %8lu %8llu %8u " "%8lu %8lu %8llu %8u " "%8u %8u %8u " "%8lu %8lu %8llu %8u " "%8lu %8u" "\n", stat.ios[STAT_READ], stat.merges[STAT_READ], (unsigned long long)stat.sectors[STAT_READ], (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC), stat.ios[STAT_WRITE], stat.merges[STAT_WRITE], (unsigned long long)stat.sectors[STAT_WRITE], (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC), inflight, jiffies_to_msecs(stat.io_ticks), (unsigned int)div_u64(stat.nsecs[STAT_READ] + stat.nsecs[STAT_WRITE] + stat.nsecs[STAT_DISCARD] + stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC), stat.ios[STAT_DISCARD], stat.merges[STAT_DISCARD], (unsigned long long)stat.sectors[STAT_DISCARD], (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC), stat.ios[STAT_FLUSH], (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; if (queue_is_mq(q)) blk_mq_in_flight_rw(q, p, inflight); else part_in_flight_rw(p, inflight); return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } static ssize_t disk_capability_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%x\n", disk->flags); } static ssize_t disk_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); } static ssize_t disk_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); } static DEVICE_ATTR(range, 0444, disk_range_show, NULL); static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL); static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL); static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL); static DEVICE_ATTR(size, 0444, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL); static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL); static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store); #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); return sprintf(buf, "%d\n", p->make_it_fail); } ssize_t part_fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct hd_struct *p = dev_to_part(dev); int i; if (count > 0 && sscanf(buf, "%d", &i) > 0) p->make_it_fail = (i == 0) ? 0 : 1; return count; } static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif /* CONFIG_FAIL_MAKE_REQUEST */ #ifdef CONFIG_FAIL_IO_TIMEOUT static struct device_attribute dev_attr_fail_timeout = __ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store); #endif static struct attribute *disk_attrs[] = { &dev_attr_range.attr, &dev_attr_ext_range.attr, &dev_attr_removable.attr, &dev_attr_hidden.attr, &dev_attr_ro.attr, &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_discard_alignment.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, &dev_attr_badblocks.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif #ifdef CONFIG_FAIL_IO_TIMEOUT &dev_attr_fail_timeout.attr, #endif NULL }; static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, typeof(*dev), kobj); struct gendisk *disk = dev_to_disk(dev); if (a == &dev_attr_badblocks.attr && !disk->bb) return 0; return a->mode; } static struct attribute_group disk_attr_group = { .attrs = disk_attrs, .is_visible = disk_visible, }; static const struct attribute_group *disk_attr_groups[] = { &disk_attr_group, NULL }; /** * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way * @disk: disk to replace part_tbl for * @new_ptbl: new part_tbl to install * * Replace disk->part_tbl with @new_ptbl in RCU-safe way. The * original ptbl is freed using RCU callback. * * LOCKING: * Matching bd_mutex locked or the caller is the only user of @disk. */ static void disk_replace_part_tbl(struct gendisk *disk, struct disk_part_tbl *new_ptbl) { struct disk_part_tbl *old_ptbl = rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(disk->part_tbl, new_ptbl); if (old_ptbl) { rcu_assign_pointer(old_ptbl->last_lookup, NULL); kfree_rcu(old_ptbl, rcu_head); } } /** * disk_expand_part_tbl - expand disk->part_tbl * @disk: disk to expand part_tbl for * @partno: expand such that this partno can fit in * * Expand disk->part_tbl such that @partno can fit in. disk->part_tbl * uses RCU to allow unlocked dereferencing for stats and other stuff. * * LOCKING: * Matching bd_mutex locked or the caller is the only user of @disk. * Might sleep. * * RETURNS: * 0 on success, -errno on failure. */ int disk_expand_part_tbl(struct gendisk *disk, int partno) { struct disk_part_tbl *old_ptbl = rcu_dereference_protected(disk->part_tbl, 1); struct disk_part_tbl *new_ptbl; int len = old_ptbl ? old_ptbl->len : 0; int i, target; /* * check for int overflow, since we can get here from blkpg_ioctl() * with a user passed 'partno'. */ target = partno + 1; if (target < 0) return -EINVAL; /* disk_max_parts() is zero during initialization, ignore if so */ if (disk_max_parts(disk) && target > disk_max_parts(disk)) return -EINVAL; if (target <= len) return 0; new_ptbl = kzalloc_node(struct_size(new_ptbl, part, target), GFP_KERNEL, disk->node_id); if (!new_ptbl) return -ENOMEM; new_ptbl->len = target; for (i = 0; i < len; i++) rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]); disk_replace_part_tbl(disk, new_ptbl); return 0; } /** * disk_release - releases all allocated resources of the gendisk * @dev: the device representing this disk * * This function releases all allocated resources of the gendisk. * * The struct gendisk refcount is incremented with get_gendisk() or * get_disk_and_module(), and its refcount is decremented with * put_disk_and_module() or put_disk(). Once the refcount reaches 0 this * function is called. * * Drivers which used __device_add_disk() have a gendisk with a request_queue * assigned. Since the request_queue sits on top of the gendisk for these * drivers we also call blk_put_queue() for them, and we expect the * request_queue refcount to reach 0 at this point, and so the request_queue * will also be freed prior to the disk. * * Context: can sleep */ static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); might_sleep(); blk_free_devt(dev->devt); disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); hd_free_part(&disk->part0); if (disk->queue) blk_put_queue(disk->queue); kfree(disk); } struct class block_class = { .name = "block", }; static char *block_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { struct gendisk *disk = dev_to_disk(dev); if (disk->fops->devnode) return disk->fops->devnode(disk, mode); return NULL; } const struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, .devnode = block_devnode, }; #ifdef CONFIG_PROC_FS /* * aggregate disk stat collector. Uses the same stats that the sysfs * entries do, above, but makes them available through one seq_file. * * The output looks suspiciously like /proc/partitions with a bunch of * extra fields. */ static int diskstats_show(struct seq_file *seqf, void *v) { struct gendisk *gp = v; struct disk_part_iter piter; struct hd_struct *hd; char buf[BDEVNAME_SIZE]; unsigned int inflight; struct disk_stats stat; /* if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next) seq_puts(seqf, "major minor name" " rio rmerge rsect ruse wio wmerge " "wsect wuse running use aveq" "\n\n"); */ disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0); while ((hd = disk_part_iter_next(&piter))) { part_stat_read_all(hd, &stat); if (queue_is_mq(gp->queue)) inflight = blk_mq_in_flight(gp->queue, hd); else inflight = part_in_flight(hd); seq_printf(seqf, "%4d %7d %s " "%lu %lu %lu %u " "%lu %lu %lu %u " "%u %u %u " "%lu %lu %lu %u " "%lu %u" "\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), stat.ios[STAT_READ], stat.merges[STAT_READ], stat.sectors[STAT_READ], (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC), stat.ios[STAT_WRITE], stat.merges[STAT_WRITE], stat.sectors[STAT_WRITE], (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC), inflight, jiffies_to_msecs(stat.io_ticks), (unsigned int)div_u64(stat.nsecs[STAT_READ] + stat.nsecs[STAT_WRITE] + stat.nsecs[STAT_DISCARD] + stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC), stat.ios[STAT_DISCARD], stat.merges[STAT_DISCARD], stat.sectors[STAT_DISCARD], (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC), stat.ios[STAT_FLUSH], (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC) ); } disk_part_iter_exit(&piter); return 0; } static const struct seq_operations diskstats_op = { .start = disk_seqf_start, .next = disk_seqf_next, .stop = disk_seqf_stop, .show = diskstats_show }; static int __init proc_genhd_init(void) { proc_create_seq("diskstats", 0, NULL, &diskstats_op); proc_create_seq("partitions", 0, NULL, &partitions_op); return 0; } module_init(proc_genhd_init); #endif /* CONFIG_PROC_FS */ dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); struct hd_struct *part; if (strcmp(dev_name(dev), name)) continue; if (partno < disk->minors) { /* We need to return the right devno, even * if the partition doesn't exist yet. */ devt = MKDEV(MAJOR(dev->devt), MINOR(dev->devt) + partno); break; } part = disk_get_part(disk, partno); if (part) { devt = part_devt(part); disk_put_part(part); break; } disk_put_part(part); } class_dev_iter_exit(&iter); return devt; } struct gendisk *__alloc_disk_node(int minors, int node_id) { struct gendisk *disk; struct disk_part_tbl *ptbl; if (minors > DISK_MAX_PARTS) { printk(KERN_ERR "block: can't allocate more than %d partitions\n", DISK_MAX_PARTS); minors = DISK_MAX_PARTS; } disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) return NULL; disk->part0.dkstats = alloc_percpu(struct disk_stats); if (!disk->part0.dkstats) goto out_free_disk; init_rwsem(&disk->lookup_sem); disk->node_id = node_id; if (disk_expand_part_tbl(disk, 0)) { free_percpu(disk->part0.dkstats); goto out_free_disk; } ptbl = rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(ptbl->part[0], &disk->part0); /* * set_capacity() and get_capacity() currently don't use * seqcounter to read/update the part0->nr_sects. Still init * the counter as we can read the sectors in IO submission * patch using seqence counters. * * TODO: Ideally set_capacity() and get_capacity() should be * converted to make use of bd_mutex and sequence counters. */ hd_sects_seq_init(&disk->part0); if (hd_ref_init(&disk->part0)) goto out_free_part0; disk->minors = minors; rand_initialize_disk(disk); disk_to_dev(disk)->class = &block_class; disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); return disk; out_free_part0: hd_free_part(&disk->part0); out_free_disk: kfree(disk); return NULL; } EXPORT_SYMBOL(__alloc_disk_node); /** * get_disk_and_module - increments the gendisk and gendisk fops module refcount * @disk: the struct gendisk to increment the refcount for * * This increments the refcount for the struct gendisk, and the gendisk's * fops module owner. * * Context: Any context. */ struct kobject *get_disk_and_module(struct gendisk *disk) { struct module *owner; struct kobject *kobj; if (!disk->fops) return NULL; owner = disk->fops->owner; if (owner && !try_module_get(owner)) return NULL; kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj); if (kobj == NULL) { module_put(owner); return NULL; } return kobj; } EXPORT_SYMBOL(get_disk_and_module); /** * put_disk - decrements the gendisk refcount * @disk: the struct gendisk to decrement the refcount for * * This decrements the refcount for the struct gendisk. When this reaches 0 * we'll have disk_release() called. * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void put_disk(struct gendisk *disk) { if (disk) kobject_put(&disk_to_dev(disk)->kobj); } EXPORT_SYMBOL(put_disk); /** * put_disk_and_module - decrements the module and gendisk refcount * @disk: the struct gendisk to decrement the refcount for * * This is a counterpart of get_disk_and_module() and thus also of * get_gendisk(). * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void put_disk_and_module(struct gendisk *disk) { if (disk) { struct module *owner = disk->fops->owner; put_disk(disk); module_put(owner); } } EXPORT_SYMBOL(put_disk_and_module); static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; char *envp[] = { event, NULL }; if (!ro) event[8] = '0'; kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp); } void set_device_ro(struct block_device *bdev, int flag) { bdev->bd_part->policy = flag; } EXPORT_SYMBOL(set_device_ro); void set_disk_ro(struct gendisk *disk, int flag) { struct disk_part_iter piter; struct hd_struct *part; if (disk->part0.policy != flag) { set_disk_ro_uevent(disk, flag); disk->part0.policy = flag; } disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); while ((part = disk_part_iter_next(&piter))) part->policy = flag; disk_part_iter_exit(&piter); } EXPORT_SYMBOL(set_disk_ro); int bdev_read_only(struct block_device *bdev) { if (!bdev) return 0; return bdev->bd_part->policy; } EXPORT_SYMBOL(bdev_read_only); /* * Disk events - monitor disk events like media change and eject request. */ struct disk_events { struct list_head node; /* all disk_event's */ struct gendisk *disk; /* the associated disk */ spinlock_t lock; struct mutex block_mutex; /* protects blocking */ int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ long poll_msecs; /* interval, -1 for default */ struct delayed_work dwork; }; static const char *disk_events_strs[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", }; static char *disk_uevents[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", }; /* list of all disk_events */ static DEFINE_MUTEX(disk_events_mutex); static LIST_HEAD(disk_events); /* disable in-kernel polling by default */ static unsigned long disk_events_dfl_poll_msecs; static unsigned long disk_events_poll_jiffies(struct gendisk *disk) { struct disk_events *ev = disk->ev; long intv_msecs = 0; /* * If device-specific poll interval is set, always use it. If * the default is being used, poll if the POLL flag is set. */ if (ev->poll_msecs >= 0) intv_msecs = ev->poll_msecs; else if (disk->event_flags & DISK_EVENT_FLAG_POLL) intv_msecs = disk_events_dfl_poll_msecs; return msecs_to_jiffies(intv_msecs); } /** * disk_block_events - block and flush disk event checking * @disk: disk to block events for * * On return from this function, it is guaranteed that event checking * isn't in progress and won't happen until unblocked by * disk_unblock_events(). Events blocking is counted and the actual * unblocking happens after the matching number of unblocks are done. * * Note that this intentionally does not block event checking from * disk_clear_events(). * * CONTEXT: * Might sleep. */ void disk_block_events(struct gendisk *disk) { struct disk_events *ev = disk->ev; unsigned long flags; bool cancel; if (!ev) return; /* * Outer mutex ensures that the first blocker completes canceling * the event work before further blockers are allowed to finish. */ mutex_lock(&ev->block_mutex); spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); if (cancel) cancel_delayed_work_sync(&disk->ev->dwork); mutex_unlock(&ev->block_mutex); } static void __disk_unblock_events(struct gendisk *disk, bool check_now) { struct disk_events *ev = disk->ev; unsigned long intv; unsigned long flags; spin_lock_irqsave(&ev->lock, flags); if (WARN_ON_ONCE(ev->block <= 0)) goto out_unlock; if (--ev->block) goto out_unlock; intv = disk_events_poll_jiffies(disk); if (check_now) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); else if (intv) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, intv); out_unlock: spin_unlock_irqrestore(&ev->lock, flags); } /** * disk_unblock_events - unblock disk event checking * @disk: disk to unblock events for * * Undo disk_block_events(). When the block count reaches zero, it * starts events polling if configured. * * CONTEXT: * Don't care. Safe to call from irq context. */ void disk_unblock_events(struct gendisk *disk) { if (disk->ev) __disk_unblock_events(disk, false); } /** * disk_flush_events - schedule immediate event checking and flushing * @disk: disk to check and flush events for * @mask: events to flush * * Schedule immediate event checking on @disk if not blocked. Events in * @mask are scheduled to be cleared from the driver. Note that this * doesn't clear the events from @disk->ev. * * CONTEXT: * If @mask is non-zero must be called with bdev->bd_mutex held. */ void disk_flush_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; if (!ev) return; spin_lock_irq(&ev->lock); ev->clearing |= mask; if (!ev->block) mod_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); spin_unlock_irq(&ev->lock); } /** * disk_clear_events - synchronously check, clear and return pending events * @disk: disk to fetch and clear events from * @mask: mask of events to be fetched and cleared * * Disk events are synchronously checked and pending events in @mask * are cleared and returned. This ignores the block count. * * CONTEXT: * Might sleep. */ static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; unsigned int pending; unsigned int clearing = mask; if (!ev) return 0; disk_block_events(disk); /* * store the union of mask and ev->clearing on the stack so that the * race with disk_flush_events does not cause ambiguity (ev->clearing * can still be modified even if events are blocked). */ spin_lock_irq(&ev->lock); clearing |= ev->clearing; ev->clearing = 0; spin_unlock_irq(&ev->lock); disk_check_events(ev, &clearing); /* * if ev->clearing is not 0, the disk_flush_events got called in the * middle of this function, so we want to run the workfn without delay. */ __disk_unblock_events(disk, ev->clearing ? true : false); /* then, fetch and clear pending events */ spin_lock_irq(&ev->lock); pending = ev->pending & mask; ev->pending &= ~mask; spin_unlock_irq(&ev->lock); WARN_ON_ONCE(clearing & mask); return pending; } /** * bdev_check_media_change - check if a removable media has been changed * @bdev: block device to check * * Check whether a removable media has been changed, and attempt to free all * dentries and inodes and invalidates all block device page cache entries in * that case. * * Returns %true if the block device changed, or %false if not. */ bool bdev_check_media_change(struct block_device *bdev) { unsigned int events; events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST); if (!(events & DISK_EVENT_MEDIA_CHANGE)) return false; if (__invalidate_device(bdev, true)) pr_warn("VFS: busy inodes on changed media %s\n", bdev->bd_disk->disk_name); set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); return true; } EXPORT_SYMBOL(bdev_check_media_change); /* * Separate this part out so that a different pointer for clearing_ptr can be * passed in for disk_clear_events. */ static void disk_events_workfn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct disk_events *ev = container_of(dwork, struct disk_events, dwork); disk_check_events(ev, &ev->clearing); } static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr) { struct gendisk *disk = ev->disk; char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; unsigned int clearing = *clearing_ptr; unsigned int events; unsigned long intv; int nr_events = 0, i; /* check events */ events = disk->fops->check_events(disk, clearing); /* accumulate pending events and schedule next poll if necessary */ spin_lock_irq(&ev->lock); events &= ~ev->pending; ev->pending |= events; *clearing_ptr &= ~clearing; intv = disk_events_poll_jiffies(disk); if (!ev->block && intv) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, intv); spin_unlock_irq(&ev->lock); /* * Tell userland about new events. Only the events listed in * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT * is set. Otherwise, events are processed internally but never * get reported to userland. */ for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) if ((events & disk->events & (1 << i)) && (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) envp[nr_events++] = disk_uevents[i]; if (nr_events) kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); } /* * A disk events enabled device has the following sysfs nodes under * its /sys/block/X/ directory. * * events : list of all supported events * events_async : list of events which can be detected w/o polling * (always empty, only for backwards compatibility) * events_poll_msecs : polling interval, 0: disable, -1: system default */ static ssize_t __disk_events_show(unsigned int events, char *buf) { const char *delim = ""; ssize_t pos = 0; int i; for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) if (events & (1 << i)) { pos += sprintf(buf + pos, "%s%s", delim, disk_events_strs[i]); delim = " "; } if (pos) pos += sprintf(buf + pos, "\n"); return pos; } static ssize_t disk_events_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) return 0; return __disk_events_show(disk->events, buf); } static ssize_t disk_events_async_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static ssize_t disk_events_poll_msecs_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); if (!disk->ev) return sprintf(buf, "-1\n"); return sprintf(buf, "%ld\n", disk->ev->poll_msecs); } static ssize_t disk_events_poll_msecs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); long intv; if (!count || !sscanf(buf, "%ld", &intv)) return -EINVAL; if (intv < 0 && intv != -1) return -EINVAL; if (!disk->ev) return -ENODEV; disk_block_events(disk); disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); return count; } static const DEVICE_ATTR(events, 0444, disk_events_show, NULL); static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); static const DEVICE_ATTR(events_poll_msecs, 0644, disk_events_poll_msecs_show, disk_events_poll_msecs_store); static const struct attribute *disk_events_attrs[] = { &dev_attr_events.attr, &dev_attr_events_async.attr, &dev_attr_events_poll_msecs.attr, NULL, }; /* * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to * /sys/module/block/parameters/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) { struct disk_events *ev; int ret; ret = param_set_ulong(val, kp); if (ret < 0) return ret; mutex_lock(&disk_events_mutex); list_for_each_entry(ev, &disk_events, node) disk_flush_events(ev->disk, 0); mutex_unlock(&disk_events_mutex); return 0; } static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { .set = disk_events_set_dfl_poll_msecs, .get = param_get_ulong, }; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "block." module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, &disk_events_dfl_poll_msecs, 0644); /* * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. */ static void disk_alloc_events(struct gendisk *disk) { struct disk_events *ev; if (!disk->fops->check_events || !disk->events) return; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { pr_warn("%s: failed to initialize events\n", disk->disk_name); return; } INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); mutex_init(&ev->block_mutex); ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); disk->ev = ev; } static void disk_add_events(struct gendisk *disk) { /* FIXME: error handling */ if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) pr_warn("%s: failed to create sysfs files for events\n", disk->disk_name); if (!disk->ev) return; mutex_lock(&disk_events_mutex); list_add_tail(&disk->ev->node, &disk_events); mutex_unlock(&disk_events_mutex); /* * Block count is initialized to 1 and the following initial * unblock kicks it into action. */ __disk_unblock_events(disk, true); } static void disk_del_events(struct gendisk *disk) { if (disk->ev) { disk_block_events(disk); mutex_lock(&disk_events_mutex); list_del_init(&disk->ev->node); mutex_unlock(&disk_events_mutex); } sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs); } static void disk_release_events(struct gendisk *disk) { /* the block count should be 1 from disk_del_events() */ WARN_ON_ONCE(disk->ev && disk->ev->block != 1); kfree(disk->ev); } |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <asm/processor.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags); /* * If the work is already pending, no need to raise the IPI. * The pairing atomic_fetch_andnot() in irq_work_run() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { /* If the work is "lazy", handle it from next tick if any */ if (atomic_read(&work->flags) & IRQ_WORK_LAZY) { if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && tick_nohz_tick_stopped()) arch_irq_work_raise(); } else { if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) arch_irq_work_raise(); } } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); __smp_call_single_queue(cpu, &work->llnode); } else { __irq_work_queue_local(work); } preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work * can be re-used. * Make it immediately visible so that other CPUs trying * to claim that work don't rely on us to handle their data * while we are in the middle of the func. */ flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags); lockdep_irq_work_enter(work); work->func(work); lockdep_irq_work_exit(work); /* * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ flags &= ~IRQ_WORK_PENDING; (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; BUG_ON(!irqs_disabled()); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, llnode) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); irq_work_run_list(this_cpu_ptr(&lazy_list)); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); irq_work_run_list(this_cpu_ptr(&lazy_list)); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); while (atomic_read(&work->flags) & IRQ_WORK_BUSY) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> /* * Leveraged for setting/resetting capabilities */ const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; EXPORT_SYMBOL(__cap_empty_set); int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", get_task_comm(name, current)); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", get_task_comm(name, current)); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (!ret) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; for (i = 0; i < tocopy; i++) { kdata[i].effective = pE.cap[i]; kdata[i].permitted = pP.cap[i]; kdata[i].inheritable = pI.cap[i]; } /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(struct __user_cap_data_struct))) { return -EFAULT; } } return ret; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; for (i = 0; i < tocopy; i++) { effective.cap[i] = kdata[i].effective; permitted.cap[i] = kdata[i].permitted; inheritable.cap[i] = kdata[i].inheritable; } while (i < _KERNEL_CAPABILITY_U32S) { effective.cap[i] = 0; permitted.cap[i] = 0; inheritable.cap[i] = 0; i++; } effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_capability - Does a task have a capability in init_user_ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode) { return kuid_has_mapping(ns, inode->i_uid) && kgid_has_mapping(ns, inode->i_gid); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/super.c * * Copyright (C) 1991, 1992 Linus Torvalds * * super.c contains code to handle: - mount structures * - super-block tables * - filesystem drivers list * - mount system call * - umount system call * - ustat system call * * GK 2/5/95 - Changed to support mounting the root fs via NFS * * Added kerneld support: Jacques Gelinas and Bjorn Ekwall * Added change_root: Werner Almesberger & Hans Lermen, Feb '96 * Added options to /proc/mounts: * Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996. * Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998 * Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000 */ #include <linux/export.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/writeback.h> /* for the emergency remount stuff */ #include <linux/idr.h> #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/rculist_bl.h> #include <linux/cleancache.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/lockdep.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <uapi/linux/mount.h> #include "internal.h" static int thaw_super_locked(struct super_block *sb); static LIST_HEAD(super_blocks); static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = { "sb_writers", "sb_pagefaults", "sb_internal", }; /* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { struct super_block *sb; long fs_objects = 0; long total_objects; long freed = 0; long dentries; long inodes; sb = container_of(shrink, struct super_block, s_shrink); /* * Deadlock avoidance. We may hold various FS locks, and we don't want * to recurse into the FS that called us in clear_inode() and friends.. */ if (!(sc->gfp_mask & __GFP_FS)) return SHRINK_STOP; if (!trylock_super(sb)) return SHRINK_STOP; if (sb->s_op->nr_cached_objects) fs_objects = sb->s_op->nr_cached_objects(sb, sc); inodes = list_lru_shrink_count(&sb->s_inode_lru, sc); dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc); total_objects = dentries + inodes + fs_objects + 1; if (!total_objects) total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); inodes = mult_frac(sc->nr_to_scan, inodes, total_objects); fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects); /* * prune the dcache first as the icache is pinned by it, then * prune the icache, followed by the filesystem specific caches * * Ensure that we always scan at least one object - memcg kmem * accounting uses this to fully empty the caches. */ sc->nr_to_scan = dentries + 1; freed = prune_dcache_sb(sb, sc); sc->nr_to_scan = inodes + 1; freed += prune_icache_sb(sb, sc); if (fs_objects) { sc->nr_to_scan = fs_objects + 1; freed += sb->s_op->free_cached_objects(sb, sc); } up_read(&sb->s_umount); return freed; } static unsigned long super_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct super_block *sb; long total_objects = 0; sb = container_of(shrink, struct super_block, s_shrink); /* * We don't call trylock_super() here as it is a scalability bottleneck, * so we're exposed to partial setup state. The shrinker rwsem does not * protect filesystem operations backing list_lru_shrink_count() or * s_op->nr_cached_objects(). Counts can change between * super_cache_count and super_cache_scan, so we really don't need locks * here. * * However, if we are currently mounting the superblock, the underlying * filesystem might be in a state of partial construction and hence it * is dangerous to access it. trylock_super() uses a SB_BORN check to * avoid this situation, so do the same here. The memory barrier is * matched with the one in mount_fs() as we don't hold locks here. */ if (!(sb->s_flags & SB_BORN)) return 0; smp_rmb(); if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc); total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc); total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc); if (!total_objects) return SHRINK_EMPTY; total_objects = vfs_pressure_ratio(total_objects); return total_objects; } static void destroy_super_work(struct work_struct *work) { struct super_block *s = container_of(work, struct super_block, destroy_work); int i; for (i = 0; i < SB_FREEZE_LEVELS; i++) percpu_free_rwsem(&s->s_writers.rw_sem[i]); kfree(s); } static void destroy_super_rcu(struct rcu_head *head) { struct super_block *s = container_of(head, struct super_block, rcu); INIT_WORK(&s->destroy_work, destroy_super_work); schedule_work(&s->destroy_work); } /* Free a superblock that has never been seen by anyone */ static void destroy_unused_super(struct super_block *s) { if (!s) return; up_write(&s->s_umount); list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); security_sb_free(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); free_prealloced_shrinker(&s->s_shrink); /* no delays needed */ destroy_super_work(&s->destroy_work); } /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to * @flags: the mount flags * @user_ns: User namespace for the super_block * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); static const struct super_operations default_op; int i; if (!s) return NULL; INIT_LIST_HEAD(&s->s_mounts); s->s_user_ns = get_user_ns(user_ns); init_rwsem(&s->s_umount); lockdep_set_class(&s->s_umount, &type->s_umount_key); /* * sget() can have s_umount recursion. * * When it cannot find a suitable sb, it allocates a new * one (this one), and tries again to find a suitable old * one. * * In case that succeeds, it will acquire the s_umount * lock of the old one. Since these are clearly distrinct * locks, and this object isn't exposed yet, there's no * risk of deadlocks. * * Annotate this by putting this lock in a different * subclass. */ down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); if (security_sb_alloc(s)) goto fail; for (i = 0; i < SB_FREEZE_LEVELS; i++) { if (__percpu_init_rwsem(&s->s_writers.rw_sem[i], sb_writers_name[i], &type->s_writers_key[i])) goto fail; } init_waitqueue_head(&s->s_writers.wait_unfrozen); s->s_bdi = &noop_backing_dev_info; s->s_flags = flags; if (s->s_user_ns != &init_user_ns) s->s_iflags |= SB_I_NODEV; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_roots); mutex_init(&s->s_sync_lock); INIT_LIST_HEAD(&s->s_inodes); spin_lock_init(&s->s_inode_list_lock); INIT_LIST_HEAD(&s->s_inodes_wb); spin_lock_init(&s->s_inode_wblist_lock); s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key); init_rwsem(&s->s_dquot.dqio_sem); s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; s->cleancache_poolid = CLEANCACHE_NO_POOL; s->s_shrink.seeks = DEFAULT_SEEKS; s->s_shrink.scan_objects = super_cache_scan; s->s_shrink.count_objects = super_cache_count; s->s_shrink.batch = 1024; s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE; if (prealloc_shrinker(&s->s_shrink)) goto fail; if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) goto fail; if (list_lru_init_memcg(&s->s_inode_lru, &s->s_shrink)) goto fail; return s; fail: destroy_unused_super(s); return NULL; } /* Superblock refcounting */ /* * Drop a superblock's refcount. The caller must hold sb_lock. */ static void __put_super(struct super_block *s) { if (!--s->s_count) { list_del_init(&s->s_list); WARN_ON(s->s_dentry_lru.node); WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); security_sb_free(s); fscrypt_destroy_keyring(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); call_rcu(&s->rcu, destroy_super_rcu); } } /** * put_super - drop a temporary reference to superblock * @sb: superblock in question * * Drops a temporary reference, frees superblock if there's no * references left. */ static void put_super(struct super_block *sb) { spin_lock(&sb_lock); __put_super(sb); spin_unlock(&sb_lock); } /** * deactivate_locked_super - drop an active reference to superblock * @s: superblock to deactivate * * Drops an active reference to superblock, converting it into a temporary * one if there is no other active references left. In that case we * tell fs driver to shut it down and drop the temporary reference we * had just acquired. * * Caller holds exclusive lock on superblock; that lock is released. */ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { cleancache_invalidate_fs(s); unregister_shrinker(&s->s_shrink); fs->kill_sb(s); /* * Since list_lru_destroy() may sleep, we cannot call it from * put_super(), where we hold the sb_lock. Therefore we destroy * the lru lists right now. */ list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); put_filesystem(fs); put_super(s); } else { up_write(&s->s_umount); } } EXPORT_SYMBOL(deactivate_locked_super); /** * deactivate_super - drop an active reference to superblock * @s: superblock to deactivate * * Variant of deactivate_locked_super(), except that superblock is *not* * locked by caller. If we are going to drop the final active reference, * lock will be acquired prior to that. */ void deactivate_super(struct super_block *s) { if (!atomic_add_unless(&s->s_active, -1, 1)) { down_write(&s->s_umount); deactivate_locked_super(s); } } EXPORT_SYMBOL(deactivate_super); /** * grab_super - acquire an active reference * @s: reference we are trying to make active * * Tries to acquire an active reference. grab_super() is used when we * had just found a superblock in super_blocks or fs_type->fs_supers * and want to turn it into a full-blown active reference. grab_super() * is called with sb_lock held and drops it. Returns 1 in case of * success, 0 if we had failed (superblock contents was already dead or * dying when grab_super() had been called). Note that this is only * called for superblocks not in rundown mode (== ones still on ->fs_supers * of their type), so increment of ->s_count is OK here. */ static int grab_super(struct super_block *s) __releases(sb_lock) { s->s_count++; spin_unlock(&sb_lock); down_write(&s->s_umount); if ((s->s_flags & SB_BORN) && atomic_inc_not_zero(&s->s_active)) { put_super(s); return 1; } up_write(&s->s_umount); put_super(s); return 0; } /* * trylock_super - try to grab ->s_umount shared * @sb: reference we are trying to grab * * Try to prevent fs shutdown. This is used in places where we * cannot take an active reference but we need to ensure that the * filesystem is not shut down while we are working on it. It returns * false if we cannot acquire s_umount or if we lose the race and * filesystem already got into shutdown, and returns true with the s_umount * lock held in read mode in case of success. On successful return, * the caller must drop the s_umount lock when done. * * Note that unlike get_super() et.al. this one does *not* bump ->s_count. * The reason why it's safe is that we are OK with doing trylock instead * of down_read(). There's a couple of places that are OK with that, but * it's very much not a general-purpose interface. */ bool trylock_super(struct super_block *sb) { if (down_read_trylock(&sb->s_umount)) { if (!hlist_unhashed(&sb->s_instances) && sb->s_root && (sb->s_flags & SB_BORN)) return true; up_read(&sb->s_umount); } return false; } /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill * * generic_shutdown_super() does all fs-independent work on superblock * shutdown. Typical ->kill_sb() should pick all fs-specific objects * that need destruction out of superblock, call generic_shutdown_super() * and release aforementioned objects. Note: dentries and inodes _are_ * taken care of and do not need specific handling. * * Upon calling this function, the filesystem may no longer alter or * rearrange the set of dentries belonging to this super_block, nor may it * change the attachments of dentries to inodes. */ void generic_shutdown_super(struct super_block *sb) { const struct super_operations *sop = sb->s_op; if (sb->s_root) { shrink_dcache_for_umount(sb); sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; cgroup_writeback_umount(); /* evict all inodes with zero refcount */ evict_inodes(sb); /* only nonzero refcount inodes can have marks */ fsnotify_sb_delete(sb); fscrypt_destroy_keyring(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); sb->s_dio_done_wq = NULL; } if (sop->put_super) sop->put_super(sb); if (!list_empty(&sb->s_inodes)) { printk("VFS: Busy inodes after unmount of %s. " "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); } } spin_lock(&sb_lock); /* should be initialized for __put_super_and_need_restart() */ hlist_del_init(&sb->s_instances); spin_unlock(&sb_lock); up_write(&sb->s_umount); if (sb->s_bdi != &noop_backing_dev_info) { if (sb->s_iflags & SB_I_PERSB_BDI) bdi_unregister(sb->s_bdi); bdi_put(sb->s_bdi); sb->s_bdi = &noop_backing_dev_info; } } EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc) { if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) return capable(CAP_SYS_ADMIN); else return ns_capable(fc->user_ns, CAP_SYS_ADMIN); } /** * sget_fc - Find or create a superblock * @fc: Filesystem context. * @test: Comparison callback * @set: Setup callback * * Find or create a superblock using the parameters stored in the filesystem * context and the two callback functions. * * If an extant superblock is matched, then that will be returned with an * elevated reference count that the caller must transfer or discard. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info and s_id will be set and * the set() callback will be invoked), the superblock will be published and it * will be returned in a partially constructed state with SB_BORN and SB_ACTIVE * as yet unset. */ struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)) { struct super_block *s = NULL; struct super_block *old; struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns; int err; /* * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is * not set, as the filesystem is likely unprepared to handle it. * This can happen when fsconfig() is called from init_user_ns with * an fs_fd opened in another user namespace. */ if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) { errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed"); return ERR_PTR(-EPERM); } retry: spin_lock(&sb_lock); if (test) { hlist_for_each_entry(old, &fc->fs_type->fs_supers, s_instances) { if (test(old, fc)) goto share_extant_sb; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(fc->fs_type, fc->sb_flags, user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } s->s_fs_info = fc->s_fs_info; err = set(s, fc); if (err) { s->s_fs_info = NULL; spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(err); } fc->s_fs_info = NULL; s->s_type = fc->fs_type; s->s_iflags |= fc->s_iflags; strlcpy(s->s_id, s->s_type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &s->s_type->fs_supers); spin_unlock(&sb_lock); get_filesystem(s->s_type); register_shrinker_prepared(&s->s_shrink); return s; share_extant_sb: if (user_ns != old->s_user_ns) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(-EBUSY); } if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; } EXPORT_SYMBOL(sget_fc); /** * sget - find or create a superblock * @type: filesystem type superblock should belong to * @test: comparison callback * @set: setup callback * @flags: mount flags * @data: argument to each of them */ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data) { struct user_namespace *user_ns = current_user_ns(); struct super_block *s = NULL; struct super_block *old; int err; /* We don't yet pass the user namespace of the parent * mount through to here so always use &init_user_ns * until that changes. */ if (flags & SB_SUBMOUNT) user_ns = &init_user_ns; retry: spin_lock(&sb_lock); if (test) { hlist_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (user_ns != old->s_user_ns) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(-EBUSY); } if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } err = set(s, data); if (err) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(err); } s->s_type = type; strlcpy(s->s_id, type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); register_shrinker_prepared(&s->s_shrink); return s; } EXPORT_SYMBOL(sget); void drop_super(struct super_block *sb) { up_read(&sb->s_umount); put_super(sb); } EXPORT_SYMBOL(drop_super); void drop_super_exclusive(struct super_block *sb) { up_write(&sb->s_umount); put_super(sb); } EXPORT_SYMBOL(drop_super_exclusive); static void __iterate_supers(void (*f)(struct super_block *)) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (hlist_unhashed(&sb->s_instances)) continue; sb->s_count++; spin_unlock(&sb_lock); f(sb); spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } /** * iterate_supers - call function for all active superblocks * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (hlist_unhashed(&sb->s_instances)) continue; sb->s_count++; spin_unlock(&sb_lock); down_read(&sb->s_umount); if (sb->s_root && (sb->s_flags & SB_BORN)) f(sb, arg); up_read(&sb->s_umount); spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } /** * iterate_supers_type - call function for superblocks of given type * @type: fs type * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers_type(struct file_system_type *type, void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); hlist_for_each_entry(sb, &type->fs_supers, s_instances) { sb->s_count++; spin_unlock(&sb_lock); down_read(&sb->s_umount); if (sb->s_root && (sb->s_flags & SB_BORN)) f(sb, arg); up_read(&sb->s_umount); spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } EXPORT_SYMBOL(iterate_supers_type); static struct super_block *__get_super(struct block_device *bdev, bool excl) { struct super_block *sb; if (!bdev) return NULL; spin_lock(&sb_lock); rescan: list_for_each_entry(sb, &super_blocks, s_list) { if (hlist_unhashed(&sb->s_instances)) continue; if (sb->s_bdev == bdev) { sb->s_count++; spin_unlock(&sb_lock); if (!excl) down_read(&sb->s_umount); else down_write(&sb->s_umount); /* still alive? */ if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; if (!excl) up_read(&sb->s_umount); else up_write(&sb->s_umount); /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); goto rescan; } } spin_unlock(&sb_lock); return NULL; } /** * get_super - get the superblock of a device * @bdev: device to get the superblock for * * Scans the superblock list and finds the superblock of the file system * mounted on the device given. %NULL is returned if no match is found. */ struct super_block *get_super(struct block_device *bdev) { return __get_super(bdev, false); } EXPORT_SYMBOL(get_super); static struct super_block *__get_super_thawed(struct block_device *bdev, bool excl) { while (1) { struct super_block *s = __get_super(bdev, excl); if (!s || s->s_writers.frozen == SB_UNFROZEN) return s; if (!excl) up_read(&s->s_umount); else up_write(&s->s_umount); wait_event(s->s_writers.wait_unfrozen, s->s_writers.frozen == SB_UNFROZEN); put_super(s); } } /** * get_super_thawed - get thawed superblock of a device * @bdev: device to get the superblock for * * Scans the superblock list and finds the superblock of the file system * mounted on the device. The superblock is returned once it is thawed * (or immediately if it was not frozen). %NULL is returned if no match * is found. */ struct super_block *get_super_thawed(struct block_device *bdev) { return __get_super_thawed(bdev, false); } EXPORT_SYMBOL(get_super_thawed); /** * get_super_exclusive_thawed - get thawed superblock of a device * @bdev: device to get the superblock for * * Scans the superblock list and finds the superblock of the file system * mounted on the device. The superblock is returned once it is thawed * (or immediately if it was not frozen) and s_umount semaphore is held * in exclusive mode. %NULL is returned if no match is found. */ struct super_block *get_super_exclusive_thawed(struct block_device *bdev) { return __get_super_thawed(bdev, true); } EXPORT_SYMBOL(get_super_exclusive_thawed); /** * get_active_super - get an active reference to the superblock of a device * @bdev: device to get the superblock for * * Scans the superblock list and finds the superblock of the file system * mounted on the device given. Returns the superblock with an active * reference or %NULL if none was found. */ struct super_block *get_active_super(struct block_device *bdev) { struct super_block *sb; if (!bdev) return NULL; restart: spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (hlist_unhashed(&sb->s_instances)) continue; if (sb->s_bdev == bdev) { if (!grab_super(sb)) goto restart; up_write(&sb->s_umount); return sb; } } spin_unlock(&sb_lock); return NULL; } struct super_block *user_get_super(dev_t dev) { struct super_block *sb; spin_lock(&sb_lock); rescan: list_for_each_entry(sb, &super_blocks, s_list) { if (hlist_unhashed(&sb->s_instances)) continue; if (sb->s_dev == dev) { sb->s_count++; spin_unlock(&sb_lock); down_read(&sb->s_umount); /* still alive? */ if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; up_read(&sb->s_umount); /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); goto rescan; } } spin_unlock(&sb_lock); return NULL; } /** * reconfigure_super - asks filesystem to change superblock parameters * @fc: The superblock and configuration * * Alters the configuration parameters of a live superblock. */ int reconfigure_super(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) return -EINVAL; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; retval = security_sb_remount(sb, fc->security); if (retval) return retval; if (fc->sb_flags_mask & SB_RDONLY) { #ifdef CONFIG_BLOCK if (!(fc->sb_flags & SB_RDONLY) && bdev_read_only(sb->s_bdev)) return -EACCES; #endif remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } if (remount_ro) { if (!hlist_empty(&sb->s_pins)) { up_write(&sb->s_umount); group_pin_kill(&sb->s_pins); down_write(&sb->s_umount); if (!sb->s_root) return 0; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; remount_ro = !sb_rdonly(sb); } } shrink_dcache_sb(sb); /* If we are reconfiguring to RDONLY and current sb is read/write, * make sure there are no files open for writing. */ if (remount_ro) { if (force) { sb->s_readonly_remount = 1; smp_wmb(); } else { retval = sb_prepare_remount_readonly(sb); if (retval) return retval; } } else if (remount_rw) { /* * We set s_readonly_remount here to protect filesystem's * reconfigure code from writes from userspace until * reconfigure finishes. */ sb->s_readonly_remount = 1; smp_wmb(); } if (fc->ops->reconfigure) { retval = fc->ops->reconfigure(fc); if (retval) { if (!force) goto cancel_readonly; /* If forced remount, go ahead despite any errors */ WARN(1, "forced remount of a %s fs returned %i\n", sb->s_type->name, retval); } } WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | (fc->sb_flags & fc->sb_flags_mask))); /* Needs to be ordered wrt mnt_is_readonly() */ smp_wmb(); sb->s_readonly_remount = 0; /* * Some filesystems modify their metadata via some other path than the * bdev buffer cache (eg. use a private mapping, or directories in * pagecache, etc). Also file data modifications go via their own * mappings. So If we try to mount readonly then copy the filesystem * from bdev, we could get stale data, so invalidate it to give a best * effort at coherency. */ if (remount_ro && sb->s_bdev) invalidate_bdev(sb->s_bdev); return 0; cancel_readonly: sb->s_readonly_remount = 0; return retval; } static void do_emergency_remount_callback(struct super_block *sb) { down_write(&sb->s_umount); if (sb->s_root && sb->s_bdev && (sb->s_flags & SB_BORN) && !sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY | SB_FORCE, SB_RDONLY); if (!IS_ERR(fc)) { if (parse_monolithic_mount_data(fc, NULL) == 0) (void)reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); } static void do_emergency_remount(struct work_struct *work) { __iterate_supers(do_emergency_remount_callback); kfree(work); printk("Emergency Remount complete\n"); } void emergency_remount(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_emergency_remount); schedule_work(work); } } static void do_thaw_all_callback(struct super_block *sb) { down_write(&sb->s_umount); if (sb->s_root && sb->s_flags & SB_BORN) { emergency_thaw_bdev(sb); thaw_super_locked(sb); } else { up_write(&sb->s_umount); } } static void do_thaw_all(struct work_struct *work) { __iterate_supers(do_thaw_all_callback); kfree(work); printk(KERN_WARNING "Emergency Thaw complete\n"); } /** * emergency_thaw_all -- forcibly thaw every frozen filesystem * * Used for emergency unfreeze of all filesystems via SysRq */ void emergency_thaw_all(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_thaw_all); schedule_work(work); } } static DEFINE_IDA(unnamed_dev_ida); /** * get_anon_bdev - Allocate a block device for filesystems which don't have one. * @p: Pointer to a dev_t. * * Filesystems which don't use real block devices can call this function * to allocate a virtual block device. * * Context: Any context. Frequently called while holding sb_lock. * Return: 0 on success, -EMFILE if there are no anonymous bdevs left * or -ENOMEM if memory allocation failed. */ int get_anon_bdev(dev_t *p) { int dev; /* * Many userspace utilities consider an FSID of 0 invalid. * Always return at least 1 from get_anon_bdev. */ dev = ida_alloc_range(&unnamed_dev_ida, 1, (1 << MINORBITS) - 1, GFP_ATOMIC); if (dev == -ENOSPC) dev = -EMFILE; if (dev < 0) return dev; *p = MKDEV(0, dev); return 0; } EXPORT_SYMBOL(get_anon_bdev); void free_anon_bdev(dev_t dev) { ida_free(&unnamed_dev_ida, MINOR(dev)); } EXPORT_SYMBOL(free_anon_bdev); int set_anon_super(struct super_block *s, void *data) { return get_anon_bdev(&s->s_dev); } EXPORT_SYMBOL(set_anon_super); void kill_anon_super(struct super_block *sb) { dev_t dev = sb->s_dev; generic_shutdown_super(sb); free_anon_bdev(dev); } EXPORT_SYMBOL(kill_anon_super); void kill_litter_super(struct super_block *sb) { if (sb->s_root) d_genocide(sb->s_root); kill_anon_super(sb); } EXPORT_SYMBOL(kill_litter_super); int set_anon_super_fc(struct super_block *sb, struct fs_context *fc) { return set_anon_super(sb, NULL); } EXPORT_SYMBOL(set_anon_super_fc); static int test_keyed_super(struct super_block *sb, struct fs_context *fc) { return sb->s_fs_info == fc->s_fs_info; } static int test_single_super(struct super_block *s, struct fs_context *fc) { return 1; } /** * vfs_get_super - Get a superblock with a search key set in s_fs_info. * @fc: The filesystem context holding the parameters * @keying: How to distinguish superblocks * @fill_super: Helper to initialise a new superblock * * Search for a superblock and create a new one if not found. The search * criterion is controlled by @keying. If the search fails, a new superblock * is created and @fill_super() is called to initialise it. * * @keying can take one of a number of values: * * (1) vfs_get_single_super - Only one superblock of this type may exist on the * system. This is typically used for special system filesystems. * * (2) vfs_get_keyed_super - Multiple superblocks may exist, but they must have * distinct keys (where the key is in s_fs_info). Searching for the same * key again will turn up the superblock for that key. * * (3) vfs_get_independent_super - Multiple superblocks may exist and are * unkeyed. Each call will get a new superblock. * * A permissions check is made by sget_fc() unless we're getting a superblock * for a kernel-internal mount or a submount. */ int vfs_get_super(struct fs_context *fc, enum vfs_get_super_keying keying, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { int (*test)(struct super_block *, struct fs_context *); struct super_block *sb; int err; switch (keying) { case vfs_get_single_super: case vfs_get_single_reconf_super: test = test_single_super; break; case vfs_get_keyed_super: test = test_keyed_super; break; case vfs_get_independent_super: test = NULL; break; default: BUG(); } sb = sget_fc(fc, test, set_anon_super_fc); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { err = fill_super(sb, fc); if (err) goto error; sb->s_flags |= SB_ACTIVE; fc->root = dget(sb->s_root); } else { fc->root = dget(sb->s_root); if (keying == vfs_get_single_reconf_super) { err = reconfigure_super(fc); if (err < 0) { dput(fc->root); fc->root = NULL; goto error; } } } return 0; error: deactivate_locked_super(sb); return err; } EXPORT_SYMBOL(vfs_get_super); int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, vfs_get_independent_super, fill_super); } EXPORT_SYMBOL(get_tree_nodev); int get_tree_single(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, vfs_get_single_super, fill_super); } EXPORT_SYMBOL(get_tree_single); int get_tree_single_reconf(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, vfs_get_single_reconf_super, fill_super); } EXPORT_SYMBOL(get_tree_single_reconf); int get_tree_keyed(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), void *key) { fc->s_fs_info = key; return vfs_get_super(fc, vfs_get_keyed_super, fill_super); } EXPORT_SYMBOL(get_tree_keyed); #ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; s->s_bdi = bdi_get(s->s_bdev->bd_bdi); if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue)) s->s_iflags |= SB_I_STABLE_WRITES; return 0; } static int set_bdev_super_fc(struct super_block *s, struct fs_context *fc) { return set_bdev_super(s, fc->sget_key); } static int test_bdev_super_fc(struct super_block *s, struct fs_context *fc) { return s->s_bdev == fc->sget_key; } /** * get_tree_bdev - Get a superblock based on a single block device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock */ int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *, struct fs_context *)) { struct block_device *bdev; struct super_block *s; fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; if (!(fc->sb_flags & SB_RDONLY)) mode |= FMODE_WRITE; if (!fc->source) return invalf(fc, "No source specified"); bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type); if (IS_ERR(bdev)) { errorf(fc, "%s: Can't open blockdev", fc->source); return PTR_ERR(bdev); } /* Once the superblock is inserted into the list by sget_fc(), s_umount * will protect the lockfs code from trying to start a snapshot while * we are mounting */ mutex_lock(&bdev->bd_fsfreeze_mutex); if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); blkdev_put(bdev, mode); return -EBUSY; } fc->sb_flags |= SB_NOSEC; fc->sget_key = bdev; s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) { blkdev_put(bdev, mode); return PTR_ERR(s); } if (s->s_root) { /* Don't summarily change the RO/RW state. */ if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { warnf(fc, "%pg: Can't mount, would change RO state", bdev); deactivate_locked_super(s); blkdev_put(bdev, mode); return -EBUSY; } /* * s_umount nests inside bd_mutex during * __invalidate_device(). blkdev_put() acquires * bd_mutex and can't be called under s_umount. Drop * s_umount temporarily. This is safe as we're * holding an active reference. */ up_write(&s->s_umount); blkdev_put(bdev, mode); down_write(&s->s_umount); } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, fc); if (error) { deactivate_locked_super(s); return error; } s->s_flags |= SB_ACTIVE; bdev->bd_super = s; } BUG_ON(fc->root); fc->root = dget(s->s_root); return 0; } EXPORT_SYMBOL(get_tree_bdev); static int test_bdev_super(struct super_block *s, void *data) { return (void *)s->s_bdev == data; } struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)) { struct block_device *bdev; struct super_block *s; fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; bdev = blkdev_get_by_path(dev_name, mode, fs_type); if (IS_ERR(bdev)) return ERR_CAST(bdev); /* * once the super is inserted into the list by sget, s_umount * will protect the lockfs code from trying to start a snapshot * while we are mounting */ mutex_lock(&bdev->bd_fsfreeze_mutex); if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); error = -EBUSY; goto error_bdev; } s = sget(fs_type, test_bdev_super, set_bdev_super, flags | SB_NOSEC, bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) goto error_s; if (s->s_root) { if ((flags ^ s->s_flags) & SB_RDONLY) { deactivate_locked_super(s); error = -EBUSY; goto error_bdev; } /* * s_umount nests inside bd_mutex during * __invalidate_device(). blkdev_put() acquires * bd_mutex and can't be called under s_umount. Drop * s_umount temporarily. This is safe as we're * holding an active reference. */ up_write(&s->s_umount); blkdev_put(bdev, mode); down_write(&s->s_umount); } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); goto error; } s->s_flags |= SB_ACTIVE; bdev->bd_super = s; } return dget(s->s_root); error_s: error = PTR_ERR(s); error_bdev: blkdev_put(bdev, mode); error: return ERR_PTR(error); } EXPORT_SYMBOL(mount_bdev); void kill_block_super(struct super_block *sb) { struct block_device *bdev = sb->s_bdev; fmode_t mode = sb->s_mode; bdev->bd_super = NULL; generic_shutdown_super(sb); sync_blockdev(bdev); WARN_ON_ONCE(!(mode & FMODE_EXCL)); blkdev_put(bdev, mode | FMODE_EXCL); } EXPORT_SYMBOL(kill_block_super); #endif struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)) { int error; struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); return ERR_PTR(error); } s->s_flags |= SB_ACTIVE; return dget(s->s_root); } EXPORT_SYMBOL(mount_nodev); int reconfigure_single(struct super_block *s, int flags, void *data) { struct fs_context *fc; int ret; /* The caller really need to be passing fc down into mount_single(), * then a chunk of this can be removed. [Bollocks -- AV] * Better yet, reconfiguration shouldn't happen, but rather the second * mount should be rejected if the parameters are not compatible. */ fc = fs_context_for_reconfigure(s->s_root, flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); ret = parse_monolithic_mount_data(fc, data); if (ret < 0) goto out; ret = reconfigure_super(fc); out: put_fs_context(fc); return ret; } static int compare_single(struct super_block *s, void *p) { return 1; } struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)) { struct super_block *s; int error; s = sget(fs_type, compare_single, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (!error) s->s_flags |= SB_ACTIVE; } else { error = reconfigure_single(s, flags, data); } if (unlikely(error)) { deactivate_locked_super(s); return ERR_PTR(error); } return dget(s->s_root); } EXPORT_SYMBOL(mount_single); /** * vfs_get_tree - Get the mountable root * @fc: The superblock configuration context. * * The filesystem is invoked to get or create a superblock which can then later * be used for mounting. The filesystem places a pointer to the root to be * used for mounting in @fc->root. */ int vfs_get_tree(struct fs_context *fc) { struct super_block *sb; int error; if (fc->root) return -EBUSY; /* Get the mountable root in fc->root, with a ref on the root and a ref * on the superblock. */ error = fc->ops->get_tree(fc); if (error < 0) return error; if (!fc->root) { pr_err("Filesystem %s get_tree() didn't set fc->root\n", fc->fs_type->name); /* We don't know what the locking state of the superblock is - * if there is a superblock. */ BUG(); } sb = fc->root->d_sb; WARN_ON(!sb->s_bdi); /* * Write barrier is for super_cache_count(). We place it before setting * SB_BORN as the data dependency between the two functions is the * superblock structure contents that we just set up, not the SB_BORN * flag. */ smp_wmb(); sb->s_flags |= SB_BORN; error = security_sb_set_mnt_opts(sb, fc->security, 0, NULL); if (unlikely(error)) { fc_drop_locked(fc); return error; } /* * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE * but s_maxbytes was an unsigned long long for many releases. Throw * this warning for a little while to try and catch filesystems that * violate this rule. */ WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " "negative value (%lld)\n", fc->fs_type->name, sb->s_maxbytes); return 0; } EXPORT_SYMBOL(vfs_get_tree); /* * Setup private BDI for given superblock. It gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...) { struct backing_dev_info *bdi; int err; va_list args; bdi = bdi_alloc(NUMA_NO_NODE); if (!bdi) return -ENOMEM; va_start(args, fmt); err = bdi_register_va(bdi, fmt, args); va_end(args); if (err) { bdi_put(bdi); return err; } WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi; sb->s_iflags |= SB_I_PERSB_BDI; return 0; } EXPORT_SYMBOL(super_setup_bdi_name); /* * Setup private BDI for given superblock. I gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi(struct super_block *sb) { static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name, atomic_long_inc_return(&bdi_seq)); } EXPORT_SYMBOL(super_setup_bdi); /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait * @level: type of writers we wait for (normal vs page fault) * * This function waits until there are no writers of given type to given file * system. */ static void sb_wait_write(struct super_block *sb, int level) { percpu_down_write(sb->s_writers.rw_sem + level-1); } /* * We are going to return to userspace and forget about these locks, the * ownership goes to the caller of thaw_super() which does unlock(). */ static void lockdep_sb_freeze_release(struct super_block *sb) { int level; for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } /* * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb). */ static void lockdep_sb_freeze_acquire(struct super_block *sb) { int level; for (level = 0; level < SB_FREEZE_LEVELS; ++level) percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } static void sb_freeze_unlock(struct super_block *sb, int level) { for (level--; level >= 0; level--) percpu_up_write(sb->s_writers.rw_sem + level); } /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock * * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs will return * -EBUSY. * * During this function, sb->s_writers.frozen goes through these values: * * SB_UNFROZEN: File system is normal, all writes progress as usual. * * SB_FREEZE_WRITE: The file system is in the process of being frozen. New * writes should be blocked, though page faults are still allowed. We wait for * all writes to complete and then proceed to the next stage. * * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked * but internal fs threads can still modify the filesystem (although they * should not dirty new pages or inodes), writeback can run etc. After waiting * for all running page faults we sync the filesystem which will clean all * dirty pages and inodes (no new dirty pages or inodes can be created when * sync is running). * * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs * modification are blocked (e.g. XFS preallocation truncation on inode * reclaim). This is usually implemented by blocking new transactions for * filesystems that have them and need this additional guard. After all * internal writers are finished we call ->freeze_fs() to finish filesystem * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is * mostly auxiliary for filesystems to verify they do not modify frozen fs. * * sb->s_writers.frozen is protected by sb->s_umount. */ int freeze_super(struct super_block *sb) { int ret; atomic_inc(&sb->s_active); down_write(&sb->s_umount); if (sb->s_writers.frozen != SB_UNFROZEN) { deactivate_locked_super(sb); return -EBUSY; } if (!(sb->s_flags & SB_BORN)) { up_write(&sb->s_umount); return 0; /* sic - it's "nothing to do" */ } if (sb_rdonly(sb)) { /* Nothing to do really... */ sb->s_writers.frozen = SB_FREEZE_COMPLETE; up_write(&sb->s_umount); return 0; } sb->s_writers.frozen = SB_FREEZE_WRITE; /* Release s_umount to preserve sb_start_write -> s_umount ordering */ up_write(&sb->s_umount); sb_wait_write(sb, SB_FREEZE_WRITE); down_write(&sb->s_umount); /* Now we go and block page faults... */ sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; sb_wait_write(sb, SB_FREEZE_PAGEFAULT); /* All writers are done so after syncing there won't be dirty data */ ret = sync_filesystem(sb); if (ret) { sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; } /* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; sb_wait_write(sb, SB_FREEZE_FS); if (sb->s_op->freeze_fs) { ret = sb->s_op->freeze_fs(sb); if (ret) { printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_FS); wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; } } /* * For debugging purposes so that fs can warn if it sees write activity * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ sb->s_writers.frozen = SB_FREEZE_COMPLETE; lockdep_sb_freeze_release(sb); up_write(&sb->s_umount); return 0; } EXPORT_SYMBOL(freeze_super); /** * thaw_super -- unlock filesystem * @sb: the super to thaw * * Unlocks the filesystem and marks it writeable again after freeze_super(). */ static int thaw_super_locked(struct super_block *sb) { int error; if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) { up_write(&sb->s_umount); return -EINVAL; } if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; goto out; } lockdep_sb_freeze_acquire(sb); if (sb->s_op->unfreeze_fs) { error = sb->s_op->unfreeze_fs(sb); if (error) { printk(KERN_ERR "VFS:Filesystem thaw failed\n"); lockdep_sb_freeze_release(sb); up_write(&sb->s_umount); return error; } } sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_FS); out: wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return 0; } int thaw_super(struct super_block *sb) { down_write(&sb->s_umount); return thaw_super_locked(sb); } EXPORT_SYMBOL(thaw_super); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H #include <linux/mm_types_task.h> #include <linux/auxvec.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) #define INIT_PASID 0 struct address_space; struct mem_cgroup; /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. * * If you allocate the page using alloc_pages(), you can use some of the * space in struct page for your own purposes. The five words in the main * union are available, except for bit 0 of the first word which must be * kept clear. Many users use this word to store a pointer to an object * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * * If your page will not be mapped to userspace, you can also use the four * bytes in the mapcount union, but you must call page_mapcount_reset() * before freeing it. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the * refcount does not cause problems. On receiving the page from * alloc_pages(), the refcount will be positive. * * If you allocate pages of order > 0, you can use some of the fields * in each subpage, but you may need to restore some of their values * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and * counters. That requires that freelist & counters be adjacent and * double-word aligned. We align all struct pages to double-word * boundaries, and ensure that 'freelist' is aligned within the * struct. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) #else #define _struct_page_alignment #endif struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ /* * Five words (20/40 bytes) are available in this union. * WARNING: bit 0 of the first word is used for PageTail(). That * means the other users of this union MUST NOT use the bit to * avoid collision and false-positive PageTail(). */ union { struct { /* Page cache and anonymous pages */ /** * @lru: Pageout list, eg. active_list protected by * pgdat->lru_lock. Sometimes used as a generic list * by the page owner. */ struct list_head lru; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. * Used for swp_entry_t if PageSwapCache. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; }; struct { /* page_pool used by netstack */ /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { struct list_head slab_list; struct { /* Partial pages */ struct page *next; #ifdef CONFIG_64BIT int pages; /* Nr of pages left */ int pobjects; /* Approximate count */ #else short int pages; short int pobjects; #endif }; }; struct kmem_cache *slab_cache; /* not slob */ /* Double-word boundary */ void *freelist; /* first free object */ union { void *s_mem; /* slab: first object */ unsigned long counters; /* SLUB */ struct { /* SLUB */ unsigned inuse:16; unsigned objects:15; unsigned frozen:1; }; }; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ /* First tail page only */ unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; unsigned int compound_nr; /* 1 << compound_order */ }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ atomic_t hpage_pinned_refcount; /* For both global and memcg */ struct list_head deferred_list; }; struct { /* Page table pages */ unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ union { struct mm_struct *pt_mm; /* x86 pgds only */ atomic_t pt_frag_refcount; /* powerpc */ #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE atomic_t pt_share_count; #endif }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; #endif }; struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; /* * ZONE_DEVICE private pages are counted as being * mapped so the next 3 words hold the mapping, index, * and private fields from the source anonymous or * page cache page while the page is migrated to device * private memory. * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also * use the mapping, index, and private fields when * pmem backed DAX files are mapped. */ }; /** @rcu_head: You can use this to free a page by RCU. */ struct rcu_head rcu_head; }; union { /* This union is 4 bytes in size. */ /* * If the page can be mapped to userspace, encodes the number * of times this page is referenced by a page table. */ atomic_t _mapcount; /* * If the page is neither PageSlab nor mappable to userspace, * the value stored here may help determine what this page * is used for. See page-flags.h for a list of page types * which are currently stored here. */ unsigned int page_type; unsigned int active; /* SLAB */ int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; #ifdef CONFIG_MEMCG union { struct mem_cgroup *mem_cgroup; struct obj_cgroup **obj_cgroups; }; #endif /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with * highmem some memory is mapped into kernel virtual memory * dynamically, so we need a place to store that address. * Note that this field could be 16 bits on x86 ... ;) * * Architectures with slow multiplication can define * WANT_PAGE_VIRTUAL in asm/page.h */ #if defined(WANT_PAGE_VIRTUAL) void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif } _struct_page_alignment; static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; } static inline atomic_t *compound_pincount_ptr(struct page *page) { return &page[2].hpage_pinned_refcount; } /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) { page->private = private; } struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) __u16 offset; __u16 size; #else __u32 offset; #endif /* we maintain a pagecount bias, so that we dont dirty cache line * containing page->_refcount every time we allocate a fragment. */ unsigned int pagecnt_bias; bool pfmemalloc; }; typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. */ struct vm_region { struct rb_node vm_rb; /* link in global region tree */ vm_flags_t vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for * this region */ }; #ifdef CONFIG_USERFAULTFD #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, }) struct vm_userfaultfd_ctx { struct userfaultfd_ctx *ctx; }; #else /* CONFIG_USERFAULTFD */ #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {}) struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ unsigned long vm_start; /* Our start address within vm_mm. */ unsigned long vm_end; /* The first byte after our end address within vm_mm. */ /* linked list of VM areas per task, sorted by address */ struct vm_area_struct *vm_next, *vm_prev; struct rb_node vm_rb; /* * Largest free memory gap in bytes to the left of this VMA. * Either between this VMA and vma->vm_prev, or between one of the * VMAs below us in the VMA rbtree and its ->vm_prev. This helps * get_unmapped_area find a free area of the right size. */ unsigned long rb_subtree_gap; /* Second cache line starts here. */ struct mm_struct *vm_mm; /* The address space we belong to. */ /* * Access permissions of this VMA. * See vmf_insert_mixed_prot() for discussion. */ pgprot_t vm_page_prot; unsigned long vm_flags; /* Flags, see mm.h. */ /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. */ struct { struct rb_node rb; unsigned long rb_subtree_last; } shared; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units */ struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; #endif #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; struct kioctx_table; struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* Base adresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER /** * @membarrier_state: Flags controlling membarrier behavior. * * This field is close to @pgd to hopefully fit in the same * cache-line, which needs to be touched by switch_mm(). */ atomic_t membarrier_state; #endif /** * @mm_users: The number of users including userspace. * * Use mmget()/mmget_not_zero()/mmput() to modify. When this * drops to 0 (i.e. when the task exits and there are no other * temporary reference holders), we also release a reference on * @mm_count (which may then free the &struct mm_struct if * @mm_count also drops to 0). */ atomic_t mm_users; /** * @mm_count: The number of references to &struct mm_struct * (@mm_users count as 1). * * Use mmgrab()/mmdrop() to modify. When this drops to 0, the * &struct mm_struct is freed. */ atomic_t mm_count; /** * @has_pinned: Whether this mm has pinned any pages. This can * be either replaced in the future by @pinned_vm when it * becomes stable, or grow into a counter on its own. We're * aggresive on this bit now - even if the pinned pages were * unpinned later on, we'll still keep this bit set for the * lifecycle of this mm just for simplicity. */ atomic_t has_pinned; #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some * counters */ /* * With some kernel config, the current mmap_lock's offset * inside 'mm_struct' is at 0x120, which is very optimal, as * its two hot fields 'count' and 'owner' sit in 2 different * cachelines, and when mmap_lock is highly contended, both * of the 2 fields will be accessed frequently, current layout * will help to reduce cache bouncing. * * So please be careful with adding new fields before * mmap_lock, which can easily push the 2 fields into one * cacheline. */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off * init_mm.mmlist, and are protected * by mmlist_lock */ unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ atomic64_t pinned_vm; /* Refcount permanently increased */ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; /** * @write_protect_seq: Locked when any thread is write * protecting pages mapped by this mm to enforce a later COW, * for instance during page table copying for fork(). */ seqcount_t write_protect_seq; spinlock_t arg_lock; /* protect the below fields */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ /* * Special counters, in some configurations protected by the * page_table_lock, in other configurations by being atomic. */ struct mm_rss_stat rss_stat; struct linux_binfmt *binfmt; /* Architecture-specific MM context */ mm_context_t context; unsigned long flags; /* Must use atomic bitops to access */ struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG /* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in * order for it to be changed: * * current == mm->owner * current->mm != mm * new_owner->mm == mm * new_owner->alloc_lock is held */ struct task_struct __rcu *owner; #endif struct user_namespace *user_ns; /* store ref to file /proc/<pid>/exe symlink points to */ struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING /* * numa_next_scan is the next time that the PTEs will be marked * pte_numa. NUMA hinting faults will gather statistics and * migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; /* Restart point for scanning and setting pte_numa */ unsigned long numa_scan_offset; /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when * moving a PROT_NONE or PROT_NUMA mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; #ifdef CONFIG_IOMMU_SUPPORT u32 pasid; #endif } __randomize_layout; /* * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ unsigned long cpu_bitmap[]; }; extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { return (struct cpumask *)&mm->cpu_bitmap; } struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } struct vm_fault; /** * typedef vm_fault_t - Return type for page fault handlers. * * Page fault handlers return a bitmask of %VM_FAULT values. */ typedef __bitwise unsigned int vm_fault_t; /** * enum vm_fault_reason - Page fault handlers return a bitmask of * these values to tell the core VM what happened when handling the * fault. Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. * * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage * @VM_FAULT_WRITE: Special case for get_user_pages * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits * @VM_FAULT_SIGSEGV: segmentation fault * @VM_FAULT_NOPAGE: ->fault installed the pte, not return page * @VM_FAULT_LOCKED: ->fault locked the returned page * @VM_FAULT_RETRY: ->fault blocked, must retry * @VM_FAULT_FALLBACK: huge page fault failed, fall back to small * @VM_FAULT_DONE_COW: ->fault has fully handled COW * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, VM_FAULT_WRITE = (__force vm_fault_t)0x000008, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100, VM_FAULT_LOCKED = (__force vm_fault_t)0x000200, VM_FAULT_RETRY = (__force vm_fault_t)0x000400, VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) #define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK) #define VM_FAULT_RESULT_TRACE \ { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ { VM_FAULT_WRITE, "WRITE" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ { VM_FAULT_NOPAGE, "NOPAGE" }, \ { VM_FAULT_LOCKED, "LOCKED" }, \ { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ /* * If .fault is not provided, this points to a * NULL-terminated array of pages that back the special mapping. * * This must not be NULL unless .fault is provided. */ struct page **pages; /* * If non-NULL, then this is called to resolve page faults * on the special mapping. If used, .pages is not checked. */ vm_fault_t (*fault)(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); }; enum tlb_flush_reason { TLB_FLUSH_ON_TASK_SWITCH, TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, NR_TLB_FLUSH_REASONS, }; /* * A swap entry has to fit into a "unsigned long", as the entry is hidden * in the "index" field of the swapper address space. */ typedef struct { unsigned long val; } swp_entry_t; #endif /* _LINUX_MM_TYPES_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); mark_page_accessed(bh->b_page); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the page has dirty or writeback buffers. If all the buffers * are unlocked and clean then the PageDirty information is stale. If * any of the pages are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; if (PageWriteback(page)) *writeback = true; head = page_buffers(page); bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. This is what ll_rw_block uses too. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { put_bh(bh); __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's * private_lock. * * Hack idea: for the blockdev mapping, private_lock contention * may be quite high. This code could TryLock the page, and if that * succeeds, there is no need to take private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct page *page; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; spin_lock(&bd_mapping->private_lock); if (!page_has_buffers(page)) goto out_unlock; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); put_page(page); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; int page_uptodate = 1; BUG_ON(!buffer_async_read(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); SetPageError(page); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) page_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); /* * If none of the buffers had errors and they are all * uptodate then we can set the page uptodate. */ if (page_uptodate && !PageError(page)) SetPageUptodate(page); unlock_page(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } struct decrypt_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void decrypt_bh(struct work_struct *work) { struct decrypt_bh_ctx *ctx = container_of(work, struct decrypt_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_page() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ if (uptodate && fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { INIT_WORK(&ctx->work, decrypt_bh); ctx->bh = bh; fscrypt_enqueue_decrypt_work(&ctx->work); return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_page() - pages which are unlocked * during I/O, and which have PageWriteback cleared upon I/O completion. */ void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; BUG_ON(!buffer_async_write(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); end_page_writeback(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } EXPORT_SYMBOL(end_buffer_async_write); /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for private_list is via the private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->private_lock does *not* protect mapping->private_list! In fact, * mapping->private_list will always be protected by the backing blockdev's * ->private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->private_list via these * utility functions are free to use private_lock and private_list for * whatever they want. The only requirement is that list_empty(private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as * you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } void emergency_thaw_bdev(struct super_block *sb) { while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->private_data; if (buffer_mapping == NULL || list_empty(&mapping->private_list)) return 0; return fsync_buffers_list(&buffer_mapping->private_lock, &mapping->private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) ll_rw_block(REQ_OP_WRITE, 0, 1, &bh); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_page->mapping; mark_buffer_dirty(bh); if (!mapping->private_data) { mapping->private_data = buffer_mapping; } else { BUG_ON(mapping->private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /* * Mark the page dirty, and set it dirty in the page cache, and mark the inode * dirty. * * If warn is true, then emit a warning if the page is not uptodate and has * not been truncated. * * The caller must hold lock_page_memcg(). */ void __set_page_dirty(struct page *page, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); account_page_dirtied(page, mapping); __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } EXPORT_SYMBOL_GPL(__set_page_dirty); /* * Add a page to the dirty page list. * * It is a sad fact of life that this function is called from several places * deeply under spinlocking. It may not sleep. * * If the page has buffers, the uptodate buffers are set dirty, to preserve * dirty-state coherency between the page and the buffers. It the page does * not have buffers then when they are later attached they will all be set * dirty. * * The buffers are dirtied before the page is dirtied. There's a small race * window in which a writepage caller may see the page cleanness but not the * buffer dirtiness. That's fine. If this code were to set the page dirty * before the buffers, a concurrent writepage caller could clear the page dirty * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean * page on the dirty page list. * * We use private_lock to lock against try_to_free_buffers while using the * page's buffer list. Also use this to protect against clean buffers being * added to the page after it was set dirty. * * FIXME: may need to call ->reservepage here as well. That's rather up to the * address_space though. */ int __set_page_dirty_buffers(struct page *page) { int newly_dirty; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) return !TestSetPageDirty(page); spin_lock(&mapping->private_lock); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page->mem_cgroup migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); if (newly_dirty) __set_page_dirty(page, mapping, 1); unlock_page_memcg(page); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(__set_page_dirty_buffers); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->private_lock); } return ret; } /* * Create the appropriate buffers when given a page for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { struct buffer_head *bh, *head; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; long offset; struct mem_cgroup *memcg, *old_memcg; if (retry) gfp |= __GFP_NOFAIL; memcg = get_mem_cgroup_from_page(page); old_memcg = set_active_memcg(memcg); head = NULL; offset = PAGE_SIZE; while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its page */ set_bh_page(bh, page, offset); } out: set_active_memcg(old_memcg); mem_cgroup_put(memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; attach_page_private(page, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = i_size_read(bdev->bd_inode); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev page's buffers. */ static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache page that contains the requested block. * * This is used purely for blockdev mappings. */ static int grow_dev_page(struct block_device *bdev, sector_t block, pgoff_t index, int size, int sizebits, gfp_t gfp) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; sector_t end_block; int ret = 0; gfp_t gfp_mask; gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and * will endlessly loop on improvised global reclaim. Prefer * looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp_mask |= __GFP_NOFAIL; page = find_or_create_page(inode->i_mapping, index, gfp_mask); BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); goto done; } if (!try_to_free_buffers(page)) goto failed; } /* * Allocate some buffers for this page */ bh = alloc_page_buffers(page, size, true); /* * Link the page to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the page lock. */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); put_page(page); return ret; } /* * Create buffers for the specified block device block's page. If * that page was dirty, the buffers are set dirty also. */ static int grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) { pgoff_t index; int sizebits; sizebits = -1; do { sizebits++; } while ((size << sizebits) < PAGE_SIZE); index = block >> sizebits; /* * Check for a block which wants to lie outside our maximum possible * pagecache index. (this comparison is done using sector_t types). */ if (unlikely(index != block >> sizebits)) { printk(KERN_ERR "%s: requested out-of-range block %llu for " "device %pg\n", __func__, (unsigned long long)block, bdev); return -EIO; } /* Create a page with the proper size buffers.. */ return grow_dev_page(bdev, block, index, size, sizebits, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); printk(KERN_ERR "logical block size: %d\n", bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { struct buffer_head *bh; int ret; bh = __find_get_block(bdev, block, size); if (bh) return bh; ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_page() against that page will discover all the uptodate * buffers, will set the page uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct page *page = bh->b_page; struct address_space *mapping = NULL; lock_page_memcg(page); if (!TestSetPageDirty(page)) { mapping = page_mapping(page); if (mapping) __set_page_dirty(page, mapping, 0); } unlock_page_memcg(page); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { struct super_block *sb; set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_page && bh->b_page->mapping) mapping_set_error(bh->b_page->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); rcu_read_lock(); sb = READ_ONCE(bh->b_bdev->bd_super); if (sb) errseq_set(&sb->s_wb_err, -EIO); rcu_read_unlock(); } EXPORT_SYMBOL(mark_buffer_write_io_error); /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean * and unlocked then try_to_free_buffers() may strip the buffers from the page * in preparation for freeing it (sometimes, rarely, buffers are removed from * a page but it ends up not being freed, and buffers may later be reattached). */ void __brelse(struct buffer_head * buf) { if (atomic_read(&buf->b_count)) { put_bh(buf); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /* * bforget() is like brelse(), except it discards any * potentially dirty data. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_page->mapping; spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->private_lock); } __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL */ struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } EXPORT_SYMBOL(__find_get_block); /* * __getblk_gfp() will locate (and, if necessary, create) the buffer_head * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * * __getblk_gfp() will lock up the machine if grow_dev_page's * try_to_free_buffers() attempt is failing. FIXME, perhaps? */ struct buffer_head * __getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); might_sleep(); if (bh == NULL) bh = __getblk_slow(bdev, block, size, gfp); return bh; } EXPORT_SYMBOL(__getblk_gfp); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = __getblk(bdev, block, size); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead); void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead_gfp); /** * __bread_gfp() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * @gfp: page allocation flag * * Reads a specified block, and returns buffer head that contains it. * The page cache can be allocated from non-movable area * not to prevent page migration if you set gfp to zero. * It returns NULL if the block was unreadable. */ struct buffer_head * __bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } put_cpu_var(bh_lrus); } static bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset) { bh->b_page = page; BUG_ON(offset >= PAGE_SIZE); if (PageHighMem(page)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = page_address(page) + offset; } EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state, b_state_old; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = bh->b_state; for (;;) { b_state_old = cmpxchg(&bh->b_state, b_state, (b_state & ~BUFFER_FLAGS_DISCARD)); if (b_state_old == b_state) break; b_state = b_state_old; } unlock_buffer(bh); } /** * block_invalidatepage - invalidate part or all of a buffer-backed page * * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * block_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { struct buffer_head *head, *bh, *next; unsigned int curr_off = 0; unsigned int stop = length + offset; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) goto out; /* * Check for overflow */ BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire page is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == PAGE_SIZE) try_to_release_page(page, 0); out: return; } EXPORT_SYMBOL(block_invalidatepage); /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers * is already excluded via the page lock. */ void create_empty_buffers(struct page *page, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; head = alloc_page_buffers(page, blocksize, true); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&page->mapping->private_lock); if (PageUptodate(page) || PageDirty(page)) { bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (PageUptodate(page)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct pagevec pvec; pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits); pagevec_init(&pvec); while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) { count = pagevec_count(&pvec); for (i = 0; i < count; i++) { struct page *page = pvec.pages[i]; if (!page_has_buffers(page)) continue; /* * We use page lock instead of bd_mapping->private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ lock_page(page); /* Recheck when the page is locked which pins bhs */ if (!page_has_buffers(page)) goto unlock_page; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: unlock_page(page); } pagevec_release(&pvec); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); /* * Size is a power-of-two in the range 512..PAGE_SIZE, * and the case we care about most is PAGE_SIZE. * * So this *could* possibly be written with those * constraints in mind (relevant mostly if some * architecture has a slow bit-scan instruction) */ static inline int block_size_bits(unsigned int blocksize) { return ilog2(blocksize); } static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) { BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), b_state); return page_buffers(page); } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_page is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_page() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_page() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; unsigned int blocksize, bbits; int nr_underway = 0; int write_flags = wbc_to_write_flags(wbc); head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from __set_page_dirty_buffers * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the page stays dirty. * * Buffers outside i_size may be dirtied by __set_page_dirty_buffers; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); last_block = (i_size_read(inode) - 1) >> bbits; /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this page can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_page() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, handler); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The page and its buffers are protected by PageWriteback(), so we can * drop the bh refcounts early. */ BUG_ON(PageWriteback(page)); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); err = 0; done: if (nr_underway == 0) { /* * The page was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * ll_rw_block/submit_bh. A rare case. */ end_page_writeback(page); /* * The page and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The page is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, handler); } else { /* * The buffer may have been set dirty during * attachment to a dirty page. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); SetPageError(page); BUG_ON(PageWriteback(page)); mapping_set_error(page->mapping, err); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); goto done; } EXPORT_SYMBOL(__block_write_full_page); /* * If a page has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; bh = head = page_buffers(page); block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!PageUptodate(page)) { unsigned start, size; start = max(from, block_start); size = min(to, block_end) - start; zero_user(page, start, size); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(page_zero_new_buffers); static void iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, struct iomap *iomap) { loff_t offset = block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ BUG_ON(offset >= iomap->offset + iomap->length); switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); break; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); break; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) set_buffer_new(bh); bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); break; } } int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, struct iomap *iomap) { unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; unsigned blocksize, bbits; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!PageLocked(page)); BUG_ON(from > PAGE_SIZE); BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); for(bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) { err = get_block(inode, block, bh, 1); if (err) break; } else { iomap_to_bh(inode, block, bh, iomap); } if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (PageUptodate(page)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) zero_user_segments(page, to, block_end, block_start, from); continue; } } if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) page_zero_new_buffers(page, from, to); return err; } int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(page, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); static int __block_commit_write(struct inode *inode, struct page *page, unsigned from, unsigned to) { unsigned block_start, block_end; int partial = 0; unsigned blocksize; struct buffer_head *bh, *head; bh = head = page_buffers(page); blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = 1; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus readpage() for * the next read(). Here we 'discover' whether the page went * uptodate as a result of this (potentially partial) write. */ if (!partial) SetPageUptodate(page); return 0; } /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; status = __block_write_begin(page, pos, len, get_block); if (unlikely(status)) { unlock_page(page); put_page(page); page = NULL; } *pagep = page; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; unsigned start; start = pos & (PAGE_SIZE - 1); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so we * don't have to worry about a readpage reading them and * overwriting a partial write. However if we have encountered * a short write and only partially written into a buffer, it * will not be marked uptodate, so a readpage might come in and * destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate page as a zero-length write, and force the * caller to redo the whole thing. */ if (!PageUptodate(page)) copied = 0; page_zero_new_buffers(page, start+copied, start+len); } flush_dcache_page(page); /* This could be a short (even 0-length) commit */ __block_commit_write(inode, page, start, start+copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a page are * uptodate or not. * * Returns true if all buffers which correspond to a file portion * we want to read are uptodate. */ int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; int ret = 1; if (!page_has_buffers(page)) return 0; head = page_buffers(page); blocksize = head->b_size; to = min_t(unsigned, PAGE_SIZE - from, count); to = from + to; if (from < blocksize && to > PAGE_SIZE - blocksize) return 0; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = 0; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the page asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * page struct once IO has completed. */ int block_read_full_page(struct page *page, get_block_t *get_block) { struct inode *inode = page->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); iblock = (sector_t)page->index << (PAGE_SHIFT - bbits); lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) SetPageError(page); } if (!buffer_mapped(bh)) { zero_user(page, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } arr[nr++] = bh; } while (i++, iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) SetPageMappedToDisk(page); if (!nr) { /* * All buffers are uptodate - we can set the page uptodate * as well. But not if get_block() returned an error. */ if (!PageError(page)) SetPageUptodate(page); unlock_page(page); return 0; } /* Stage two: lock the buffers */ for (i = 0; i < nr; i++) { bh = arr[i]; lock_buffer(bh); mark_buffer_async_read(bh); } /* * Stage 3: start the IO. Check for uptodateness * inside the buffer lock in case another process reading * the underlying blockdev brought it uptodate (the sct fix). */ for (i = 0; i < nr; i++) { bh = arr[i]; if (buffer_uptodate(bh)) end_buffer_async_read(bh, 1); else submit_bh(REQ_OP_READ, 0, bh); } return 0; } EXPORT_SYMBOL(block_read_full_page); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_CONT_EXPAND, &page, &fsdata); if (err) goto out; err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, flags, pagep, get_block); } EXPORT_SYMBOL(cont_write_begin); int block_commit_write(struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; __block_commit_write(inode,page,from,to); return 0; } EXPORT_SYMBOL(block_commit_write); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || (page_offset(page) > size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } /* page is wholly or partially inside EOF */ if (((page->index + 1) << PAGE_SHIFT) > size) end = size & ~PAGE_MASK; else end = PAGE_SIZE; ret = __block_write_begin(page, 0, end, get_block); if (!ret) ret = block_commit_write(page, 0, end); if (unlikely(ret < 0)) goto out_unlock; set_page_dirty(page); wait_for_stable_page(page); return 0; out_unlock: unlock_page(page); return ret; } EXPORT_SYMBOL(block_page_mkwrite); /* * nobh_write_begin()'s prereads are special: the buffer_heads are freed * immediately, while under the page lock. So it needs a special end_io * handler which does not touch the bh after unlocking it. */ static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); } /* * Attach the singly-linked list of buffers created by nobh_write_begin, to * the page (converting it to circular linked list and taking care of page * dirty races). */ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh; BUG_ON(!PageLocked(page)); spin_lock(&page->mapping->private_lock); bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (!bh->b_this_page) bh->b_this_page = head; bh = bh->b_this_page; } while (bh != head); attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } /* * On entry, the page is fully not uptodate. * On exit the page is fully uptodate in the areas outside (from,to) * The filesystem needs to handle block truncation upon failure. */ int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) { struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocksize = 1 << blkbits; struct buffer_head *head, *bh; struct page *page; pgoff_t index; unsigned from, to; unsigned block_in_page; unsigned block_start, block_end; sector_t block_in_file; int nr_reads = 0; int ret = 0; int is_mapped_to_disk = 1; index = pos >> PAGE_SHIFT; from = pos & (PAGE_SIZE - 1); to = from + len; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; *fsdata = NULL; if (page_has_buffers(page)) { ret = __block_write_begin(page, pos, len, get_block); if (unlikely(ret)) goto out_release; return ret; } if (PageMappedToDisk(page)) return 0; /* * Allocate buffers so that we can keep track of state, and potentially * attach them to the page if an error occurs. In the common case of * no error, they will just be freed again without ever being attached * to the page (which is all OK, because we're under the page lock). * * Be careful: the buffer linked list is a NULL terminated one, rather * than the circular one we're used to. */ head = alloc_page_buffers(page, blocksize, false); if (!head) { ret = -ENOMEM; goto out_release; } block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); /* * We loop across all blocks in the page, whether or not they are * part of the affected region. This is so we can discover if the * page is fully mapped-to-disk. */ for (block_start = 0, block_in_page = 0, bh = head; block_start < PAGE_SIZE; block_in_page++, block_start += blocksize, bh = bh->b_this_page) { int create; block_end = block_start + blocksize; bh->b_state = 0; create = 1; if (block_start >= to) create = 0; ret = get_block(inode, block_in_file + block_in_page, bh, create); if (ret) goto failed; if (!buffer_mapped(bh)) is_mapped_to_disk = 0; if (buffer_new(bh)) clean_bdev_bh_alias(bh); if (PageUptodate(page)) { set_buffer_uptodate(bh); continue; } if (buffer_new(bh) || !buffer_mapped(bh)) { zero_user_segments(page, block_start, from, to, block_end); continue; } if (buffer_uptodate(bh)) continue; /* reiserfs does this */ if (block_start < from || block_end > to) { lock_buffer(bh); bh->b_end_io = end_buffer_read_nobh; submit_bh(REQ_OP_READ, 0, bh); nr_reads++; } } if (nr_reads) { /* * The page is locked, so these buffers are protected from * any VM or truncate activity. Hence we don't need to care * for the buffer_head refcounts. */ for (bh = head; bh; bh = bh->b_this_page) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } if (ret) goto failed; } if (is_mapped_to_disk) SetPageMappedToDisk(page); *fsdata = head; /* to be released by nobh_write_end */ return 0; failed: BUG_ON(!ret); /* * Error recovery is a bit difficult. We need to zero out blocks that * were newly allocated, and dirty them to ensure they get written out. * Buffers need to be attached to the page at this point, otherwise * the handling of potential IO errors during writeout would be hard * (could try doing synchronous writeout, but what if that fails too?) */ attach_nobh_buffers(page, head); page_zero_new_buffers(page, from, to); out_release: unlock_page(page); put_page(page); *pagep = NULL; return ret; } EXPORT_SYMBOL(nobh_write_begin); int nobh_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; struct buffer_head *head = fsdata; struct buffer_head *bh; BUG_ON(fsdata != NULL && page_has_buffers(page)); if (unlikely(copied < len) && head) attach_nobh_buffers(page, head); if (page_has_buffers(page)) return generic_write_end(file, mapping, pos, len, copied, page, fsdata); SetPageUptodate(page); set_page_dirty(page); if (pos+copied > inode->i_size) { i_size_write(inode, pos+copied); mark_inode_dirty(inode); } unlock_page(page); put_page(page); while (head) { bh = head; head = head->b_this_page; free_buffer_head(bh); } return copied; } EXPORT_SYMBOL(nobh_write_end); /* * nobh_writepage() - based on block_full_write_page() except * that it tries to operate without attaching bufferheads to * the page. */ int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; int ret; /* Is the page fully inside i_size? */ if (page->index < end_index) goto out; /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) ret = __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); return ret; } EXPORT_SYMBOL(nobh_writepage); int nobh_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head map_bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (page_has_buffers(page)) { has_buffers: unlock_page(page); put_page(page); return block_truncate_page(mapping, from, get_block); } /* Find the buffer that contains "offset" */ pos = blocksize; while (offset >= pos) { iblock++; pos += blocksize; } map_bh.b_size = blocksize; map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(&map_bh)) goto unlock; /* Ok, it's mapped. Make sure it's up-to-date */ if (!PageUptodate(page)) { err = mapping->a_ops->readpage(NULL, page); if (err) { put_page(page); goto out; } lock_page(page); if (!PageUptodate(page)) { err = -EIO; goto unlock; } if (page_has_buffers(page)) goto has_buffers; } zero_user(page, offset, length); set_page_dirty(page); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(nobh_truncate_page); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head *bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); /* Find the buffer that contains "offset" */ bh = page_buffers(page); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } err = 0; if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (PageUptodate(page)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = -EIO; ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; } zero_user(page, offset, length); mark_buffer_dirty(bh); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces */ int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; /* Is the page fully inside i_size? */ if (page->index < end_index) return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); } EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); bio = bio_alloc(GFP_NOIO, 1); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; if (buffer_meta(bh)) op_flags |= REQ_META; if (buffer_prio(bh)) op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); } submit_bio(bio); return 0; } int submit_bh(int op, int op_flags, struct buffer_head *bh) { return submit_bh_wbc(op, op_flags, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) * @op: whether to %READ or %WRITE * @op_flags: req_flag_bits * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * * ll_rw_block() takes an array of pointers to &struct buffer_heads, and * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE. * @op_flags contains flags modifying the detailed I/O behavior, most notably * %REQ_RAHEAD. * * This function drops any buffer that it cannot get a lock on (with the * BH_Lock state bit), any buffer that appears to be clean when doing a write * request, and any buffer that appears to be up-to-date when doing read * request. Further it marks as clean buffers that are processed for * writing (the buffer cache won't assume that they are actually clean * until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if appropriate), unlocks the buffer and wakes * any waiters. * * All of the buffers must be for the same device, and must also be a * multiple of the current approved size for the device. */ void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[]) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (!trylock_buffer(bh)) continue; if (op == WRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } else { if (!buffer_uptodate(bh)) { bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } unlock_buffer(bh); } } EXPORT_SYMBOL(ll_rw_block); void write_dirty_buffer(struct buffer_head *bh, int op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE, op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) { int ret = 0; WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); wait_on_buffer(bh); if (!ret && !buffer_uptodate(bh)) ret = -EIO; } else { unlock_buffer(bh); } return ret; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); /* * try_to_free_buffers() checks if all the buffers on this particular page * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either * locking the page or by holding its mapping's private_lock. * * If the page is dirty but all the buffers are clean then we need to * be sure to mark the page clean as well. This is because the page * may be against a block device, and a later reattachment of buffers * to a dirty page will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem pages: if all the buffers are * clean then we set the page clean and proceed. To do that, we require * total exclusion from __set_page_dirty_buffers(). That is obtained with * private_lock. * * try_to_free_buffers() is non-blocking. */ static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static int drop_buffers(struct page *page, struct buffer_head **buffers_to_free) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; detach_page_private(page); return 1; failed: return 0; } int try_to_free_buffers(struct page *page) { struct address_space * const mapping = page->mapping; struct buffer_head *buffers_to_free = NULL; int ret = 0; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(page, &buffers_to_free); goto out; } spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty page. We * clean the page here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the page's buffers clean. We discover that here and clean * the page also. * * private_lock must be held over this entire operation in order * to synchronise against __set_page_dirty_buffers and prevent the * dirty bit from being lost. */ if (ret) cancel_dirty_page(page); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * There are no bdflush tunables left. But distributions are * still running obsolete flush daemons, so we terminate them here. * * Use of bdflush() is deprecated and will be removed in a future kernel. * The `flush-X' kernel threads fully replace bdflush daemons and this call. */ SYSCALL_DEFINE2(bdflush, int, func, long, data) { static int msg_count; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (msg_count < 5) { msg_count++; printk(KERN_INFO "warning: process `%s' used the obsolete bdflush" " system call\n", current->comm); printk(KERN_INFO "Fix your initscripts?\n"); } if (func == 1) do_exit(0); return 0; } /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __read_mostly; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * bh_submit_read - Submit a locked buffer for reading * @bh: struct buffer_head * * Returns zero on success and -EIO on error. */ int bh_submit_read(struct buffer_head *bh) { BUG_ON(!buffer_locked(bh)); if (buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } EXPORT_SYMBOL(bh_submit_read); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_node_allowed(node, gfp_mask); return true; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return __cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } static inline int cpuset_do_slab_mem_spread(void) { return task_spread_slab(current); } extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_wait_for_hotplug(void) { } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, cpu_possible_mask); } static inline void cpuset_cpus_allowed_fallback(struct task_struct *p) { } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) { return true; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_slab_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline int cpuset_do_slab_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 | // SPDX-License-Identifier: GPL-2.0+ /* * Base port operations for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * Split from 8250_core.c, Copyright (C) 2001 Russell King. * * A note about mapbase / membase * * mapbase is the physical address of the IO port. * membase is an 'ioremapped' cookie. */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/ktime.h> #include <asm/io.h> #include <asm/irq.h> #include "8250.h" /* Nuvoton NPCM timeout register */ #define UART_NPCM_TOR 7 #define UART_NPCM_TOIE BIT(7) /* Timeout Interrupt Enable */ /* * Debugging. */ #if 0 #define DEBUG_AUTOCONF(fmt...) printk(fmt) #else #define DEBUG_AUTOCONF(fmt...) do { } while (0) #endif #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) /* * Here we define the default xmit fifo size used for each type of UART. */ static const struct serial8250_config uart_config[] = { [PORT_UNKNOWN] = { .name = "unknown", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_8250] = { .name = "8250", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16450] = { .name = "16450", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550] = { .name = "16550", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550A] = { .name = "16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_CIRRUS] = { .name = "Cirrus", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16650] = { .name = "ST16650", .fifo_size = 1, .tx_loadsz = 1, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16650V2] = { .name = "ST16650V2", .fifo_size = 32, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_00, .rxtrig_bytes = {8, 16, 24, 28}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16750] = { .name = "TI16750", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .rxtrig_bytes = {1, 16, 32, 56}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP | UART_CAP_AFE, }, [PORT_STARTECH] = { .name = "Startech", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16C950] = { .name = "16C950/954", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {16, 32, 112, 120}, /* UART_CAP_EFR breaks billionon CF bluetooth card. */ .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_16654] = { .name = "ST16654", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_10, .rxtrig_bytes = {8, 16, 56, 60}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16850] = { .name = "XR16850", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_RSA] = { .name = "RSA", .fifo_size = 2048, .tx_loadsz = 2048, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11, .flags = UART_CAP_FIFO, }, [PORT_NS16550A] = { .name = "NS16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_NATSEMI, }, [PORT_XSCALE] = { .name = "XScale", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_UUE | UART_CAP_RTOIE, }, [PORT_OCTEON] = { .name = "OCTEON", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO, }, [PORT_AR7] = { .name = "AR7", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00, .flags = UART_CAP_FIFO /* | UART_CAP_AFE */, }, [PORT_U6_16550A] = { .name = "U6_16550A", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_TEGRA] = { .name = "Tegra", .fifo_size = 32, .tx_loadsz = 8, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_01, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_RTOIE, }, [PORT_XR17D15X] = { .name = "XR17D15X", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_XR17V35X] = { .name = "XR17V35X", .fifo_size = 256, .tx_loadsz = 256, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11 | UART_FCR_T_TRIG_11, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_LPC3220] = { .name = "LPC3220", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00 | UART_FCR_T_TRIG_00, .flags = UART_CAP_FIFO, }, [PORT_BRCM_TRUMANAGE] = { .name = "TruManage", .fifo_size = 1, .tx_loadsz = 1024, .flags = UART_CAP_HFIFO, }, [PORT_8250_CIR] = { .name = "CIR port" }, [PORT_ALTR_16550_F32] = { .name = "Altera 16550 FIFO32", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 8, 16, 30}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F64] = { .name = "Altera 16550 FIFO64", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 16, 32, 62}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F128] = { .name = "Altera 16550 FIFO128", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 126}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, /* * tx_loadsz is set to 63-bytes instead of 64-bytes to implement * workaround of errata A-008006 which states that tx_loadsz should * be configured less than Maximum supported fifo bytes. */ [PORT_16550A_FSL64] = { .name = "16550A_FSL64", .fifo_size = 64, .tx_loadsz = 63, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .flags = UART_CAP_FIFO, }, [PORT_RT2880] = { .name = "Palmchip BK-3103", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_DA830] = { .name = "TI DA8xx/66AK2x", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_MTK_BTIF] = { .name = "MediaTek BTIF", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .flags = UART_CAP_FIFO, }, [PORT_NPCM] = { .name = "Nuvoton 16550", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_SUNIX] = { .name = "Sunix", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 112}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, }; /* Uart divisor latch read */ static int default_serial_dl_read(struct uart_8250_port *up) { /* Assign these in pieces to truncate any bits above 7. */ unsigned char dll = serial_in(up, UART_DLL); unsigned char dlm = serial_in(up, UART_DLM); return dll | dlm << 8; } /* Uart divisor latch write */ static void default_serial_dl_write(struct uart_8250_port *up, int value) { serial_out(up, UART_DLL, value & 0xff); serial_out(up, UART_DLM, value >> 8 & 0xff); } #ifdef CONFIG_SERIAL_8250_RT288X /* Au1x00/RT288x UART hardware has a weird register layout */ static const s8 au_io_in_map[8] = { 0, /* UART_RX */ 2, /* UART_IER */ 3, /* UART_IIR */ 5, /* UART_LCR */ 6, /* UART_MCR */ 7, /* UART_LSR */ 8, /* UART_MSR */ -1, /* UART_SCR (unmapped) */ }; static const s8 au_io_out_map[8] = { 1, /* UART_TX */ 2, /* UART_IER */ 4, /* UART_FCR */ 5, /* UART_LCR */ 6, /* UART_MCR */ -1, /* UART_LSR (unmapped) */ -1, /* UART_MSR (unmapped) */ -1, /* UART_SCR (unmapped) */ }; unsigned int au_serial_in(struct uart_port *p, int offset) { if (offset >= ARRAY_SIZE(au_io_in_map)) return UINT_MAX; offset = au_io_in_map[offset]; if (offset < 0) return UINT_MAX; return __raw_readl(p->membase + (offset << p->regshift)); } void au_serial_out(struct uart_port *p, int offset, int value) { if (offset >= ARRAY_SIZE(au_io_out_map)) return; offset = au_io_out_map[offset]; if (offset < 0) return; __raw_writel(value, p->membase + (offset << p->regshift)); } /* Au1x00 haven't got a standard divisor latch */ static int au_serial_dl_read(struct uart_8250_port *up) { return __raw_readl(up->port.membase + 0x28); } static void au_serial_dl_write(struct uart_8250_port *up, int value) { __raw_writel(value, up->port.membase + 0x28); } #endif static unsigned int hub6_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); return inb(p->iobase + 1); } static void hub6_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); outb(value, p->iobase + 1); } static unsigned int mem_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readb(p->membase + offset); } static void mem_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writeb(value, p->membase + offset); } static void mem16_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writew(value, p->membase + offset); } static unsigned int mem16_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readw(p->membase + offset); } static void mem32_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writel(value, p->membase + offset); } static unsigned int mem32_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readl(p->membase + offset); } static void mem32be_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; iowrite32be(value, p->membase + offset); } static unsigned int mem32be_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return ioread32be(p->membase + offset); } static unsigned int io_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return inb(p->iobase + offset); } static void io_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; outb(value, p->iobase + offset); } static int serial8250_default_handle_irq(struct uart_port *port); static void set_io_from_upio(struct uart_port *p) { struct uart_8250_port *up = up_to_u8250p(p); up->dl_read = default_serial_dl_read; up->dl_write = default_serial_dl_write; switch (p->iotype) { case UPIO_HUB6: p->serial_in = hub6_serial_in; p->serial_out = hub6_serial_out; break; case UPIO_MEM: p->serial_in = mem_serial_in; p->serial_out = mem_serial_out; break; case UPIO_MEM16: p->serial_in = mem16_serial_in; p->serial_out = mem16_serial_out; break; case UPIO_MEM32: p->serial_in = mem32_serial_in; p->serial_out = mem32_serial_out; break; case UPIO_MEM32BE: p->serial_in = mem32be_serial_in; p->serial_out = mem32be_serial_out; break; #ifdef CONFIG_SERIAL_8250_RT288X case UPIO_AU: p->serial_in = au_serial_in; p->serial_out = au_serial_out; up->dl_read = au_serial_dl_read; up->dl_write = au_serial_dl_write; break; #endif default: p->serial_in = io_serial_in; p->serial_out = io_serial_out; break; } /* Remember loaded iotype */ up->cur_iotype = p->iotype; p->handle_irq = serial8250_default_handle_irq; } static void serial_port_out_sync(struct uart_port *p, int offset, int value) { switch (p->iotype) { case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: p->serial_out(p, offset, value); p->serial_in(p, UART_LCR); /* safe, no side-effects */ break; default: p->serial_out(p, offset, value); } } /* * FIFO support. */ static void serial8250_clear_fifos(struct uart_8250_port *p) { if (p->capabilities & UART_CAP_FIFO) { serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial_out(p, UART_FCR, 0); } } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t); void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p) { serial8250_clear_fifos(p); serial_out(p, UART_FCR, p->fcr); } EXPORT_SYMBOL_GPL(serial8250_clear_and_reinit_fifos); void serial8250_rpm_get(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get); void serial8250_rpm_put(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put); /** * serial8250_em485_init() - put uart_8250_port into rs485 emulating * @p: uart_8250_port port instance * * The function is used to start rs485 software emulating on the * &struct uart_8250_port* @p. Namely, RTS is switched before/after * transmission. The function is idempotent, so it is safe to call it * multiple times. * * The caller MUST enable interrupt on empty shift register before * calling serial8250_em485_init(). This interrupt is not a part of * 8250 standard, but implementation defined. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_destroy() * * Return 0 - success, -errno - otherwise */ static int serial8250_em485_init(struct uart_8250_port *p) { if (p->em485) goto deassert_rts; p->em485 = kmalloc(sizeof(struct uart_8250_em485), GFP_ATOMIC); if (!p->em485) return -ENOMEM; hrtimer_init(&p->em485->stop_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_init(&p->em485->start_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); p->em485->stop_tx_timer.function = &serial8250_em485_handle_stop_tx; p->em485->start_tx_timer.function = &serial8250_em485_handle_start_tx; p->em485->port = p; p->em485->active_timer = NULL; p->em485->tx_stopped = true; deassert_rts: if (p->em485->tx_stopped) p->rs485_stop_tx(p); return 0; } /** * serial8250_em485_destroy() - put uart_8250_port into normal state * @p: uart_8250_port port instance * * The function is used to stop rs485 software emulating on the * &struct uart_8250_port* @p. The function is idempotent, so it is safe to * call it multiple times. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_init() */ void serial8250_em485_destroy(struct uart_8250_port *p) { if (!p->em485) return; hrtimer_cancel(&p->em485->start_tx_timer); hrtimer_cancel(&p->em485->stop_tx_timer); kfree(p->em485); p->em485 = NULL; } EXPORT_SYMBOL_GPL(serial8250_em485_destroy); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings * if the uart is incapable of driving RTS as a Transmit Enable signal in * hardware, relying on software emulation instead. */ int serial8250_em485_config(struct uart_port *port, struct serial_rs485 *rs485) { struct uart_8250_port *up = up_to_u8250p(port); /* pick sane settings if the user hasn't */ if (!!(rs485->flags & SER_RS485_RTS_ON_SEND) == !!(rs485->flags & SER_RS485_RTS_AFTER_SEND)) { rs485->flags |= SER_RS485_RTS_ON_SEND; rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; } gpiod_set_value(port->rs485_term_gpio, rs485->flags & SER_RS485_TERMINATE_BUS); /* * Both serial8250_em485_init() and serial8250_em485_destroy() * are idempotent. */ if (rs485->flags & SER_RS485_ENABLED) return serial8250_em485_init(up); serial8250_em485_destroy(up); return 0; } EXPORT_SYMBOL_GPL(serial8250_em485_config); /* * These two wrappers ensure that enable_runtime_pm_tx() can be called more than * once and disable_runtime_pm_tx() will still disable RPM because the fifo is * empty and the HW can idle again. */ void serial8250_rpm_get_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 1); if (rpm_active) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get_tx); void serial8250_rpm_put_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 0); if (!rpm_active) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put_tx); /* * IER sleep support. UARTs which have EFRs need the "extended * capability" bit enabled. Note that on XR16C850s, we need to * reset LCR to write to IER. */ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) { unsigned char lcr = 0, efr = 0; serial8250_rpm_get(p); if (p->capabilities & UART_CAP_SLEEP) { if (p->capabilities & UART_CAP_EFR) { lcr = serial_in(p, UART_LCR); efr = serial_in(p, UART_EFR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, UART_EFR_ECB); serial_out(p, UART_LCR, 0); } serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0); if (p->capabilities & UART_CAP_EFR) { serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, efr); serial_out(p, UART_LCR, lcr); } } serial8250_rpm_put(p); } #ifdef CONFIG_SERIAL_8250_RSA /* * Attempts to turn on the RSA FIFO. Returns zero on failure. * We set the port uart clock rate if we succeed. */ static int __enable_rsa(struct uart_8250_port *up) { unsigned char mode; int result; mode = serial_in(up, UART_RSA_MSR); result = mode & UART_RSA_MSR_FIFO; if (!result) { serial_out(up, UART_RSA_MSR, mode | UART_RSA_MSR_FIFO); mode = serial_in(up, UART_RSA_MSR); result = mode & UART_RSA_MSR_FIFO; } if (result) up->port.uartclk = SERIAL_RSA_BAUD_BASE * 16; return result; } static void enable_rsa(struct uart_8250_port *up) { if (up->port.type == PORT_RSA) { if (up->port.uartclk != SERIAL_RSA_BAUD_BASE * 16) { spin_lock_irq(&up->port.lock); __enable_rsa(up); spin_unlock_irq(&up->port.lock); } if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) serial_out(up, UART_RSA_FRR, 0); } } /* * Attempts to turn off the RSA FIFO. Returns zero on failure. * It is unknown why interrupts were disabled in here. However, * the caller is expected to preserve this behaviour by grabbing * the spinlock before calling this function. */ static void disable_rsa(struct uart_8250_port *up) { unsigned char mode; int result; if (up->port.type == PORT_RSA && up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) { spin_lock_irq(&up->port.lock); mode = serial_in(up, UART_RSA_MSR); result = !(mode & UART_RSA_MSR_FIFO); if (!result) { serial_out(up, UART_RSA_MSR, mode & ~UART_RSA_MSR_FIFO); mode = serial_in(up, UART_RSA_MSR); result = !(mode & UART_RSA_MSR_FIFO); } if (result) up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16; spin_unlock_irq(&up->port.lock); } } #endif /* CONFIG_SERIAL_8250_RSA */ /* * This is a quickie test to see how big the FIFO is. * It doesn't work at all the time, more's the pity. */ static int size_fifo(struct uart_8250_port *up) { unsigned char old_fcr, old_mcr, old_lcr; unsigned short old_dl; int count; old_lcr = serial_in(up, UART_LCR); serial_out(up, UART_LCR, 0); old_fcr = serial_in(up, UART_FCR); old_mcr = serial8250_in_MCR(up); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial8250_out_MCR(up, UART_MCR_LOOP); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(up); serial_dl_write(up, 0x0001); serial_out(up, UART_LCR, 0x03); for (count = 0; count < 256; count++) serial_out(up, UART_TX, count); mdelay(20);/* FIXME - schedule_timeout */ for (count = 0; (serial_in(up, UART_LSR) & UART_LSR_DR) && (count < 256); count++) serial_in(up, UART_RX); serial_out(up, UART_FCR, old_fcr); serial8250_out_MCR(up, old_mcr); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_dl_write(up, old_dl); serial_out(up, UART_LCR, old_lcr); return count; } /* * Read UART ID using the divisor method - set DLL and DLM to zero * and the revision will be in DLL and device type in DLM. We * preserve the device state across this. */ static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p) { unsigned char old_lcr; unsigned int id, old_dl; old_lcr = serial_in(p, UART_LCR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(p); serial_dl_write(p, 0); id = serial_dl_read(p); serial_dl_write(p, old_dl); serial_out(p, UART_LCR, old_lcr); return id; } /* * This is a helper routine to autodetect StarTech/Exar/Oxsemi UART's. * When this function is called we know it is at least a StarTech * 16650 V2, but it might be one of several StarTech UARTs, or one of * its clones. (We treat the broken original StarTech 16650 V1 as a * 16550, and why not? Startech doesn't seem to even acknowledge its * existence.) * * What evil have men's minds wrought... */ static void autoconfig_has_efr(struct uart_8250_port *up) { unsigned int id1, id2, id3, rev; /* * Everything with an EFR has SLEEP */ up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; /* * First we check to see if it's an Oxford Semiconductor UART. * * If we have to do this here because some non-National * Semiconductor clone chips lock up if you try writing to the * LSR register (which serial_icr_read does) */ /* * Check for Oxford Semiconductor 16C950. * * EFR [4] must be set else this test fails. * * This shouldn't be necessary, but Mike Hudson (Exoray@isys.ca) * claims that it's needed for 952 dual UART's (which are not * recommended for new designs). */ up->acr = 0; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, 0x00); id1 = serial_icr_read(up, UART_ID1); id2 = serial_icr_read(up, UART_ID2); id3 = serial_icr_read(up, UART_ID3); rev = serial_icr_read(up, UART_REV); DEBUG_AUTOCONF("950id=%02x:%02x:%02x:%02x ", id1, id2, id3, rev); if (id1 == 0x16 && id2 == 0xC9 && (id3 == 0x50 || id3 == 0x52 || id3 == 0x54)) { up->port.type = PORT_16C950; /* * Enable work around for the Oxford Semiconductor 952 rev B * chip which causes it to seriously miscalculate baud rates * when DLL is 0. */ if (id3 == 0x52 && rev == 0x01) up->bugs |= UART_BUG_QUOT; return; } /* * We check for a XR16C850 by setting DLL and DLM to 0, and then * reading back DLL and DLM. The chip type depends on the DLM * value read back: * 0x10 - XR16C850 and the DLL contains the chip revision. * 0x12 - XR16C2850. * 0x14 - XR16C854. */ id1 = autoconfig_read_divisor_id(up); DEBUG_AUTOCONF("850id=%04x ", id1); id2 = id1 >> 8; if (id2 == 0x10 || id2 == 0x12 || id2 == 0x14) { up->port.type = PORT_16850; return; } /* * It wasn't an XR16C850. * * We distinguish between the '654 and the '650 by counting * how many bytes are in the FIFO. I'm using this for now, * since that's the technique that was sent to me in the * serial driver update, but I'm not convinced this works. * I've had problems doing this in the past. -TYT */ if (size_fifo(up) == 64) up->port.type = PORT_16654; else up->port.type = PORT_16650V2; } /* * We detected a chip without a FIFO. Only two fall into * this category - the original 8250 and the 16450. The * 16450 has a scratch register (accessible with LCR=0) */ static void autoconfig_8250(struct uart_8250_port *up) { unsigned char scratch, status1, status2; up->port.type = PORT_8250; scratch = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0xa5); status1 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0x5a); status2 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, scratch); if (status1 == 0xa5 && status2 == 0x5a) up->port.type = PORT_16450; } static int broken_efr(struct uart_8250_port *up) { /* * Exar ST16C2550 "A2" devices incorrectly detect as * having an EFR, and report an ID of 0x0201. See * http://linux.derkeiler.com/Mailing-Lists/Kernel/2004-11/4812.html */ if (autoconfig_read_divisor_id(up) == 0x0201 && size_fifo(up) == 16) return 1; return 0; } /* * We know that the chip has FIFOs. Does it have an EFR? The * EFR is located in the same register position as the IIR and * we know the top two bits of the IIR are currently set. The * EFR should contain zero. Try to read the EFR. */ static void autoconfig_16550a(struct uart_8250_port *up) { unsigned char status1, status2; unsigned int iersave; up->port.type = PORT_16550A; up->capabilities |= UART_CAP_FIFO; if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS) && !(up->port.flags & UPF_FULL_PROBE)) return; /* * Check for presence of the EFR when DLAB is set. * Only ST16C650V1 UARTs pass this test. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); if (serial_in(up, UART_EFR) == 0) { serial_out(up, UART_EFR, 0xA8); if (serial_in(up, UART_EFR) != 0) { DEBUG_AUTOCONF("EFRv1 "); up->port.type = PORT_16650; up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; } else { serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) >> 5; serial_out(up, UART_FCR, 0); serial_out(up, UART_LCR, 0); if (status1 == 7) up->port.type = PORT_16550A_FSL64; else DEBUG_AUTOCONF("Motorola 8xxx DUART "); } serial_out(up, UART_EFR, 0); return; } /* * Maybe it requires 0xbf to be written to the LCR. * (other ST16C650V2 UARTs, TI16C752A, etc) */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); if (serial_in(up, UART_EFR) == 0 && !broken_efr(up)) { DEBUG_AUTOCONF("EFRv2 "); autoconfig_has_efr(up); return; } /* * Check for a National Semiconductor SuperIO chip. * Attempt to switch to bank 2, read the value of the LOOP bit * from EXCR1. Switch back to bank 0, change it in MCR. Then * switch back to bank 2, read it from EXCR1 again and check * it's changed. If so, set baud_base in EXCR2 to 921600. -- dwmw2 */ serial_out(up, UART_LCR, 0); status1 = serial8250_in_MCR(up); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ if (!((status2 ^ status1) & UART_MCR_LOOP)) { serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1 ^ UART_MCR_LOOP); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1); if ((status2 ^ status1) & UART_MCR_LOOP) { unsigned short quot; serial_out(up, UART_LCR, 0xE0); quot = serial_dl_read(up); quot <<= 3; if (ns16550a_goto_highspeed(up)) serial_dl_write(up, quot); serial_out(up, UART_LCR, 0); up->port.uartclk = 921600*16; up->port.type = PORT_NS16550A; up->capabilities |= UART_NATSEMI; return; } } /* * No EFR. Try to detect a TI16750, which only sets bit 5 of * the IIR when 64 byte FIFO mode is enabled when DLAB is set. * Try setting it with and without DLAB set. Cheap clones * set bit 5 without DLAB set. */ serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) >> 5; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status2 = serial_in(up, UART_IIR) >> 5; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, 0); DEBUG_AUTOCONF("iir1=%d iir2=%d ", status1, status2); if (status1 == 6 && status2 == 7) { up->port.type = PORT_16750; up->capabilities |= UART_CAP_AFE | UART_CAP_SLEEP; return; } /* * Try writing and reading the UART_IER_UUE bit (b6). * If it works, this is probably one of the Xscale platform's * internal UARTs. * We're going to explicitly set the UUE bit to 0 before * trying to write and read a 1 just to make sure it's not * already a 1 and maybe locked there before we even start start. */ iersave = serial_in(up, UART_IER); serial_out(up, UART_IER, iersave & ~UART_IER_UUE); if (!(serial_in(up, UART_IER) & UART_IER_UUE)) { /* * OK it's in a known zero state, try writing and reading * without disturbing the current state of the other bits. */ serial_out(up, UART_IER, iersave | UART_IER_UUE); if (serial_in(up, UART_IER) & UART_IER_UUE) { /* * It's an Xscale. * We'll leave the UART_IER_UUE bit set to 1 (enabled). */ DEBUG_AUTOCONF("Xscale "); up->port.type = PORT_XSCALE; up->capabilities |= UART_CAP_UUE | UART_CAP_RTOIE; return; } } else { /* * If we got here we couldn't force the IER_UUE bit to 0. * Log it and continue. */ DEBUG_AUTOCONF("Couldn't force IER_UUE to 0 "); } serial_out(up, UART_IER, iersave); /* * We distinguish between 16550A and U6 16550A by counting * how many bytes are in the FIFO. */ if (up->port.type == PORT_16550A && size_fifo(up) == 64) { up->port.type = PORT_U6_16550A; up->capabilities |= UART_CAP_AFE; } } /* * This routine is called by rs_init() to initialize a specific serial * port. It determines what type of UART chip this serial port is * using: 8250, 16450, 16550, 16550A. The important question is * whether or not this UART is a 16550A or not, since this will * determine whether or not we can use its FIFO features or not. */ static void autoconfig(struct uart_8250_port *up) { unsigned char status1, scratch, scratch2, scratch3; unsigned char save_lcr, save_mcr; struct uart_port *port = &up->port; unsigned long flags; unsigned int old_capabilities; if (!port->iobase && !port->mapbase && !port->membase) return; DEBUG_AUTOCONF("%s: autoconf (0x%04lx, 0x%p): ", port->name, port->iobase, port->membase); /* * We really do need global IRQs disabled here - we're going to * be frobbing the chips IRQ enable register to see if it exists. */ spin_lock_irqsave(&port->lock, flags); up->capabilities = 0; up->bugs = 0; if (!(port->flags & UPF_BUGGY_UART)) { /* * Do a simple existence test first; if we fail this, * there's no point trying anything else. * * 0x80 is used as a nonsense port to prevent against * false positives due to ISA bus float. The * assumption is that 0x80 is a non-existent port; * which should be safe since include/asm/io.h also * makes this assumption. * * Note: this is safe as long as MCR bit 4 is clear * and the device is in "PC" mode. */ scratch = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); #ifdef __i386__ outb(0xff, 0x080); #endif /* * Mask out IER[7:4] bits for test as some UARTs (e.g. TL * 16C754B) allow only to modify them if an EFR bit is set. */ scratch2 = serial_in(up, UART_IER) & 0x0f; serial_out(up, UART_IER, 0x0F); #ifdef __i386__ outb(0, 0x080); #endif scratch3 = serial_in(up, UART_IER) & 0x0f; serial_out(up, UART_IER, scratch); if (scratch2 != 0 || scratch3 != 0x0F) { /* * We failed; there's nothing here */ spin_unlock_irqrestore(&port->lock, flags); DEBUG_AUTOCONF("IER test failed (%02x, %02x) ", scratch2, scratch3); goto out; } } save_mcr = serial8250_in_MCR(up); save_lcr = serial_in(up, UART_LCR); /* * Check to see if a UART is really there. Certain broken * internal modems based on the Rockwell chipset fail this * test, because they apparently don't implement the loopback * test mode. So this test is skipped on the COM 1 through * COM 4 ports. This *should* be safe, since no board * manufacturer would be stupid enough to design a board * that conflicts with COM 1-4 --- we hope! */ if (!(port->flags & UPF_SKIP_TEST)) { serial8250_out_MCR(up, UART_MCR_LOOP | 0x0A); status1 = serial_in(up, UART_MSR) & 0xF0; serial8250_out_MCR(up, save_mcr); if (status1 != 0x90) { spin_unlock_irqrestore(&port->lock, flags); DEBUG_AUTOCONF("LOOP test failed (%02x) ", status1); goto out; } } /* * We're pretty sure there's a port here. Lets find out what * type of port it is. The IIR top two bits allows us to find * out if it's 8250 or 16450, 16550, 16550A or later. This * determines what we test for next. * * We also initialise the EFR (if any) to zero for later. The * EFR occupies the same register location as the FCR and IIR. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, 0); serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); /* Assign this as it is to truncate any bits above 7. */ scratch = serial_in(up, UART_IIR); switch (scratch >> 6) { case 0: autoconfig_8250(up); break; case 1: port->type = PORT_UNKNOWN; break; case 2: port->type = PORT_16550; break; case 3: autoconfig_16550a(up); break; } #ifdef CONFIG_SERIAL_8250_RSA /* * Only probe for RSA ports if we got the region. */ if (port->type == PORT_16550A && up->probe & UART_PROBE_RSA && __enable_rsa(up)) port->type = PORT_RSA; #endif serial_out(up, UART_LCR, save_lcr); port->fifosize = uart_config[up->port.type].fifo_size; old_capabilities = up->capabilities; up->capabilities = uart_config[port->type].flags; up->tx_loadsz = uart_config[port->type].tx_loadsz; if (port->type == PORT_UNKNOWN) goto out_lock; /* * Reset the UART. */ #ifdef CONFIG_SERIAL_8250_RSA if (port->type == PORT_RSA) serial_out(up, UART_RSA_FRR, 0); #endif serial8250_out_MCR(up, save_mcr); serial8250_clear_fifos(up); serial_in(up, UART_RX); if (up->capabilities & UART_CAP_UUE) serial_out(up, UART_IER, UART_IER_UUE); else serial_out(up, UART_IER, 0); out_lock: spin_unlock_irqrestore(&port->lock, flags); /* * Check if the device is a Fintek F81216A */ if (port->type == PORT_16550A && port->iotype == UPIO_PORT) fintek_8250_probe(up); if (up->capabilities != old_capabilities) { dev_warn(port->dev, "detected caps %08x should be %08x\n", old_capabilities, up->capabilities); } out: DEBUG_AUTOCONF("iir=%d ", scratch); DEBUG_AUTOCONF("type=%s\n", uart_config[port->type].name); } static void autoconfig_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned char save_mcr, save_ier; unsigned char save_ICP = 0; unsigned int ICP = 0; unsigned long irqs; int irq; if (port->flags & UPF_FOURPORT) { ICP = (port->iobase & 0xfe0) | 0x1f; save_ICP = inb_p(ICP); outb_p(0x80, ICP); inb_p(ICP); } /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); save_ier = serial_in(up, UART_IER); serial8250_out_MCR(up, UART_MCR_OUT1 | UART_MCR_OUT2); irqs = probe_irq_on(); serial8250_out_MCR(up, 0); udelay(10); if (port->flags & UPF_FOURPORT) { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); } else { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2); } serial_out(up, UART_IER, 0x0f); /* enable all intrs */ serial_in(up, UART_LSR); serial_in(up, UART_RX); serial_in(up, UART_IIR); serial_in(up, UART_MSR); serial_out(up, UART_TX, 0xFF); udelay(20); irq = probe_irq_off(irqs); serial8250_out_MCR(up, save_mcr); serial_out(up, UART_IER, save_ier); if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); port->irq = (irq > 0) ? irq : 0; } static void serial8250_stop_rx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); up->port.read_status_mask &= ~UART_LSR_DR; serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); } /** * serial8250_em485_stop_tx() - generic ->rs485_stop_tx() callback * @p: uart 8250 port * * Generic callback usable by 8250 uart drivers to stop rs485 transmission. */ void serial8250_em485_stop_tx(struct uart_8250_port *p) { unsigned char mcr = serial8250_in_MCR(p); if (p->port.rs485.flags & SER_RS485_RTS_AFTER_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(p, mcr); /* * Empty the RX FIFO, we are not interested in anything * received during the half-duplex transmission. * Enable previously disabled RX interrupts. */ if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) { serial8250_clear_and_reinit_fifos(p); p->ier |= UART_IER_RLSI | UART_IER_RDI; serial_port_out(&p->port, UART_IER, p->ier); } } EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t) { struct uart_8250_em485 *em485; struct uart_8250_port *p; unsigned long flags; em485 = container_of(t, struct uart_8250_em485, stop_tx_timer); p = em485->port; serial8250_rpm_get(p); spin_lock_irqsave(&p->port.lock, flags); if (em485->active_timer == &em485->stop_tx_timer) { p->rs485_stop_tx(p); em485->active_timer = NULL; em485->tx_stopped = true; } spin_unlock_irqrestore(&p->port.lock, flags); serial8250_rpm_put(p); return HRTIMER_NORESTART; } static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec) { long sec = msec / 1000; long nsec = (msec % 1000) * 1000000; ktime_t t = ktime_set(sec, nsec); hrtimer_start(hrt, t, HRTIMER_MODE_REL); } static void __stop_tx_rs485(struct uart_8250_port *p) { struct uart_8250_em485 *em485 = p->em485; /* * rs485_stop_tx() is going to set RTS according to config * AND flush RX FIFO if required. */ if (p->port.rs485.delay_rts_after_send > 0) { em485->active_timer = &em485->stop_tx_timer; start_hrtimer_ms(&em485->stop_tx_timer, p->port.rs485.delay_rts_after_send); } else { p->rs485_stop_tx(p); em485->active_timer = NULL; em485->tx_stopped = true; } } static inline void __do_stop_tx(struct uart_8250_port *p) { if (serial8250_clear_THRI(p)) serial8250_rpm_put_tx(p); } static inline void __stop_tx(struct uart_8250_port *p) { struct uart_8250_em485 *em485 = p->em485; if (em485) { unsigned char lsr = serial_in(p, UART_LSR); p->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; /* * To provide required timeing and allow FIFO transfer, * __stop_tx_rs485() must be called only when both FIFO and * shift register are empty. It is for device driver to enable * interrupt on TEMT. */ if ((lsr & BOTH_EMPTY) != BOTH_EMPTY) return; __stop_tx_rs485(p); } __do_stop_tx(p); } static void serial8250_stop_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); __stop_tx(up); /* * We really want to stop the transmitter from sending. */ if (port->type == PORT_16C950) { up->acr |= UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } serial8250_rpm_put(up); } static inline void __start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma && !up->dma->tx_dma(up)) return; if (serial8250_set_THRI(up)) { if (up->bugs & UART_BUG_TXEN) { unsigned char lsr; lsr = serial_in(up, UART_LSR); up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; if (lsr & UART_LSR_THRE) serial8250_tx_chars(up); } } /* * Re-enable the transmitter if we disabled it. */ if (port->type == PORT_16C950 && up->acr & UART_ACR_TXDIS) { up->acr &= ~UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } } /** * serial8250_em485_start_tx() - generic ->rs485_start_tx() callback * @up: uart 8250 port * * Generic callback usable by 8250 uart drivers to start rs485 transmission. * Assumes that setting the RTS bit in the MCR register means RTS is high. * (Some chips use inverse semantics.) Further assumes that reception is * stoppable by disabling the UART_IER_RDI interrupt. (Some chips set the * UART_LSR_DR bit even when UART_IER_RDI is disabled, foiling this approach.) */ void serial8250_em485_start_tx(struct uart_8250_port *up) { unsigned char mcr = serial8250_in_MCR(up); if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX)) serial8250_stop_rx(&up->port); if (up->port.rs485.flags & SER_RS485_RTS_ON_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(up, mcr); } EXPORT_SYMBOL_GPL(serial8250_em485_start_tx); static inline void start_tx_rs485(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; /* * While serial8250_em485_handle_stop_tx() is a noop if * em485->active_timer != &em485->stop_tx_timer, it might happen that * the timer is still armed and triggers only after the current bunch of * chars is send and em485->active_timer == &em485->stop_tx_timer again. * So cancel the timer. There is still a theoretical race condition if * the timer is already running and only comes around to check for * em485->active_timer when &em485->stop_tx_timer is armed again. */ if (em485->active_timer == &em485->stop_tx_timer) hrtimer_try_to_cancel(&em485->stop_tx_timer); em485->active_timer = NULL; if (em485->tx_stopped) { em485->tx_stopped = false; up->rs485_start_tx(up); if (up->port.rs485.delay_rts_before_send > 0) { em485->active_timer = &em485->start_tx_timer; start_hrtimer_ms(&em485->start_tx_timer, up->port.rs485.delay_rts_before_send); return; } } __start_tx(port); } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t) { struct uart_8250_em485 *em485; struct uart_8250_port *p; unsigned long flags; em485 = container_of(t, struct uart_8250_em485, start_tx_timer); p = em485->port; spin_lock_irqsave(&p->port.lock, flags); if (em485->active_timer == &em485->start_tx_timer) { __start_tx(&p->port); em485->active_timer = NULL; } spin_unlock_irqrestore(&p->port.lock, flags); return HRTIMER_NORESTART; } static void serial8250_start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; serial8250_rpm_get_tx(up); if (em485 && em485->active_timer == &em485->start_tx_timer) return; if (em485) start_tx_rs485(port); else __start_tx(port); } static void serial8250_throttle(struct uart_port *port) { port->throttle(port); } static void serial8250_unthrottle(struct uart_port *port) { port->unthrottle(port); } static void serial8250_disable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_disable_ms(up->gpios); up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } static void serial8250_enable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_enable_ms(up->gpios); up->ier |= UART_IER_MSI; serial8250_rpm_get(up); serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); } void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr) { struct uart_port *port = &up->port; unsigned char ch; char flag = TTY_NORMAL; if (likely(lsr & UART_LSR_DR)) ch = serial_in(up, UART_RX); else /* * Intel 82571 has a Serial Over Lan device that will * set UART_LSR_BI without setting UART_LSR_DR when * it receives a break. To avoid reading from the * receive buffer without UART_LSR_DR bit set, we * just force the read character to be 0 */ ch = 0; port->icount.rx++; lsr |= up->lsr_saved_flags; up->lsr_saved_flags = 0; if (unlikely(lsr & UART_LSR_BRK_ERROR_BITS)) { if (lsr & UART_LSR_BI) { lsr &= ~(UART_LSR_FE | UART_LSR_PE); port->icount.brk++; /* * We do the SysRQ and SAK checking * here because otherwise the break * may get masked by ignore_status_mask * or read_status_mask. */ if (uart_handle_break(port)) return; } else if (lsr & UART_LSR_PE) port->icount.parity++; else if (lsr & UART_LSR_FE) port->icount.frame++; if (lsr & UART_LSR_OE) port->icount.overrun++; /* * Mask off conditions which should be ignored. */ lsr &= port->read_status_mask; if (lsr & UART_LSR_BI) { dev_dbg(port->dev, "handling break\n"); flag = TTY_BREAK; } else if (lsr & UART_LSR_PE) flag = TTY_PARITY; else if (lsr & UART_LSR_FE) flag = TTY_FRAME; } if (uart_prepare_sysrq_char(port, ch)) return; uart_insert_char(port, lsr, UART_LSR_OE, ch, flag); } EXPORT_SYMBOL_GPL(serial8250_read_char); /* * serial8250_rx_chars: processes according to the passed in LSR * value, and returns the remaining LSR bits not handled * by this Rx routine. */ unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr) { struct uart_port *port = &up->port; int max_count = 256; do { serial8250_read_char(up, lsr); if (--max_count == 0) break; lsr = serial_in(up, UART_LSR); } while (lsr & (UART_LSR_DR | UART_LSR_BI)); tty_flip_buffer_push(&port->state->port); return lsr; } EXPORT_SYMBOL_GPL(serial8250_rx_chars); void serial8250_tx_chars(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct circ_buf *xmit = &port->state->xmit; int count; if (port->x_char) { uart_xchar_out(port, UART_TX); return; } if (uart_tx_stopped(port)) { serial8250_stop_tx(port); return; } if (uart_circ_empty(xmit)) { __stop_tx(up); return; } count = up->tx_loadsz; do { serial_out(up, UART_TX, xmit->buf[xmit->tail]); if (up->bugs & UART_BUG_TXRACE) { /* * The Aspeed BMC virtual UARTs have a bug where data * may get stuck in the BMC's Tx FIFO from bursts of * writes on the APB interface. * * Delay back-to-back writes by a read cycle to avoid * stalling the VUART. Read a register that won't have * side-effects and discard the result. */ serial_in(up, UART_SCR); } xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); port->icount.tx++; if (uart_circ_empty(xmit)) break; if ((up->capabilities & UART_CAP_HFIFO) && (serial_in(up, UART_LSR) & BOTH_EMPTY) != BOTH_EMPTY) break; /* The BCM2835 MINI UART THRE bit is really a not-full bit. */ if ((up->capabilities & UART_CAP_MINI) && !(serial_in(up, UART_LSR) & UART_LSR_THRE)) break; } while (--count > 0); if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); /* * With RPM enabled, we have to wait until the FIFO is empty before the * HW can go idle. So we get here once again with empty FIFO and disable * the interrupt and RPM in __stop_tx() */ if (uart_circ_empty(xmit) && !(up->capabilities & UART_CAP_RPM)) __stop_tx(up); } EXPORT_SYMBOL_GPL(serial8250_tx_chars); /* Caller holds uart port lock */ unsigned int serial8250_modem_status(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned int status = serial_in(up, UART_MSR); status |= up->msr_saved_flags; up->msr_saved_flags = 0; if (status & UART_MSR_ANY_DELTA && up->ier & UART_IER_MSI && port->state != NULL) { if (status & UART_MSR_TERI) port->icount.rng++; if (status & UART_MSR_DDSR) port->icount.dsr++; if (status & UART_MSR_DDCD) uart_handle_dcd_change(port, status & UART_MSR_DCD); if (status & UART_MSR_DCTS) uart_handle_cts_change(port, status & UART_MSR_CTS); wake_up_interruptible(&port->state->port.delta_msr_wait); } return status; } EXPORT_SYMBOL_GPL(serial8250_modem_status); static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) { switch (iir & 0x3f) { case UART_IIR_RDI: if (!up->dma->rx_running) break; fallthrough; case UART_IIR_RLSI: case UART_IIR_RX_TIMEOUT: serial8250_rx_dma_flush(up); return true; } return up->dma->rx_dma(up); } /* * This handles the interrupt from one port. */ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) { unsigned char status; unsigned long flags; struct uart_8250_port *up = up_to_u8250p(port); struct tty_port *tport = &port->state->port; bool skip_rx = false; if (iir & UART_IIR_NO_INT) return 0; spin_lock_irqsave(&port->lock, flags); status = serial_port_in(port, UART_LSR); /* * If port is stopped and there are no error conditions in the * FIFO, then don't drain the FIFO, as this may lead to TTY buffer * overflow. Not servicing, RX FIFO would trigger auto HW flow * control when FIFO occupancy reaches preset threshold, thus * halting RX. This only works when auto HW flow control is * available. */ if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) && (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) && !(port->read_status_mask & UART_LSR_DR)) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { struct irq_data *d; d = irq_get_irq_data(port->irq); if (d && irqd_is_wakeup_set(d)) pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); } serial8250_modem_status(up); if ((!up->dma || up->dma->tx_err) && (status & UART_LSR_THRE) && (up->ier & UART_IER_THRI)) serial8250_tx_chars(up); uart_unlock_and_check_sysrq(port, flags); return 1; } EXPORT_SYMBOL_GPL(serial8250_handle_irq); static int serial8250_default_handle_irq(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int iir; int ret; serial8250_rpm_get(up); iir = serial_port_in(port, UART_IIR); ret = serial8250_handle_irq(port, iir); serial8250_rpm_put(up); return ret; } /* * Newer 16550 compatible parts such as the SC16C650 & Altera 16550 Soft IP * have a programmable TX threshold that triggers the THRE interrupt in * the IIR register. In this case, the THRE interrupt indicates the FIFO * has space available. Load it up with tx_loadsz bytes. */ static int serial8250_tx_threshold_handle_irq(struct uart_port *port) { unsigned long flags; unsigned int iir = serial_port_in(port, UART_IIR); /* TX Threshold IRQ triggered so load up FIFO */ if ((iir & UART_IIR_ID) == UART_IIR_THRI) { struct uart_8250_port *up = up_to_u8250p(port); spin_lock_irqsave(&port->lock, flags); serial8250_tx_chars(up); spin_unlock_irqrestore(&port->lock, flags); } iir = serial_port_in(port, UART_IIR); return serial8250_handle_irq(port, iir); } static unsigned int serial8250_tx_empty(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int result = 0; unsigned long flags; unsigned int lsr; serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); if (!serial8250_tx_dma_running(up)) { lsr = serial_port_in(port, UART_LSR); up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; if ((lsr & BOTH_EMPTY) == BOTH_EMPTY) result = TIOCSER_TEMT; } spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); return result; } unsigned int serial8250_do_get_mctrl(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int status; unsigned int val; serial8250_rpm_get(up); status = serial8250_modem_status(up); serial8250_rpm_put(up); val = serial8250_MSR_to_TIOCM(status); if (up->gpios) return mctrl_gpio_get(up->gpios, &val); return val; } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); static unsigned int serial8250_get_mctrl(struct uart_port *port) { if (port->get_mctrl) return port->get_mctrl(port); return serial8250_do_get_mctrl(port); } void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char mcr; mcr = serial8250_TIOCM_to_MCR(mctrl); mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr; serial8250_out_MCR(up, mcr); } EXPORT_SYMBOL_GPL(serial8250_do_set_mctrl); static void serial8250_set_mctrl(struct uart_port *port, unsigned int mctrl) { if (port->rs485.flags & SER_RS485_ENABLED) return; if (port->set_mctrl) port->set_mctrl(port, mctrl); else serial8250_do_set_mctrl(port, mctrl); } static void serial8250_break_ctl(struct uart_port *port, int break_state) { struct uart_8250_port *up = up_to_u8250p(port); unsigned long flags; serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); if (break_state == -1) up->lcr |= UART_LCR_SBC; else up->lcr &= ~UART_LCR_SBC; serial_port_out(port, UART_LCR, up->lcr); spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); } /* * Wait for transmitter & holding register to empty */ static void wait_for_xmitr(struct uart_8250_port *up, int bits) { unsigned int status, tmout = 10000; /* Wait up to 10ms for the character(s) to be sent. */ for (;;) { status = serial_in(up, UART_LSR); up->lsr_saved_flags |= status & LSR_SAVE_FLAGS; if ((status & bits) == bits) break; if (--tmout == 0) break; udelay(1); touch_nmi_watchdog(); } /* Wait up to 1s for flow control if necessary */ if (up->port.flags & UPF_CONS_FLOW) { for (tmout = 1000000; tmout; tmout--) { unsigned int msr = serial_in(up, UART_MSR); up->msr_saved_flags |= msr & MSR_SAVE_FLAGS; if (msr & UART_MSR_CTS) break; udelay(1); touch_nmi_watchdog(); } } } #ifdef CONFIG_CONSOLE_POLL /* * Console polling routines for writing and reading from the uart while * in an interrupt or debug context. */ static int serial8250_get_poll_char(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char lsr; int status; serial8250_rpm_get(up); lsr = serial_port_in(port, UART_LSR); if (!(lsr & UART_LSR_DR)) { status = NO_POLL_CHAR; goto out; } status = serial_port_in(port, UART_RX); out: serial8250_rpm_put(up); return status; } static void serial8250_put_poll_char(struct uart_port *port, unsigned char c) { unsigned int ier; struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); /* * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); if (up->capabilities & UART_CAP_UUE) serial_port_out(port, UART_IER, UART_IER_UUE); else serial_port_out(port, UART_IER, 0); wait_for_xmitr(up, BOTH_EMPTY); /* * Send the character out. */ serial_port_out(port, UART_TX, c); /* * Finally, wait for transmitter to become empty * and restore the IER */ wait_for_xmitr(up, BOTH_EMPTY); serial_port_out(port, UART_IER, ier); serial8250_rpm_put(up); } #endif /* CONFIG_CONSOLE_POLL */ int serial8250_do_startup(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned long flags; unsigned char lsr, iir; int retval; if (!port->fifosize) port->fifosize = uart_config[port->type].fifo_size; if (!up->tx_loadsz) up->tx_loadsz = uart_config[port->type].tx_loadsz; if (!up->capabilities) up->capabilities = uart_config[port->type].flags; up->mcr = 0; if (port->iotype != up->cur_iotype) set_io_from_upio(port); serial8250_rpm_get(up); if (port->type == PORT_16C950) { /* Wake up and initialize UART */ up->acr = 0; serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, UART_EFR, UART_EFR_ECB); serial_port_out(port, UART_IER, 0); serial_port_out(port, UART_LCR, 0); serial_icr_write(up, UART_CSR, 0); /* Reset the UART */ serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, UART_EFR, UART_EFR_ECB); serial_port_out(port, UART_LCR, 0); } if (port->type == PORT_DA830) { /* Reset the port */ serial_port_out(port, UART_IER, 0); serial_port_out(port, UART_DA830_PWREMU_MGMT, 0); mdelay(10); /* Enable Tx, Rx and free run mode */ serial_port_out(port, UART_DA830_PWREMU_MGMT, UART_DA830_PWREMU_MGMT_UTRST | UART_DA830_PWREMU_MGMT_URRST | UART_DA830_PWREMU_MGMT_FREE); } if (port->type == PORT_NPCM) { /* * Nuvoton calls the scratch register 'UART_TOR' (timeout * register). Enable it, and set TIOC (timeout interrupt * comparator) to be 0x20 for correct operation. */ serial_port_out(port, UART_NPCM_TOR, UART_NPCM_TOIE | 0x20); } #ifdef CONFIG_SERIAL_8250_RSA /* * If this is an RSA port, see if we can kick it up to the * higher speed clock. */ enable_rsa(up); #endif /* * Clear the FIFO buffers and disable them. * (they will be reenabled in set_termios()) */ serial8250_clear_fifos(up); /* * Clear the interrupt registers. */ serial_port_in(port, UART_LSR); serial_port_in(port, UART_RX); serial_port_in(port, UART_IIR); serial_port_in(port, UART_MSR); /* * At this point, there's no way the LSR could still be 0xff; * if it is, then bail out, because there's likely no UART * here. */ if (!(port->flags & UPF_BUGGY_UART) && (serial_port_in(port, UART_LSR) == 0xff)) { dev_info_ratelimited(port->dev, "LSR safety check engaged!\n"); retval = -ENODEV; goto out; } /* * For a XR16C850, we need to set the trigger levels */ if (port->type == PORT_16850) { unsigned char fctr; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); fctr = serial_in(up, UART_FCTR) & ~(UART_FCTR_RX|UART_FCTR_TX); serial_port_out(port, UART_FCTR, fctr | UART_FCTR_TRGD | UART_FCTR_RX); serial_port_out(port, UART_TRG, UART_TRG_96); serial_port_out(port, UART_FCTR, fctr | UART_FCTR_TRGD | UART_FCTR_TX); serial_port_out(port, UART_TRG, UART_TRG_96); serial_port_out(port, UART_LCR, 0); } /* * For the Altera 16550 variants, set TX threshold trigger level. */ if (((port->type == PORT_ALTR_16550_F32) || (port->type == PORT_ALTR_16550_F64) || (port->type == PORT_ALTR_16550_F128)) && (port->fifosize > 1)) { /* Bounds checking of TX threshold (valid 0 to fifosize-2) */ if ((up->tx_loadsz < 2) || (up->tx_loadsz > port->fifosize)) { dev_err(port->dev, "TX FIFO Threshold errors, skipping\n"); } else { serial_port_out(port, UART_ALTR_AFR, UART_ALTR_EN_TXFIFO_LW); serial_port_out(port, UART_ALTR_TX_LOW, port->fifosize - up->tx_loadsz); port->handle_irq = serial8250_tx_threshold_handle_irq; } } /* Check if we need to have shared IRQs */ if (port->irq && (up->port.flags & UPF_SHARE_IRQ)) up->port.irqflags |= IRQF_SHARED; retval = up->ops->setup_irq(up); if (retval) goto out; if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) { unsigned char iir1; if (port->irqflags & IRQF_SHARED) disable_irq_nosync(port->irq); /* * Test for UARTs that do not reassert THRE when the * transmitter is idle and the interrupt has already * been cleared. Real 16550s should always reassert * this interrupt whenever the transmitter is idle and * the interrupt is enabled. Delays are necessary to * allow register changes to become visible. */ spin_lock_irqsave(&port->lock, flags); wait_for_xmitr(up, UART_LSR_THRE); serial_port_out_sync(port, UART_IER, UART_IER_THRI); udelay(1); /* allow THRE to set */ iir1 = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); serial_port_out_sync(port, UART_IER, UART_IER_THRI); udelay(1); /* allow a working UART time to re-assert THRE */ iir = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); spin_unlock_irqrestore(&port->lock, flags); if (port->irqflags & IRQF_SHARED) enable_irq(port->irq); /* * If the interrupt is not reasserted, or we otherwise * don't trust the iir, setup a timer to kick the UART * on a regular basis. */ if ((!(iir1 & UART_IIR_NO_INT) && (iir & UART_IIR_NO_INT)) || up->port.flags & UPF_BUG_THRE) { up->bugs |= UART_BUG_THRE; } } up->ops->setup_timer(up); /* * Now, initialize the UART */ spin_lock_irqsave(&port->lock, flags); serial_port_out(port, UART_LCR, UART_LCR_WLEN8); if (up->port.flags & UPF_FOURPORT) { if (!up->port.irq) up->port.mctrl |= TIOCM_OUT1; } else /* * Most PC uarts need OUT2 raised to enable interrupts. */ if (port->irq) up->port.mctrl |= TIOCM_OUT2; serial8250_set_mctrl(port, port->mctrl); /* * Serial over Lan (SoL) hack: * Intel 8257x Gigabit ethernet chips have a 16550 emulation, to be * used for Serial Over Lan. Those chips take a longer time than a * normal serial device to signalize that a transmission data was * queued. Due to that, the above test generally fails. One solution * would be to delay the reading of iir. However, this is not * reliable, since the timeout is variable. So, let's just don't * test if we receive TX irq. This way, we'll never enable * UART_BUG_TXEN. */ if (up->port.quirks & UPQ_NO_TXEN_TEST) goto dont_test_tx_en; /* * Do a quick test to see if we receive an interrupt when we enable * the TX irq. */ serial_port_out(port, UART_IER, UART_IER_THRI); lsr = serial_port_in(port, UART_LSR); iir = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); if (lsr & UART_LSR_TEMT && iir & UART_IIR_NO_INT) { if (!(up->bugs & UART_BUG_TXEN)) { up->bugs |= UART_BUG_TXEN; dev_dbg(port->dev, "enabling bad tx status workarounds\n"); } } else { up->bugs &= ~UART_BUG_TXEN; } dont_test_tx_en: spin_unlock_irqrestore(&port->lock, flags); /* * Clear the interrupt registers again for luck, and clear the * saved flags to avoid getting false values from polling * routines or the previous session. */ serial_port_in(port, UART_LSR); serial_port_in(port, UART_RX); serial_port_in(port, UART_IIR); serial_port_in(port, UART_MSR); up->lsr_saved_flags = 0; up->msr_saved_flags = 0; /* * Request DMA channels for both RX and TX. */ if (up->dma) { const char *msg = NULL; if (uart_console(port)) msg = "forbid DMA for kernel console"; else if (serial8250_request_dma(up)) msg = "failed to request DMA"; if (msg) { dev_warn_ratelimited(port->dev, "%s\n", msg); up->dma = NULL; } } /* * Set the IER shadow for rx interrupts but defer actual interrupt * enable until after the FIFOs are enabled; otherwise, an already- * active sender can swamp the interrupt handler with "too much work". */ up->ier = UART_IER_RLSI | UART_IER_RDI; if (port->flags & UPF_FOURPORT) { unsigned int icp; /* * Enable interrupts on the AST Fourport board */ icp = (port->iobase & 0xfe0) | 0x01f; outb_p(0x80, icp); inb_p(icp); } retval = 0; out: serial8250_rpm_put(up); return retval; } EXPORT_SYMBOL_GPL(serial8250_do_startup); static int serial8250_startup(struct uart_port *port) { if (port->startup) return port->startup(port); return serial8250_do_startup(port); } void serial8250_do_shutdown(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned long flags; serial8250_rpm_get(up); /* * Disable interrupts from this port */ spin_lock_irqsave(&port->lock, flags); up->ier = 0; serial_port_out(port, UART_IER, 0); spin_unlock_irqrestore(&port->lock, flags); synchronize_irq(port->irq); if (up->dma) serial8250_release_dma(up); spin_lock_irqsave(&port->lock, flags); if (port->flags & UPF_FOURPORT) { /* reset interrupts on the AST Fourport board */ inb((port->iobase & 0xfe0) | 0x1f); port->mctrl |= TIOCM_OUT1; } else port->mctrl &= ~TIOCM_OUT2; serial8250_set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); /* * Disable break condition and FIFOs */ serial_port_out(port, UART_LCR, serial_port_in(port, UART_LCR) & ~UART_LCR_SBC); serial8250_clear_fifos(up); #ifdef CONFIG_SERIAL_8250_RSA /* * Reset the RSA board back to 115kbps compat mode. */ disable_rsa(up); #endif /* * Read data port to reset things, and then unlink from * the IRQ chain. */ serial_port_in(port, UART_RX); /* * LCR writes on DW UART can trigger late (unmaskable) IRQs. * Handle them before releasing the handler. */ synchronize_irq(port->irq); serial8250_rpm_put(up); up->ops->release_irq(up); } EXPORT_SYMBOL_GPL(serial8250_do_shutdown); static void serial8250_shutdown(struct uart_port *port) { if (port->shutdown) port->shutdown(port); else serial8250_do_shutdown(port); } /* Nuvoton NPCM UARTs have a custom divisor calculation */ static unsigned int npcm_get_divisor(struct uart_8250_port *up, unsigned int baud) { struct uart_port *port = &up->port; return DIV_ROUND_CLOSEST(port->uartclk, 16 * baud + 2) - 2; } static void serial8250_flush_buffer(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma) serial8250_tx_dma_flush(up); } static unsigned int serial8250_do_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int quot; /* * Handle magic divisors for baud rates above baud_base on * SMSC SuperIO chips. * */ if ((port->flags & UPF_MAGIC_MULTIPLIER) && baud == (port->uartclk/4)) quot = 0x8001; else if ((port->flags & UPF_MAGIC_MULTIPLIER) && baud == (port->uartclk/8)) quot = 0x8002; else if (up->port.type == PORT_NPCM) quot = npcm_get_divisor(up, baud); else quot = uart_get_divisor(port, baud); /* * Oxford Semi 952 rev B workaround */ if (up->bugs & UART_BUG_QUOT && (quot & 0xff) == 0) quot++; return quot; } static unsigned int serial8250_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) { if (port->get_divisor) return port->get_divisor(port, baud, frac); return serial8250_do_get_divisor(port, baud, frac); } static unsigned char serial8250_compute_lcr(struct uart_8250_port *up, tcflag_t c_cflag) { unsigned char cval; switch (c_cflag & CSIZE) { case CS5: cval = UART_LCR_WLEN5; break; case CS6: cval = UART_LCR_WLEN6; break; case CS7: cval = UART_LCR_WLEN7; break; default: case CS8: cval = UART_LCR_WLEN8; break; } if (c_cflag & CSTOPB) cval |= UART_LCR_STOP; if (c_cflag & PARENB) cval |= UART_LCR_PARITY; if (!(c_cflag & PARODD)) cval |= UART_LCR_EPAR; #ifdef CMSPAR if (c_cflag & CMSPAR) cval |= UART_LCR_SPAR; #endif return cval; } void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot, unsigned int quot_frac) { struct uart_8250_port *up = up_to_u8250p(port); /* Workaround to enable 115200 baud on OMAP1510 internal ports */ if (is_omap1510_8250(up)) { if (baud == 115200) { quot = 1; serial_port_out(port, UART_OMAP_OSC_12M_SEL, 1); } else serial_port_out(port, UART_OMAP_OSC_12M_SEL, 0); } /* * For NatSemi, switch to bank 2 not bank 1, to avoid resetting EXCR2, * otherwise just set DLAB */ if (up->capabilities & UART_NATSEMI) serial_port_out(port, UART_LCR, 0xe0); else serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB); serial_dl_write(up, quot); } EXPORT_SYMBOL_GPL(serial8250_do_set_divisor); static void serial8250_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot, unsigned int quot_frac) { if (port->set_divisor) port->set_divisor(port, baud, quot, quot_frac); else serial8250_do_set_divisor(port, baud, quot, quot_frac); } static unsigned int serial8250_get_baud_rate(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { unsigned int tolerance = port->uartclk / 100; unsigned int min; unsigned int max; /* * Handle magic divisors for baud rates above baud_base on SMSC * Super I/O chips. Enable custom rates of clk/4 and clk/8, but * disable divisor values beyond 32767, which are unavailable. */ if (port->flags & UPF_MAGIC_MULTIPLIER) { min = port->uartclk / 16 / UART_DIV_MAX >> 1; max = (port->uartclk + tolerance) / 4; } else { min = port->uartclk / 16 / UART_DIV_MAX; max = (port->uartclk + tolerance) / 16; } /* * Ask the core to calculate the divisor for us. * Allow 1% tolerance at the upper limit so uart clks marginally * slower than nominal still match standard baud rates without * causing transmission errors. */ return uart_get_baud_rate(port, termios, old, min, max); } /* * Note in order to avoid the tty port mutex deadlock don't use the next method * within the uart port callbacks. Primarily it's supposed to be utilized to * handle a sudden reference clock rate change. */ void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk) { struct uart_8250_port *up = up_to_u8250p(port); struct tty_port *tport = &port->state->port; unsigned int baud, quot, frac = 0; struct ktermios *termios; struct tty_struct *tty; unsigned long flags; tty = tty_port_tty_get(tport); if (!tty) { mutex_lock(&tport->mutex); port->uartclk = uartclk; mutex_unlock(&tport->mutex); return; } down_write(&tty->termios_rwsem); mutex_lock(&tport->mutex); if (port->uartclk == uartclk) goto out_lock; port->uartclk = uartclk; if (!tty_port_initialized(tport)) goto out_lock; termios = &tty->termios; baud = serial8250_get_baud_rate(port, termios, NULL); quot = serial8250_get_divisor(port, baud, &frac); serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); uart_update_timeout(port, termios->c_cflag, baud); serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); out_lock: mutex_unlock(&tport->mutex); up_write(&tty->termios_rwsem); tty_kref_put(tty); } EXPORT_SYMBOL_GPL(serial8250_update_uartclk); void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char cval; unsigned long flags; unsigned int baud, quot, frac = 0; if (up->capabilities & UART_CAP_MINI) { termios->c_cflag &= ~(CSTOPB | PARENB | PARODD | CMSPAR); if ((termios->c_cflag & CSIZE) == CS5 || (termios->c_cflag & CSIZE) == CS6) termios->c_cflag = (termios->c_cflag & ~CSIZE) | CS7; } cval = serial8250_compute_lcr(up, termios->c_cflag); baud = serial8250_get_baud_rate(port, termios, old); quot = serial8250_get_divisor(port, baud, &frac); /* * Ok, we're now changing the port state. Do it with * interrupts disabled. */ serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); up->lcr = cval; /* Save computed LCR */ if (up->capabilities & UART_CAP_FIFO && port->fifosize > 1) { if (baud < 2400 && !up->dma) { up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= UART_FCR_TRIGGER_1; } } /* * MCR-based auto flow control. When AFE is enabled, RTS will be * deasserted when the receive FIFO contains more characters than * the trigger, or the MCR RTS bit is cleared. */ if (up->capabilities & UART_CAP_AFE) { up->mcr &= ~UART_MCR_AFE; if (termios->c_cflag & CRTSCTS) up->mcr |= UART_MCR_AFE; } /* * Update the per-port timeout. */ uart_update_timeout(port, termios->c_cflag, baud); port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (termios->c_iflag & INPCK) port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART_LSR_BI; /* * Characteres to ignore */ port->ignore_status_mask = 0; if (termios->c_iflag & IGNPAR) port->ignore_status_mask |= UART_LSR_PE | UART_LSR_FE; if (termios->c_iflag & IGNBRK) { port->ignore_status_mask |= UART_LSR_BI; /* * If we're ignoring parity and break indicators, * ignore overruns too (for real raw support). */ if (termios->c_iflag & IGNPAR) port->ignore_status_mask |= UART_LSR_OE; } /* * ignore all characters if CREAD is not set */ if ((termios->c_cflag & CREAD) == 0) port->ignore_status_mask |= UART_LSR_DR; /* * CTS flow control flag and modem status interrupts */ up->ier &= ~UART_IER_MSI; if (!(up->bugs & UART_BUG_NOMSR) && UART_ENABLE_MS(&up->port, termios->c_cflag)) up->ier |= UART_IER_MSI; if (up->capabilities & UART_CAP_UUE) up->ier |= UART_IER_UUE; if (up->capabilities & UART_CAP_RTOIE) up->ier |= UART_IER_RTOIE; serial_port_out(port, UART_IER, up->ier); if (up->capabilities & UART_CAP_EFR) { unsigned char efr = 0; /* * TI16C752/Startech hardware flow control. FIXME: * - TI16C752 requires control thresholds to be set. * - UART_MCR_RTS is ineffective if auto-RTS mode is enabled. */ if (termios->c_cflag & CRTSCTS) efr |= UART_EFR_CTS; serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); if (port->flags & UPF_EXAR_EFR) serial_port_out(port, UART_XR_EFR, efr); else serial_port_out(port, UART_EFR, efr); } serial8250_set_divisor(port, baud, quot, frac); /* * LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR * is written without DLAB set, this mode will be disabled. */ if (port->type == PORT_16750) serial_port_out(port, UART_FCR, up->fcr); serial_port_out(port, UART_LCR, up->lcr); /* reset DLAB */ if (port->type != PORT_16750) { /* emulated UARTs (Lucent Venus 167x) need two steps */ if (up->fcr & UART_FCR_ENABLE_FIFO) serial_port_out(port, UART_FCR, UART_FCR_ENABLE_FIFO); serial_port_out(port, UART_FCR, up->fcr); /* set fcr */ } serial8250_set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); /* Don't rewrite B0 */ if (tty_termios_baud_rate(termios)) tty_termios_encode_baud_rate(termios, baud, baud); } EXPORT_SYMBOL(serial8250_do_set_termios); static void serial8250_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { if (port->set_termios) port->set_termios(port, termios, old); else serial8250_do_set_termios(port, termios, old); } void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios) { if (termios->c_line == N_PPS) { port->flags |= UPF_HARDPPS_CD; spin_lock_irq(&port->lock); serial8250_enable_ms(port); spin_unlock_irq(&port->lock); } else { port->flags &= ~UPF_HARDPPS_CD; if (!UART_ENABLE_MS(port, termios->c_cflag)) { spin_lock_irq(&port->lock); serial8250_disable_ms(port); spin_unlock_irq(&port->lock); } } } EXPORT_SYMBOL_GPL(serial8250_do_set_ldisc); static void serial8250_set_ldisc(struct uart_port *port, struct ktermios *termios) { if (port->set_ldisc) port->set_ldisc(port, termios); else serial8250_do_set_ldisc(port, termios); } void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) { struct uart_8250_port *p = up_to_u8250p(port); serial8250_set_sleep(p, state != 0); } EXPORT_SYMBOL(serial8250_do_pm); static void serial8250_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) { if (port->pm) port->pm(port, state, oldstate); else serial8250_do_pm(port, state, oldstate); } static unsigned int serial8250_port_size(struct uart_8250_port *pt) { if (pt->port.mapsize) return pt->port.mapsize; if (pt->port.iotype == UPIO_AU) { if (pt->port.type == PORT_RT2880) return 0x100; return 0x1000; } if (is_omap1_8250(pt)) return 0x16 << pt->port.regshift; return 8 << pt->port.regshift; } /* * Resource handling. */ static int serial8250_request_std_resource(struct uart_8250_port *up) { unsigned int size = serial8250_port_size(up); struct uart_port *port = &up->port; int ret = 0; switch (port->iotype) { case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) { ret = -EINVAL; break; } if (!request_mem_region(port->mapbase, size, "serial")) { ret = -EBUSY; break; } if (port->flags & UPF_IOREMAP) { port->membase = ioremap(port->mapbase, size); if (!port->membase) { release_mem_region(port->mapbase, size); ret = -ENOMEM; } } break; case UPIO_HUB6: case UPIO_PORT: if (!request_region(port->iobase, size, "serial")) ret = -EBUSY; break; } return ret; } static void serial8250_release_std_resource(struct uart_8250_port *up) { unsigned int size = serial8250_port_size(up); struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) break; if (port->flags & UPF_IOREMAP) { iounmap(port->membase); port->membase = NULL; } release_mem_region(port->mapbase, size); break; case UPIO_HUB6: case UPIO_PORT: release_region(port->iobase, size); break; } } static void serial8250_release_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_release_std_resource(up); } static int serial8250_request_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); return serial8250_request_std_resource(up); } static int fcr_get_rxtrig_bytes(struct uart_8250_port *up) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; unsigned char bytes; bytes = conf_type->rxtrig_bytes[UART_FCR_R_TRIG_BITS(up->fcr)]; return bytes ? bytes : -EOPNOTSUPP; } static int bytes_to_fcr_rxtrig(struct uart_8250_port *up, unsigned char bytes) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; int i; if (!conf_type->rxtrig_bytes[UART_FCR_R_TRIG_BITS(UART_FCR_R_TRIG_00)]) return -EOPNOTSUPP; for (i = 1; i < UART_FCR_R_TRIG_MAX_STATE; i++) { if (bytes < conf_type->rxtrig_bytes[i]) /* Use the nearest lower value */ return (--i) << UART_FCR_R_TRIG_SHIFT; } return UART_FCR_R_TRIG_11; } static int do_get_rxtrig(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = state->uart_port; struct uart_8250_port *up = up_to_u8250p(uport); if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) return -EINVAL; return fcr_get_rxtrig_bytes(up); } static int do_serial8250_get_rxtrig(struct tty_port *port) { int rxtrig_bytes; mutex_lock(&port->mutex); rxtrig_bytes = do_get_rxtrig(port); mutex_unlock(&port->mutex); return rxtrig_bytes; } static ssize_t rx_trig_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); int rxtrig_bytes; rxtrig_bytes = do_serial8250_get_rxtrig(port); if (rxtrig_bytes < 0) return rxtrig_bytes; return snprintf(buf, PAGE_SIZE, "%d\n", rxtrig_bytes); } static int do_set_rxtrig(struct tty_port *port, unsigned char bytes) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = state->uart_port; struct uart_8250_port *up = up_to_u8250p(uport); int rxtrig; if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) return -EINVAL; rxtrig = bytes_to_fcr_rxtrig(up, bytes); if (rxtrig < 0) return rxtrig; serial8250_clear_fifos(up); up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= (unsigned char)rxtrig; serial_out(up, UART_FCR, up->fcr); return 0; } static int do_serial8250_set_rxtrig(struct tty_port *port, unsigned char bytes) { int ret; mutex_lock(&port->mutex); ret = do_set_rxtrig(port, bytes); mutex_unlock(&port->mutex); return ret; } static ssize_t rx_trig_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); unsigned char bytes; int ret; if (!count) return -EINVAL; ret = kstrtou8(buf, 10, &bytes); if (ret < 0) return ret; ret = do_serial8250_set_rxtrig(port, bytes); if (ret < 0) return ret; return count; } static DEVICE_ATTR_RW(rx_trig_bytes); static struct attribute *serial8250_dev_attrs[] = { &dev_attr_rx_trig_bytes.attr, NULL }; static struct attribute_group serial8250_dev_attr_group = { .attrs = serial8250_dev_attrs, }; static void register_dev_spec_attr_grp(struct uart_8250_port *up) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; if (conf_type->rxtrig_bytes[0]) up->port.attr_group = &serial8250_dev_attr_group; } static void serial8250_config_port(struct uart_port *port, int flags) { struct uart_8250_port *up = up_to_u8250p(port); int ret; /* * Find the region that we can probe for. This in turn * tells us whether we can probe for the type of port. */ ret = serial8250_request_std_resource(up); if (ret < 0) return; if (port->iotype != up->cur_iotype) set_io_from_upio(port); if (flags & UART_CONFIG_TYPE) autoconfig(up); /* if access method is AU, it is a 16550 with a quirk */ if (port->type == PORT_16550A && port->iotype == UPIO_AU) up->bugs |= UART_BUG_NOMSR; /* HW bugs may trigger IRQ while IIR == NO_INT */ if (port->type == PORT_TEGRA) up->bugs |= UART_BUG_NOMSR; if (port->type != PORT_UNKNOWN && flags & UART_CONFIG_IRQ) autoconfig_irq(up); if (port->type == PORT_UNKNOWN) serial8250_release_std_resource(up); register_dev_spec_attr_grp(up); up->fcr = uart_config[up->port.type].fcr; } static int serial8250_verify_port(struct uart_port *port, struct serial_struct *ser) { if (ser->irq >= nr_irqs || ser->irq < 0 || ser->baud_base < 9600 || ser->type < PORT_UNKNOWN || ser->type >= ARRAY_SIZE(uart_config) || ser->type == PORT_CIRRUS || ser->type == PORT_STARTECH) return -EINVAL; return 0; } static const char *serial8250_type(struct uart_port *port) { int type = port->type; if (type >= ARRAY_SIZE(uart_config)) type = 0; return uart_config[type].name; } static const struct uart_ops serial8250_pops = { .tx_empty = serial8250_tx_empty, .set_mctrl = serial8250_set_mctrl, .get_mctrl = serial8250_get_mctrl, .stop_tx = serial8250_stop_tx, .start_tx = serial8250_start_tx, .throttle = serial8250_throttle, .unthrottle = serial8250_unthrottle, .stop_rx = serial8250_stop_rx, .enable_ms = serial8250_enable_ms, .break_ctl = serial8250_break_ctl, .startup = serial8250_startup, .shutdown = serial8250_shutdown, .flush_buffer = serial8250_flush_buffer, .set_termios = serial8250_set_termios, .set_ldisc = serial8250_set_ldisc, .pm = serial8250_pm, .type = serial8250_type, .release_port = serial8250_release_port, .request_port = serial8250_request_port, .config_port = serial8250_config_port, .verify_port = serial8250_verify_port, #ifdef CONFIG_CONSOLE_POLL .poll_get_char = serial8250_get_poll_char, .poll_put_char = serial8250_put_poll_char, #endif }; void serial8250_init_port(struct uart_8250_port *up) { struct uart_port *port = &up->port; spin_lock_init(&port->lock); port->pm = NULL; port->ops = &serial8250_pops; port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); up->cur_iotype = 0xFF; } EXPORT_SYMBOL_GPL(serial8250_init_port); void serial8250_set_defaults(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (up->port.flags & UPF_FIXED_TYPE) { unsigned int type = up->port.type; if (!up->port.fifosize) up->port.fifosize = uart_config[type].fifo_size; if (!up->tx_loadsz) up->tx_loadsz = uart_config[type].tx_loadsz; if (!up->capabilities) up->capabilities = uart_config[type].flags; } set_io_from_upio(port); /* default dma handlers */ if (up->dma) { if (!up->dma->tx_dma) up->dma->tx_dma = serial8250_tx_dma; if (!up->dma->rx_dma) up->dma->rx_dma = serial8250_rx_dma; } } EXPORT_SYMBOL_GPL(serial8250_set_defaults); #ifdef CONFIG_SERIAL_8250_CONSOLE static void serial8250_console_putchar(struct uart_port *port, int ch) { struct uart_8250_port *up = up_to_u8250p(port); wait_for_xmitr(up, UART_LSR_THRE); serial_port_out(port, UART_TX, ch); } /* * Restore serial console when h/w power-off detected */ static void serial8250_console_restore(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct ktermios termios; unsigned int baud, quot, frac = 0; termios.c_cflag = port->cons->cflag; termios.c_ispeed = port->cons->ispeed; termios.c_ospeed = port->cons->ospeed; if (port->state->port.tty && termios.c_cflag == 0) { termios.c_cflag = port->state->port.tty->termios.c_cflag; termios.c_ispeed = port->state->port.tty->termios.c_ispeed; termios.c_ospeed = port->state->port.tty->termios.c_ospeed; } baud = serial8250_get_baud_rate(port, &termios, NULL); quot = serial8250_get_divisor(port, baud, &frac); serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } /* * Print a string to the serial port trying not to disturb * any possible real use of the port... * * The console_lock must be held when we get here. * * Doing runtime PM is really a bad idea for the kernel console. * Thus, we assume the function is called when device is powered up. */ void serial8250_console_write(struct uart_8250_port *up, const char *s, unsigned int count) { struct uart_8250_em485 *em485 = up->em485; struct uart_port *port = &up->port; unsigned long flags; unsigned int ier; int locked = 1; touch_nmi_watchdog(); if (oops_in_progress) locked = spin_trylock_irqsave(&port->lock, flags); else spin_lock_irqsave(&port->lock, flags); /* * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); if (up->capabilities & UART_CAP_UUE) serial_port_out(port, UART_IER, UART_IER_UUE); else serial_port_out(port, UART_IER, 0); /* check scratch reg to see if port powered off during system sleep */ if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { serial8250_console_restore(up); up->canary = 0; } if (em485) { if (em485->tx_stopped) up->rs485_start_tx(up); mdelay(port->rs485.delay_rts_before_send); } uart_console_write(port, s, count, serial8250_console_putchar); /* * Finally, wait for transmitter to become empty * and restore the IER */ wait_for_xmitr(up, BOTH_EMPTY); if (em485) { mdelay(port->rs485.delay_rts_after_send); if (em485->tx_stopped) up->rs485_stop_tx(up); } serial_port_out(port, UART_IER, ier); /* * The receive handling will happen properly because the * receive ready bit will still be set; it is not cleared * on read. However, modem control will not, we must * call it if we have saved something in the saved flags * while processing with interrupts off. */ if (up->msr_saved_flags) serial8250_modem_status(up); if (locked) spin_unlock_irqrestore(&port->lock, flags); } static unsigned int probe_baud(struct uart_port *port) { unsigned char lcr, dll, dlm; unsigned int quot; lcr = serial_port_in(port, UART_LCR); serial_port_out(port, UART_LCR, lcr | UART_LCR_DLAB); dll = serial_port_in(port, UART_DLL); dlm = serial_port_in(port, UART_DLM); serial_port_out(port, UART_LCR, lcr); quot = (dlm << 8) | dll; return (port->uartclk / 16) / quot; } int serial8250_console_setup(struct uart_port *port, char *options, bool probe) { int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; int ret; if (!port->iobase && !port->membase) return -ENODEV; if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else if (probe) baud = probe_baud(port); ret = uart_set_options(port, port->cons, baud, parity, bits, flow); if (ret) return ret; if (port->dev) pm_runtime_get_sync(port->dev); return 0; } int serial8250_console_exit(struct uart_port *port) { if (port->dev) pm_runtime_put_sync(port->dev); return 0; } #endif /* CONFIG_SERIAL_8250_CONSOLE */ MODULE_LICENSE("GPL"); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Kernel Probes (KProbes) * kernel/kprobes.c * * Copyright (C) IBM Corporation, 2002, 2004 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation (includes suggestions from * Rusty Russell). * 2004-Aug Updated by Prasanna S Panchamukhi <prasanna@in.ibm.com> with * hlists and exceptions notifier as suggested by Andi Kleen. * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes * interface to access function arguments. * 2004-Sep Prasanna S Panchamukhi <prasanna@in.ibm.com> Changed Kprobes * exceptions notifier to be first on the priority list. * 2005-May Hien Nguyen <hien@us.ibm.com>, Jim Keniston * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ #include <linux/kprobes.h> #include <linux/hash.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/export.h> #include <linux/moduleloader.h> #include <linux/kallsyms.h> #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/sysctl.h> #include <linux/kdebug.h> #include <linux/memory.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/jump_label.h> #include <linux/perf_event.h> #include <linux/static_call.h> #include <asm/sections.h> #include <asm/cacheflush.h> #include <asm/errno.h> #include <linux/uaccess.h> #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) static int kprobes_initialized; /* kprobe_table can be accessed by * - Normal hlist traversal and RCU add/del under kprobe_mutex is held. * Or * - RCU hlist traversal under disabling preempt (breakpoint handlers) */ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; /* NOTE: change this value only with kprobe_mutex held */ static bool kprobes_all_disarmed; /* This protects kprobe_table and optimizing_list */ static DEFINE_MUTEX(kprobe_mutex); static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { raw_spinlock_t lock ____cacheline_aligned_in_smp; } kretprobe_table_locks[KPROBE_TABLE_SIZE]; kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, unsigned int __unused) { return ((kprobe_opcode_t *)(kallsyms_lookup_name(name))); } static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) { return &(kretprobe_table_locks[hash].lock); } /* Blacklist -- list of struct kprobe_blacklist_entry */ static LIST_HEAD(kprobe_blacklist); #ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* * kprobe->ainsn.insn points to the copy of the instruction to be * single-stepped. x86_64, POWER4 and above have no-exec support and * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster */ struct kprobe_insn_page { struct list_head list; kprobe_opcode_t *insns; /* Page of instruction slots */ struct kprobe_insn_cache *cache; int nused; int ngarbage; char slot_used[]; }; #define KPROBE_INSN_PAGE_SIZE(slots) \ (offsetof(struct kprobe_insn_page, slot_used) + \ (sizeof(char) * (slots))) static int slots_per_page(struct kprobe_insn_cache *c) { return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t)); } enum kprobe_slot_state { SLOT_CLEAN = 0, SLOT_DIRTY = 1, SLOT_USED = 2, }; void __weak *alloc_insn_page(void) { return module_alloc(PAGE_SIZE); } void __weak free_insn_page(void *page) { module_memfree(page); } struct kprobe_insn_cache kprobe_insn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, .sym = KPROBE_INSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), .insn_size = MAX_INSN_SIZE, .nr_garbage = 0, }; static int collect_garbage_slots(struct kprobe_insn_cache *c); /** * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; kprobe_opcode_t *slot = NULL; /* Since the slot array is not protected by rcu, we need a mutex */ mutex_lock(&c->mutex); retry: rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if (kip->nused < slots_per_page(c)) { int i; for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; kip->nused++; slot = kip->insns + (i * c->insn_size); rcu_read_unlock(); goto out; } } /* kip->nused is broken. Fix it. */ kip->nused = slots_per_page(c); WARN_ON(1); } } rcu_read_unlock(); /* If there are any garbage slots, collect it and try again. */ if (c->nr_garbage && collect_garbage_slots(c) == 0) goto retry; /* All out of space. Need to allocate a new page. */ kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL); if (!kip) goto out; /* * Use module_alloc so this page is within +/- 2GB of where the * kernel image and loaded module images reside. This is required * so x86_64 can correctly handle the %rip-relative fixups. */ kip->insns = c->alloc(); if (!kip->insns) { kfree(kip); goto out; } INIT_LIST_HEAD(&kip->list); memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); kip->slot_used[0] = SLOT_USED; kip->nused = 1; kip->ngarbage = 0; kip->cache = c; list_add_rcu(&kip->list, &c->pages); slot = kip->insns; /* Record the perf ksymbol register event after adding the page */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, false, c->sym); out: mutex_unlock(&c->mutex); return slot; } /* Return 1 if all garbages are collected, otherwise 0. */ static int collect_one_slot(struct kprobe_insn_page *kip, int idx) { kip->slot_used[idx] = SLOT_CLEAN; kip->nused--; if (kip->nused == 0) { /* * Page is no longer in use. Free it unless * it's the last one. We keep the last one * so as not to have to set it up again the * next time somebody inserts a probe. */ if (!list_is_singular(&kip->list)) { /* * Record perf ksymbol unregister event before removing * the page. */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, true, kip->cache->sym); list_del_rcu(&kip->list); synchronize_rcu(); kip->cache->free(kip->insns); kfree(kip); } return 1; } return 0; } static int collect_garbage_slots(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip, *next; /* Ensure no-one is interrupted on the garbages */ synchronize_rcu(); list_for_each_entry_safe(kip, next, &c->pages, list) { int i; if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i)) break; } } c->nr_garbage = 0; return 0; } void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; long idx; mutex_lock(&c->mutex); rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { idx = ((long)slot - (long)kip->insns) / (c->insn_size * sizeof(kprobe_opcode_t)); if (idx >= 0 && idx < slots_per_page(c)) goto out; } /* Could not find this slot. */ WARN_ON(1); kip = NULL; out: rcu_read_unlock(); /* Mark and sweep: this may sleep */ if (kip) { /* Check double free */ WARN_ON(kip->slot_used[idx] != SLOT_USED); if (dirty) { kip->slot_used[idx] = SLOT_DIRTY; kip->ngarbage++; if (++c->nr_garbage > slots_per_page(c)) collect_garbage_slots(c); } else { collect_one_slot(kip, idx); } } mutex_unlock(&c->mutex); } /* * Check given address is on the page of kprobe instruction slots. * This will be used for checking whether the address on a stack * is on a text area or not. */ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr) { struct kprobe_insn_page *kip; bool ret = false; rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if (addr >= (unsigned long)kip->insns && addr < (unsigned long)kip->insns + PAGE_SIZE) { ret = true; break; } } rcu_read_unlock(); return ret; } int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, unsigned long *value, char *type, char *sym) { struct kprobe_insn_page *kip; int ret = -ERANGE; rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if ((*symnum)--) continue; strlcpy(sym, c->sym, KSYM_NAME_LEN); *type = 't'; *value = (unsigned long)kip->insns; ret = 0; break; } rcu_read_unlock(); return ret; } #ifdef CONFIG_OPTPROBES /* For optimized_kprobe buffer */ struct kprobe_insn_cache kprobe_optinsn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, .sym = KPROBE_OPTINSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), /* .insn_size is initialized later */ .nr_garbage = 0, }; #endif #endif /* We have preemption disabled.. so it is safe to use __ versions */ static inline void set_kprobe_instance(struct kprobe *kp) { __this_cpu_write(kprobe_instance, kp); } static inline void reset_kprobe_instance(void) { __this_cpu_write(kprobe_instance, NULL); } /* * This routine is called either: * - under the kprobe_mutex - during kprobe_[un]register() * OR * - with preemption disabled - from arch/xxx/kernel/kprobes.c */ struct kprobe *get_kprobe(void *addr) { struct hlist_head *head; struct kprobe *p; head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; hlist_for_each_entry_rcu(p, head, hlist, lockdep_is_held(&kprobe_mutex)) { if (p->addr == addr) return p; } return NULL; } NOKPROBE_SYMBOL(get_kprobe); static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); /* Return true if the kprobe is an aggregator */ static inline int kprobe_aggrprobe(struct kprobe *p) { return p->pre_handler == aggr_pre_handler; } /* Return true(!0) if the kprobe is unused */ static inline int kprobe_unused(struct kprobe *p) { return kprobe_aggrprobe(p) && kprobe_disabled(p) && list_empty(&p->list); } /* * Keep all fields in the kprobe consistent */ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) { memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t)); memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn)); } #ifdef CONFIG_OPTPROBES /* NOTE: change this value only with kprobe_mutex held */ static bool kprobes_allow_optimization; /* * Call all pre_handler on the list, but ignores its return value. * This must be called from arch-dep optimized caller. */ void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->pre_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); kp->pre_handler(kp, regs); } reset_kprobe_instance(); } } NOKPROBE_SYMBOL(opt_pre_handler); /* Free optimized instructions and optimized_kprobe */ static void free_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); arch_remove_optimized_kprobe(op); arch_remove_kprobe(p); kfree(op); } /* Return true(!0) if the kprobe is ready for optimization. */ static inline int kprobe_optready(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); return arch_prepared_optinsn(&op->optinsn); } return 0; } /* Return true if the kprobe is disarmed. Note: p must be on hash list */ bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; /* If kprobe is not aggr/opt probe, just return kprobe is disabled */ if (!kprobe_aggrprobe(p)) return kprobe_disabled(p); op = container_of(p, struct optimized_kprobe, kp); return kprobe_disabled(p) && list_empty(&op->list); } /* Return true(!0) if the probe is queued on (un)optimizing lists */ static int kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) return 1; } return 0; } /* * Return an optimized kprobe whose optimizing code replaces * instructions including addr (exclude breakpoint). */ static struct kprobe *get_optimized_kprobe(unsigned long addr) { int i; struct kprobe *p = NULL; struct optimized_kprobe *op; /* Don't check i == 0, since that is a breakpoint case. */ for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) p = get_kprobe((void *)(addr - i)); if (p && kprobe_optready(p)) { op = container_of(p, struct optimized_kprobe, kp); if (arch_within_optimized_kprobe(op, addr)) return p; } return NULL; } /* Optimization staging list, protected by kprobe_mutex */ static LIST_HEAD(optimizing_list); static LIST_HEAD(unoptimizing_list); static LIST_HEAD(freeing_list); static void kprobe_optimizer(struct work_struct *work); static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); #define OPTIMIZE_DELAY 5 /* * Optimize (replace a breakpoint with a jump) kprobes listed on * optimizing_list. */ static void do_optimize_kprobes(void) { lockdep_assert_held(&text_mutex); /* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus. * And same time, text_mutex will be held in cpu-hotplug and here. * This combination can cause a deadlock (cpu-hotplug try to lock * text_mutex but stop_machine can not be done because online_cpus * has been changed) * To avoid this deadlock, caller must have locked cpu hotplug * for preventing cpu-hotplug outside of text_mutex locking. */ lockdep_assert_cpus_held(); /* Optimization never be done when disarmed */ if (kprobes_all_disarmed || !kprobes_allow_optimization || list_empty(&optimizing_list)) return; arch_optimize_kprobes(&optimizing_list); } /* * Unoptimize (replace a jump with a breakpoint and remove the breakpoint * if need) kprobes listed on unoptimizing_list. */ static void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; lockdep_assert_held(&text_mutex); /* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held(); if (!list_empty(&unoptimizing_list)) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop on 'freeing_list' for disarming and removing from kprobe hash list */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { /* Switching from detour code to origin */ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled and not gone */ if (kprobe_disabled(&op->kp) && !kprobe_gone(&op->kp)) arch_disarm_kprobe(&op->kp); if (kprobe_unused(&op->kp)) { /* * Remove unused probes from hash list. After waiting * for synchronization, these probes are reclaimed. * (reclaiming is done by do_free_cleaned_kprobes.) */ hlist_del_rcu(&op->kp.hlist); } else list_del_init(&op->list); } } /* Reclaim all kprobes on the free_list */ static void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; list_for_each_entry_safe(op, tmp, &freeing_list, list) { list_del_init(&op->list); if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) { /* * This must not happen, but if there is a kprobe * still in use, keep it on kprobes hash list. */ continue; } free_aggr_kprobe(&op->kp); } } /* Start optimizer after OPTIMIZE_DELAY passed */ static void kick_kprobe_optimizer(void) { schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); } /* Kprobe jump optimizer */ static void kprobe_optimizer(struct work_struct *work) { mutex_lock(&kprobe_mutex); cpus_read_lock(); mutex_lock(&text_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) * kprobes before waiting for quiesence period. */ do_unoptimize_kprobes(); /* * Step 2: Wait for quiesence period to ensure all potentially * preempted tasks to have normally scheduled. Because optprobe * may modify multiple instructions, there is a chance that Nth * instruction is preempted. In that case, such tasks can return * to 2nd-Nth byte of jump instruction. This wait is for avoiding it. * Note that on non-preemptive kernel, this is transparently converted * to synchronoze_sched() to wait for all interrupts to have completed. */ synchronize_rcu_tasks(); /* Step 3: Optimize kprobes after quiesence period */ do_optimize_kprobes(); /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(); mutex_unlock(&text_mutex); cpus_read_unlock(); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { mutex_unlock(&kprobe_mutex); /* this will also make optimizing_work execute immmediately */ flush_delayed_work(&optimizing_work); /* @optimizing_work might not have been queued yet, relax */ cpu_relax(); mutex_lock(&kprobe_mutex); } mutex_unlock(&kprobe_mutex); } bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; list_for_each_entry(_op, &unoptimizing_list, list) { if (op == _op) return true; } return false; } /* Optimize kprobe if p is ready to be optimized */ static void optimize_kprobe(struct kprobe *p) { struct optimized_kprobe *op; /* Check if the kprobe is disabled or not ready for optimization. */ if (!kprobe_optready(p) || !kprobes_allow_optimization || (kprobe_disabled(p) || kprobes_all_disarmed)) return; /* kprobes with post_handler can not be optimized */ if (p->post_handler) return; op = container_of(p, struct optimized_kprobe, kp); /* Check there is no other kprobes at the optimized instructions */ if (arch_check_optimized_kprobe(op) < 0) return; /* Check if it is already optimized. */ if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) { if (optprobe_queued_unopt(op)) { /* This is under unoptimizing. Just dequeue the probe */ list_del_init(&op->list); } return; } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ if (WARN_ON_ONCE(!list_empty(&op->list))) return; list_add(&op->list, &optimizing_list); kick_kprobe_optimizer(); } /* Short cut to direct unoptimizing */ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; } /* Unoptimize a kprobe if p is optimized */ static void unoptimize_kprobe(struct kprobe *p, bool force) { struct optimized_kprobe *op; if (!kprobe_aggrprobe(p) || kprobe_disarmed(p)) return; /* This is not an optprobe nor optimized */ op = container_of(p, struct optimized_kprobe, kp); if (!kprobe_optimized(p)) return; if (!list_empty(&op->list)) { if (optprobe_queued_unopt(op)) { /* Queued in unoptimizing queue */ if (force) { /* * Forcibly unoptimize the kprobe here, and queue it * in the freeing list for release afterwards. */ force_unoptimize_kprobe(op); list_move(&op->list, &freeing_list); } } else { /* Dequeue from the optimizing queue */ list_del_init(&op->list); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; } return; } /* Optimized kprobe case */ if (force) { /* Forcibly update the code: this is a special case */ force_unoptimize_kprobe(op); } else { list_add(&op->list, &unoptimizing_list); kick_kprobe_optimizer(); } } /* Cancel unoptimizing for reusing */ static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means * there is still a relative jump) and disabled. */ op = container_of(ap, struct optimized_kprobe, kp); WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ if (!kprobe_optready(ap)) return -EINVAL; optimize_kprobe(ap); return 0; } /* Remove optimized instructions */ static void kill_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) /* Dequeue from the (un)optimization queue */ list_del_init(&op->list); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_unused(p)) { /* * Unused kprobe is on unoptimizing or freeing list. We move it * to freeing_list and let the kprobe_optimizer() remove it from * the kprobe hash list and free it. */ if (optprobe_queued_unopt(op)) list_move(&op->list, &freeing_list); } /* Don't touch the code, because it is already freed. */ arch_remove_optimized_kprobe(op); } static inline void __prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) { if (!kprobe_ftrace(p)) arch_prepare_optimized_kprobe(op, p); } /* Try to prepare optimized instructions */ static void prepare_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); __prepare_optimized_kprobe(op, p); } /* Allocate new optimized_kprobe and try to prepare optimized instructions */ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); if (!op) return NULL; INIT_LIST_HEAD(&op->list); op->kp.addr = p->addr; __prepare_optimized_kprobe(op, p); return &op->kp; } static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); /* * Prepare an optimized_kprobe and optimize it * NOTE: p must be a normal registered kprobe */ static void try_to_optimize_kprobe(struct kprobe *p) { struct kprobe *ap; struct optimized_kprobe *op; /* Impossible to optimize ftrace-based kprobe */ if (kprobe_ftrace(p)) return; /* For preparing optimization, jump_label_text_reserved() is called */ cpus_read_lock(); jump_label_lock(); mutex_lock(&text_mutex); ap = alloc_aggr_kprobe(p); if (!ap) goto out; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe */ arch_remove_optimized_kprobe(op); kfree(op); goto out; } init_aggr_kprobe(ap, p); optimize_kprobe(ap); /* This just kicks optimizer thread */ out: mutex_unlock(&text_mutex); jump_label_unlock(); cpus_read_unlock(); } static void optimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; mutex_lock(&kprobe_mutex); /* If optimization is already allowed, just return */ if (kprobes_allow_optimization) goto out; cpus_read_lock(); kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) if (!kprobe_disabled(p)) optimize_kprobe(p); } cpus_read_unlock(); printk(KERN_INFO "Kprobes globally optimized\n"); out: mutex_unlock(&kprobe_mutex); } #ifdef CONFIG_SYSCTL static void unoptimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; mutex_lock(&kprobe_mutex); /* If optimization is already prohibited, just return */ if (!kprobes_allow_optimization) { mutex_unlock(&kprobe_mutex); return; } cpus_read_lock(); kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) unoptimize_kprobe(p, false); } } cpus_read_unlock(); mutex_unlock(&kprobe_mutex); /* Wait for unoptimizing completion */ wait_for_kprobe_optimizer(); printk(KERN_INFO "Kprobes globally unoptimized\n"); } static DEFINE_MUTEX(kprobe_sysctl_mutex); int sysctl_kprobes_optimization; int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; mutex_lock(&kprobe_sysctl_mutex); sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (sysctl_kprobes_optimization) optimize_all_kprobes(); else unoptimize_all_kprobes(); mutex_unlock(&kprobe_sysctl_mutex); return ret; } #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. Must be called with text_mutex locked */ static void __arm_kprobe(struct kprobe *p) { struct kprobe *_p; /* Check collision with other optimized kprobes */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p)) /* Fallback to unoptimized kprobe */ unoptimize_kprobe(_p, true); arch_arm_kprobe(p); optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ } /* Remove the breakpoint of a probe. Must be called with text_mutex locked */ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; /* Try to unoptimize */ unoptimize_kprobe(p, kprobes_all_disarmed); if (!kprobe_queued(p)) { arch_disarm_kprobe(p); /* If another kprobe was blocked, optimize it. */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p) && reopt) optimize_kprobe(_p); } /* TODO: reoptimize others after unoptimized this probe */ } #else /* !CONFIG_OPTPROBES */ #define optimize_kprobe(p) do {} while (0) #define unoptimize_kprobe(p, f) do {} while (0) #define kill_optimized_kprobe(p) do {} while (0) #define prepare_optimized_kprobe(p) do {} while (0) #define try_to_optimize_kprobe(p) do {} while (0) #define __arm_kprobe(p) arch_arm_kprobe(p) #define __disarm_kprobe(p, o) arch_disarm_kprobe(p) #define kprobe_disarmed(p) kprobe_disabled(p) #define wait_for_kprobe_optimizer() do {} while (0) static int reuse_unused_kprobe(struct kprobe *ap) { /* * If the optimized kprobe is NOT supported, the aggr kprobe is * released at the same time that the last aggregated kprobe is * unregistered. * Thus there should be no chance to reuse unused kprobe. */ printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); return -EINVAL; } static void free_aggr_kprobe(struct kprobe *p) { arch_remove_kprobe(p); kfree(p); } static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { return kzalloc(sizeof(struct kprobe), GFP_KERNEL); } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS, }; static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_IPMODIFY, }; static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; /* Must ensure p->addr is really on ftrace */ static int prepare_kprobe(struct kprobe *p) { if (!kprobe_ftrace(p)) return arch_prepare_kprobe(p); return arch_prepare_kprobe_ftrace(p); } /* Caller must lock kprobe_mutex */ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); if (ret) { pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", p->addr, ret); return ret; } if (*cnt == 0) { ret = register_ftrace_function(ops); if (ret) { pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); goto err_ftrace; } } (*cnt)++; return ret; err_ftrace: /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. */ ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); return ret; } static int arm_kprobe_ftrace(struct kprobe *p) { bool ipmodify = (p->post_handler != NULL); return __arm_kprobe_ftrace(p, ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } /* Caller must lock kprobe_mutex */ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; if (*cnt == 1) { ret = unregister_ftrace_function(ops); if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) return ret; } (*cnt)--; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", p->addr, ret); return ret; } static int disarm_kprobe_ftrace(struct kprobe *p) { bool ipmodify = (p->post_handler != NULL); return __disarm_kprobe_ftrace(p, ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ static inline int prepare_kprobe(struct kprobe *p) { return arch_prepare_kprobe(p); } static inline int arm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; } static inline int disarm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; } #endif /* Arm a kprobe with text_mutex */ static int arm_kprobe(struct kprobe *kp) { if (unlikely(kprobe_ftrace(kp))) return arm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); return 0; } /* Disarm a kprobe with text_mutex */ static int disarm_kprobe(struct kprobe *kp, bool reopt) { if (unlikely(kprobe_ftrace(kp))) return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); return 0; } /* * Aggregate handlers for multiple kprobes support - these handlers * take care of invoking the individual kprobe handlers on p->list */ static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->pre_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); if (kp->pre_handler(kp, regs)) return 1; } reset_kprobe_instance(); } return 0; } NOKPROBE_SYMBOL(aggr_pre_handler); static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, unsigned long flags) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->post_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); kp->post_handler(kp, regs, flags); reset_kprobe_instance(); } } } NOKPROBE_SYMBOL(aggr_post_handler); static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr) { struct kprobe *cur = __this_cpu_read(kprobe_instance); /* * if we faulted "during" the execution of a user specified * probe handler, invoke just that probe's fault handler */ if (cur && cur->fault_handler) { if (cur->fault_handler(cur, regs, trapnr)) return 1; } return 0; } NOKPROBE_SYMBOL(aggr_fault_handler); /* Walks the list and increments nmissed count for multiprobe case */ void kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) kp->nmissed++; } return; } NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); static void recycle_rp_inst(struct kretprobe_instance *ri) { struct kretprobe *rp = ri->rp; /* remove rp inst off the rprobe_inst_table */ hlist_del(&ri->hlist); INIT_HLIST_NODE(&ri->hlist); if (likely(rp)) { raw_spin_lock(&rp->lock); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock(&rp->lock); } else kfree_rcu(ri, rcu); } NOKPROBE_SYMBOL(recycle_rp_inst); static void kretprobe_hash_lock(struct task_struct *tsk, struct hlist_head **head, unsigned long *flags) __acquires(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); raw_spinlock_t *hlist_lock; *head = &kretprobe_inst_table[hash]; hlist_lock = kretprobe_table_lock_ptr(hash); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. * Differentiate when it is taken in NMI context. */ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_hash_lock); static void kretprobe_table_lock(unsigned long hash, unsigned long *flags) __acquires(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. * Differentiate when it is taken in NMI context. */ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_table_lock); static void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags) __releases(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); raw_spinlock_t *hlist_lock; hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } NOKPROBE_SYMBOL(kretprobe_hash_unlock); static void kretprobe_table_unlock(unsigned long hash, unsigned long *flags) __releases(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } NOKPROBE_SYMBOL(kretprobe_table_unlock); static struct kprobe kprobe_busy = { .addr = (void *) get_kprobe, }; void kprobe_busy_begin(void) { struct kprobe_ctlblk *kcb; preempt_disable(); __this_cpu_write(current_kprobe, &kprobe_busy); kcb = get_kprobe_ctlblk(); kcb->kprobe_status = KPROBE_HIT_ACTIVE; } void kprobe_busy_end(void) { __this_cpu_write(current_kprobe, NULL); preempt_enable(); } /* * This function is called from finish_task_switch when task tk becomes dead, * so that we can recycle any function-return probe instances associated * with this task. These left over instances represent probed functions * that have been called but will never return. */ void kprobe_flush_task(struct task_struct *tk) { struct kretprobe_instance *ri; struct hlist_head *head; struct hlist_node *tmp; unsigned long hash, flags = 0; if (unlikely(!kprobes_initialized)) /* Early boot. kretprobe_table_locks not yet initialized. */ return; kprobe_busy_begin(); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task == tk) recycle_rp_inst(ri); } kretprobe_table_unlock(hash, &flags); kprobe_busy_end(); } NOKPROBE_SYMBOL(kprobe_flush_task); static inline void free_rp_inst(struct kretprobe *rp) { struct kretprobe_instance *ri; struct hlist_node *next; hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) { hlist_del(&ri->hlist); kfree(ri); } } static void cleanup_rp_inst(struct kretprobe *rp) { unsigned long flags, hash; struct kretprobe_instance *ri; struct hlist_node *next; struct hlist_head *head; /* To avoid recursive kretprobe by NMI, set kprobe busy here */ kprobe_busy_begin(); for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) { kretprobe_table_lock(hash, &flags); head = &kretprobe_inst_table[hash]; hlist_for_each_entry_safe(ri, next, head, hlist) { if (ri->rp == rp) ri->rp = NULL; } kretprobe_table_unlock(hash, &flags); } kprobe_busy_end(); free_rp_inst(rp); } NOKPROBE_SYMBOL(cleanup_rp_inst); /* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ list_add_rcu(&p->list, &ap->list); if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; return 0; } /* * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { /* Copy p's insn slot to ap */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; INIT_LIST_HEAD(&ap->list); INIT_HLIST_NODE(&ap->hlist); list_add_rcu(&p->list, &ap->list); hlist_replace_rcu(&p->hlist, &ap->hlist); } /* * This is the second or subsequent kprobe at the address - handle * the intricacies */ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) { int ret = 0; struct kprobe *ap = orig_p; cpus_read_lock(); /* For preparing optimization, jump_label_text_reserved() is called */ jump_label_lock(); mutex_lock(&text_mutex); if (!kprobe_aggrprobe(orig_p)) { /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ ap = alloc_aggr_kprobe(orig_p); if (!ap) { ret = -ENOMEM; goto out; } init_aggr_kprobe(ap, orig_p); } else if (kprobe_unused(ap)) { /* This probe is going to die. Rescue it */ ret = reuse_unused_kprobe(ap); if (ret) goto out; } if (kprobe_gone(ap)) { /* * Attempting to insert new probe at the same location that * had a probe in the module vaddr area which already * freed. So, the instruction slot has already been * released. We need a new slot for the new probe. */ ret = arch_prepare_kprobe(ap); if (ret) /* * Even if fail to allocate new slot, don't need to * free aggr_probe. It will be used next time, or * freed by unregister_kprobe. */ goto out; /* Prepare optimized instructions if possible. */ prepare_optimized_kprobe(ap); /* * Clear gone flag to prevent allocating new slot again, and * set disabled flag because it is not armed yet. */ ap->flags = (ap->flags & ~KPROBE_FLAG_GONE) | KPROBE_FLAG_DISABLED; } /* Copy ap's insn slot to p */ copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); out: mutex_unlock(&text_mutex); jump_label_unlock(); cpus_read_unlock(); if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ ret = arm_kprobe(ap); if (ret) { ap->flags |= KPROBE_FLAG_DISABLED; list_del_rcu(&p->list); synchronize_rcu(); } } } return ret; } bool __weak arch_within_kprobe_blacklist(unsigned long addr) { /* The __kprobes marked functions and entry code must not be probed */ return addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end; } static bool __within_kprobe_blacklist(unsigned long addr) { struct kprobe_blacklist_entry *ent; if (arch_within_kprobe_blacklist(addr)) return true; /* * If there exists a kprobe_blacklist, verify and * fail any probe registration in the prohibited area */ list_for_each_entry(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) return true; } return false; } bool within_kprobe_blacklist(unsigned long addr) { char symname[KSYM_NAME_LEN], *p; if (__within_kprobe_blacklist(addr)) return true; /* Check if the address is on a suffixed-symbol */ if (!lookup_symbol_name(addr, symname)) { p = strchr(symname, '.'); if (!p) return false; *p = '\0'; addr = (unsigned long)kprobe_lookup_name(symname, 0); if (addr) return __within_kprobe_blacklist(addr); } return false; } /* * If we have a symbol_name argument, look it up and add the offset field * to it. This way, we can specify a relative address to a symbol. * This returns encoded errors if it fails to look up symbol or invalid * combination of parameters. */ static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name, unsigned int offset) { if ((symbol_name && addr) || (!symbol_name && !addr)) goto invalid; if (symbol_name) { addr = kprobe_lookup_name(symbol_name, offset); if (!addr) return ERR_PTR(-ENOENT); } addr = (kprobe_opcode_t *)(((char *)addr) + offset); if (addr) return addr; invalid: return ERR_PTR(-EINVAL); } static kprobe_opcode_t *kprobe_addr(struct kprobe *p) { return _kprobe_addr(p->addr, p->symbol_name, p->offset); } /* Check passed kprobe is valid and return kprobe in kprobe_table. */ static struct kprobe *__get_valid_kprobe(struct kprobe *p) { struct kprobe *ap, *list_p; lockdep_assert_held(&kprobe_mutex); ap = get_kprobe(p->addr); if (unlikely(!ap)) return NULL; if (p != ap) { list_for_each_entry(list_p, &ap->list, list) if (list_p == p) /* kprobe p is a valid probe */ goto valid; return NULL; } valid: return ap; } /* Return error if the kprobe is being re-registered */ static inline int check_kprobe_rereg(struct kprobe *p) { int ret = 0; mutex_lock(&kprobe_mutex); if (__get_valid_kprobe(p)) ret = -EINVAL; mutex_unlock(&kprobe_mutex); return ret; } int __weak arch_check_ftrace_location(struct kprobe *p) { unsigned long addr = (unsigned long)p->addr; if (ftrace_location(addr) == addr) { #ifdef CONFIG_KPROBES_ON_FTRACE p->flags |= KPROBE_FLAG_FTRACE; #else /* !CONFIG_KPROBES_ON_FTRACE */ return -EINVAL; #endif } return 0; } static bool is_cfi_preamble_symbol(unsigned long addr) { char symbuf[KSYM_NAME_LEN]; if (lookup_symbol_name(addr, symbuf)) return false; return str_has_prefix(symbuf, "__cfi_") || str_has_prefix(symbuf, "__pfx_"); } static int check_kprobe_address_safe(struct kprobe *p, struct module **probed_mod) { int ret; ret = arch_check_ftrace_location(p); if (ret) return ret; jump_label_lock(); preempt_disable(); /* Ensure the address is in a text area, and find a module if exists. */ *probed_mod = NULL; if (!core_kernel_text((unsigned long) p->addr)) { *probed_mod = __module_text_address((unsigned long) p->addr); if (!(*probed_mod)) { ret = -EINVAL; goto out; } } /* Ensure it is not in reserved area. */ if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || find_bug((unsigned long)p->addr) || is_cfi_preamble_symbol((unsigned long)p->addr)) { ret = -EINVAL; goto out; } /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ if (unlikely(!try_module_get(*probed_mod))) { ret = -ENOENT; goto out; } /* * If the module freed .init.text, we couldn't insert * kprobes in there. */ if (within_module_init((unsigned long)p->addr, *probed_mod) && (*probed_mod)->state != MODULE_STATE_COMING) { module_put(*probed_mod); *probed_mod = NULL; ret = -ENOENT; } } out: preempt_enable(); jump_label_unlock(); return ret; } int register_kprobe(struct kprobe *p) { int ret; struct kprobe *old_p; struct module *probed_mod; kprobe_opcode_t *addr; /* Adjust probe address from symbol */ addr = kprobe_addr(p); if (IS_ERR(addr)) return PTR_ERR(addr); p->addr = addr; ret = check_kprobe_rereg(p); if (ret) return ret; /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; p->nmissed = 0; INIT_LIST_HEAD(&p->list); ret = check_kprobe_address_safe(p, &probed_mod); if (ret) return ret; mutex_lock(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { /* Since this may unoptimize old_p, locking text_mutex. */ ret = register_aggr_kprobe(old_p, p); goto out; } cpus_read_lock(); /* Prevent text modification */ mutex_lock(&text_mutex); ret = prepare_kprobe(p); mutex_unlock(&text_mutex); cpus_read_unlock(); if (ret) goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) { ret = arm_kprobe(p); if (ret) { hlist_del_rcu(&p->hlist); synchronize_rcu(); goto out; } } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); out: mutex_unlock(&kprobe_mutex); if (probed_mod) module_put(probed_mod); return ret; } EXPORT_SYMBOL_GPL(register_kprobe); /* Check if all probes on the aggrprobe are disabled */ static int aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; lockdep_assert_held(&kprobe_mutex); list_for_each_entry(kp, &ap->list, list) if (!kprobe_disabled(kp)) /* * There is an active probe on the list. * We can't disable this ap. */ return 0; return 1; } /* Disable one kprobe: Make sure called under kprobe_mutex is locked */ static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ if (p != orig_p) p->flags |= KPROBE_FLAG_DISABLED; /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* * Don't be lazy here. Even if 'kprobes_all_disarmed' * is false, 'orig_p' might not have been armed yet. * Note arm_all_kprobes() __tries__ to arm all kprobes * on the best effort basis. */ if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; return ERR_PTR(ret); } } orig_p->flags |= KPROBE_FLAG_DISABLED; } } return orig_p; } /* * Unregister a kprobe without a scheduler synchronization. */ static int __unregister_kprobe_top(struct kprobe *p) { struct kprobe *ap, *list_p; /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); if (IS_ERR(ap)) return PTR_ERR(ap); if (ap == p) /* * This probe is an independent(and non-optimized) kprobe * (not an aggrprobe). Remove from the hash list. */ goto disarmed; /* Following process expects this probe is an aggrprobe */ WARN_ON(!kprobe_aggrprobe(ap)); if (list_is_singular(&ap->list) && kprobe_disarmed(ap)) /* * !disarmed could be happen if the probe is under delayed * unoptimizing. */ goto disarmed; else { /* If disabling probe has special handlers, update aggrprobe */ if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) goto noclean; } /* * For the kprobe-on-ftrace case, we keep the * post_handler setting to identify this aggrprobe * armed with kprobe_ipmodify_ops. */ if (!kprobe_ftrace(ap)) ap->post_handler = NULL; } noclean: /* * Remove from the aggrprobe: this path will do nothing in * __unregister_kprobe_bottom(). */ list_del_rcu(&p->list); if (!kprobe_disabled(ap) && !kprobes_all_disarmed) /* * Try to optimize this probe again, because post * handler may have been changed. */ optimize_kprobe(ap); } return 0; disarmed: hlist_del_rcu(&ap->hlist); return 0; } static void __unregister_kprobe_bottom(struct kprobe *p) { struct kprobe *ap; if (list_empty(&p->list)) /* This is an independent kprobe */ arch_remove_kprobe(p); else if (list_is_singular(&p->list)) { /* This is the last child of an aggrprobe */ ap = list_entry(p->list.next, struct kprobe, list); list_del(&p->list); free_aggr_kprobe(ap); } /* Otherwise, do nothing. */ } int register_kprobes(struct kprobe **kps, int num) { int i, ret = 0; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { ret = register_kprobe(kps[i]); if (ret < 0) { if (i > 0) unregister_kprobes(kps, i); break; } } return ret; } EXPORT_SYMBOL_GPL(register_kprobes); void unregister_kprobe(struct kprobe *p) { unregister_kprobes(&p, 1); } EXPORT_SYMBOL_GPL(unregister_kprobe); void unregister_kprobes(struct kprobe **kps, int num) { int i; if (num <= 0) return; mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) if (__unregister_kprobe_top(kps[i]) < 0) kps[i]->addr = NULL; mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) if (kps[i]->addr) __unregister_kprobe_bottom(kps[i]); } EXPORT_SYMBOL_GPL(unregister_kprobes); int __weak kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { return NOTIFY_DONE; } NOKPROBE_SYMBOL(kprobe_exceptions_notify); static struct notifier_block kprobe_exceptions_nb = { .notifier_call = kprobe_exceptions_notify, .priority = 0x7fffffff /* we need to be notified first */ }; unsigned long __weak arch_deref_entry_point(void *entry) { return (unsigned long)entry; } #ifdef CONFIG_KRETPROBES unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer) { struct kretprobe_instance *ri = NULL, *last = NULL; struct hlist_head *head; struct hlist_node *tmp; unsigned long flags; kprobe_opcode_t *correct_ret_addr = NULL; bool skipped = false; kretprobe_hash_lock(current, &head, &flags); /* * It is possible to have multiple instances associated with a given * task either because multiple functions in the call path have * return probes installed on them, and/or more than one * return probe was registered for a target function. * * We can handle this because: * - instances are always pushed into the head of the list * - when multiple return probes are registered for the same * function, the (chronologically) first instance's ret_addr * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; /* * Return probes must be pushed on this hash list correct * order (same as return order) so that it can be popped * correctly. However, if we find it is pushed it incorrect * order, this means we find a function which should not be * probed, because the wrong order entry is pushed on the * path of processing other kretprobe itself. */ if (ri->fp != frame_pointer) { if (!skipped) pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); skipped = true; continue; } correct_ret_addr = ri->ret_addr; if (skipped) pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", ri->rp->kp.addr); if (correct_ret_addr != trampoline_address) /* * This is the real return address. Any other * instances associated with this task are for * other calls deeper on the call stack */ break; } BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address)); last = ri; hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; if (ri->fp != frame_pointer) continue; if (ri->rp && ri->rp->handler) { struct kprobe *prev = kprobe_running(); __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); __this_cpu_write(current_kprobe, prev); } recycle_rp_inst(ri); if (ri == last) break; } kretprobe_hash_unlock(current, &flags); return (unsigned long)correct_ret_addr; } NOKPROBE_SYMBOL(__kretprobe_trampoline_handler) /* * This kprobe pre_handler is registered with every kretprobe. When probe * hits it will set up the return probe. */ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { struct kretprobe *rp = container_of(p, struct kretprobe, kp); unsigned long hash, flags = 0; struct kretprobe_instance *ri; /* TODO: consider to only swap the RA after the last pre_handler fired */ hash = hash_ptr(current, KPROBE_HASH_BITS); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. */ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); if (!hlist_empty(&rp->free_instances)) { ri = hlist_entry(rp->free_instances.first, struct kretprobe_instance, hlist); hlist_del(&ri->hlist); raw_spin_unlock_irqrestore(&rp->lock, flags); ri->rp = rp; ri->task = current; if (rp->entry_handler && rp->entry_handler(ri, regs)) { raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock_irqrestore(&rp->lock, flags); return 0; } arch_prepare_kretprobe(ri, regs); /* XXX(hch): why is there no hlist_move_head? */ INIT_HLIST_NODE(&ri->hlist); kretprobe_table_lock(hash, &flags); hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]); kretprobe_table_unlock(hash, &flags); } else { rp->nmissed++; raw_spin_unlock_irqrestore(&rp->lock, flags); } return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); bool __weak arch_kprobe_on_func_entry(unsigned long offset) { return !offset; } /** * kprobe_on_func_entry() -- check whether given address is function entry * @addr: Target address * @sym: Target symbol name * @offset: The offset from the symbol or the address * * This checks whether the given @addr+@offset or @sym+@offset is on the * function entry address or not. * This returns 0 if it is the function entry, or -EINVAL if it is not. * And also it returns -ENOENT if it fails the symbol or address lookup. * Caller must pass @addr or @sym (either one must be NULL), or this * returns -EINVAL. */ int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); if (IS_ERR(kp_addr)) return PTR_ERR(kp_addr); if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset)) return -ENOENT; if (!arch_kprobe_on_func_entry(offset)) return -EINVAL; return 0; } int register_kretprobe(struct kretprobe *rp) { int ret; struct kretprobe_instance *inst; int i; void *addr; ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset); if (ret) return ret; /* If only rp->kp.addr is specified, check reregistering kprobes */ if (rp->kp.addr && check_kprobe_rereg(&rp->kp)) return -EINVAL; if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); if (IS_ERR(addr)) return PTR_ERR(addr); for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { if (kretprobe_blacklist[i].addr == addr) return -EINVAL; } } if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) return -E2BIG; rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; rp->kp.fault_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { #ifdef CONFIG_PREEMPTION rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); #else rp->maxactive = num_possible_cpus(); #endif } raw_spin_lock_init(&rp->lock); INIT_HLIST_HEAD(&rp->free_instances); for (i = 0; i < rp->maxactive; i++) { inst = kmalloc(sizeof(struct kretprobe_instance) + rp->data_size, GFP_KERNEL); if (inst == NULL) { free_rp_inst(rp); return -ENOMEM; } INIT_HLIST_NODE(&inst->hlist); hlist_add_head(&inst->hlist, &rp->free_instances); } rp->nmissed = 0; /* Establish function entry probe point */ ret = register_kprobe(&rp->kp); if (ret != 0) free_rp_inst(rp); return ret; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { int ret = 0, i; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { ret = register_kretprobe(rps[i]); if (ret < 0) { if (i > 0) unregister_kretprobes(rps, i); break; } } return ret; } EXPORT_SYMBOL_GPL(register_kretprobes); void unregister_kretprobe(struct kretprobe *rp) { unregister_kretprobes(&rp, 1); } EXPORT_SYMBOL_GPL(unregister_kretprobe); void unregister_kretprobes(struct kretprobe **rps, int num) { int i; if (num <= 0) return; mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) if (__unregister_kprobe_top(&rps[i]->kp) < 0) rps[i]->kp.addr = NULL; mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) { if (rps[i]->kp.addr) { __unregister_kprobe_bottom(&rps[i]->kp); cleanup_rp_inst(rps[i]); } } } EXPORT_SYMBOL_GPL(unregister_kretprobes); #else /* CONFIG_KRETPROBES */ int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobes); void unregister_kretprobe(struct kretprobe *rp) { } EXPORT_SYMBOL_GPL(unregister_kretprobe); void unregister_kretprobes(struct kretprobe **rps, int num) { } EXPORT_SYMBOL_GPL(unregister_kretprobes); static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); #endif /* CONFIG_KRETPROBES */ /* Set the kprobe gone and remove its instruction buffer. */ static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; lockdep_assert_held(&kprobe_mutex); if (WARN_ON_ONCE(kprobe_gone(p))) return; p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. */ list_for_each_entry(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; kill_optimized_kprobe(p); } /* * Here, we can remove insn_slot safely, because no thread calls * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); /* * The module is going away. We should disarm the kprobe which * is using ftrace, because ftrace framework is still available at * MODULE_STATE_GOING notification. */ if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); } /* Disable one kprobe */ int disable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ p = __disable_kprobe(kp); if (IS_ERR(p)) ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(disable_kprobe); /* Enable one kprobe */ int enable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; mutex_lock(&kprobe_mutex); /* Check whether specified probe is valid. */ p = __get_valid_kprobe(kp); if (unlikely(p == NULL)) { ret = -EINVAL; goto out; } if (kprobe_gone(kp)) { /* This kprobe has gone, we couldn't enable it. */ ret = -EINVAL; goto out; } if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); if (ret) { p->flags |= KPROBE_FLAG_DISABLED; if (p != kp) kp->flags |= KPROBE_FLAG_DISABLED; } } out: mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(enable_kprobe); /* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { pr_err("Dumping kprobe:\n"); pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); int kprobe_add_ksym_blacklist(unsigned long entry) { struct kprobe_blacklist_entry *ent; unsigned long offset = 0, size = 0; if (!kernel_text_address(entry) || !kallsyms_lookup_size_offset(entry, &size, &offset)) return -EINVAL; ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return -ENOMEM; ent->start_addr = entry; ent->end_addr = entry + size; INIT_LIST_HEAD(&ent->list); list_add_tail(&ent->list, &kprobe_blacklist); return (int)size; } /* Add all symbols in given area into kprobe blacklist */ int kprobe_add_area_blacklist(unsigned long start, unsigned long end) { unsigned long entry; int ret = 0; for (entry = start; entry < end; entry += ret) { ret = kprobe_add_ksym_blacklist(entry); if (ret < 0) return ret; if (ret == 0) /* In case of alias symbol */ ret = 1; } return 0; } /* Remove all symbols in given area from kprobe blacklist */ static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) { struct kprobe_blacklist_entry *ent, *n; list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { if (ent->start_addr < start || ent->start_addr >= end) continue; list_del(&ent->list); kfree(ent); } } static void kprobe_remove_ksym_blacklist(unsigned long entry) { kprobe_remove_area_blacklist(entry, entry + 1); } int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { #ifdef __ARCH_WANT_KPROBES_INSN_SLOT if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym)) return 0; #ifdef CONFIG_OPTPROBES if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym)) return 0; #endif #endif if (!arch_kprobe_get_kallsym(&symnum, value, type, sym)) return 0; return -ERANGE; } int __init __weak arch_populate_kprobe_blacklist(void) { return 0; } /* * Lookup and populate the kprobe_blacklist. * * Unlike the kretprobe blacklist, we'll need to determine * the range of addresses that belong to the said functions, * since a kprobe need not necessarily be at the beginning * of a function. */ static int __init populate_kprobe_blacklist(unsigned long *start, unsigned long *end) { unsigned long entry; unsigned long *iter; int ret; for (iter = start; iter < end; iter++) { entry = arch_deref_entry_point((void *)*iter); ret = kprobe_add_ksym_blacklist(entry); if (ret == -EINVAL) continue; if (ret < 0) return ret; } /* Symbols in __kprobes_text are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start, (unsigned long)__kprobes_text_end); if (ret) return ret; /* Symbols in noinstr section are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start, (unsigned long)__noinstr_text_end); return ret ? : arch_populate_kprobe_blacklist(); } static void add_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; int i; if (mod->kprobe_blacklist) { for (i = 0; i < mod->num_kprobe_blacklist; i++) kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]); } start = (unsigned long)mod->kprobes_text_start; if (start) { end = start + mod->kprobes_text_size; kprobe_add_area_blacklist(start, end); } start = (unsigned long)mod->noinstr_text_start; if (start) { end = start + mod->noinstr_text_size; kprobe_add_area_blacklist(start, end); } } static void remove_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; int i; if (mod->kprobe_blacklist) { for (i = 0; i < mod->num_kprobe_blacklist; i++) kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]); } start = (unsigned long)mod->kprobes_text_start; if (start) { end = start + mod->kprobes_text_size; kprobe_remove_area_blacklist(start, end); } start = (unsigned long)mod->noinstr_text_start; if (start) { end = start + mod->noinstr_text_size; kprobe_remove_area_blacklist(start, end); } } /* Module notifier call back, checking kprobes on the module */ static int kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) { struct module *mod = data; struct hlist_head *head; struct kprobe *p; unsigned int i; int checkcore = (val == MODULE_STATE_GOING); if (val == MODULE_STATE_COMING) { mutex_lock(&kprobe_mutex); add_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); } if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; /* * When MODULE_STATE_GOING was notified, both of module .text and * .init.text sections would be freed. When MODULE_STATE_LIVE was * notified, only .init.text section would be freed. We need to * disable kprobes which have been inserted in the sections. */ mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (kprobe_gone(p)) continue; if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { /* * The vaddr this probe is installed will soon * be vfreed buy not synced to disk. Hence, * disarming the breakpoint isn't needed. * * Note, this will also move any optimized probes * that are pending to be removed from their * corresponding lists to the freeing_list and * will not be touched by the delayed * kprobe_optimizer work handler. */ kill_kprobe(p); } } } if (val == MODULE_STATE_GOING) remove_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; } static struct notifier_block kprobe_module_nb = { .notifier_call = kprobes_module_callback, .priority = 0 }; /* Markers of _kprobe_blacklist section */ extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; void kprobe_free_init_mem(void) { void *start = (void *)(&__init_begin); void *end = (void *)(&__init_end); struct hlist_head *head; struct kprobe *p; int i; mutex_lock(&kprobe_mutex); /* Kill all kprobes on initmem */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (start <= (void *)p->addr && (void *)p->addr < end) kill_kprobe(p); } } mutex_unlock(&kprobe_mutex); } static int __init init_kprobes(void) { int i, err = 0; /* FIXME allocate the probe table, currently defined statically */ /* initialize all list heads */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { INIT_HLIST_HEAD(&kprobe_table[i]); INIT_HLIST_HEAD(&kretprobe_inst_table[i]); raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); } err = populate_kprobe_blacklist(__start_kprobe_blacklist, __stop_kprobe_blacklist); if (err) { pr_err("kprobes: failed to populate blacklist: %d\n", err); pr_err("Please take care of using kprobes.\n"); } if (kretprobe_blacklist_size) { /* lookup the function address from its name */ for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { kretprobe_blacklist[i].addr = kprobe_lookup_name(kretprobe_blacklist[i].name, 0); if (!kretprobe_blacklist[i].addr) printk("kretprobe: lookup failed: %s\n", kretprobe_blacklist[i].name); } } /* By default, kprobes are armed */ kprobes_all_disarmed = false; #if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) /* Init kprobe_optinsn_slots for allocation */ kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; #endif err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); if (!err) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); if (!err) init_test_probes(); return err; } early_initcall(init_kprobes); #if defined(CONFIG_OPTPROBES) static int __init init_optprobes(void) { /* * Enable kprobe optimization - this kicks the optimizer which * depends on synchronize_rcu_tasks() and ksoftirqd, that is * not spawned in early initcall. So delay the optimization. */ optimize_all_kprobes(); return 0; } subsys_initcall(init_optprobes); #endif #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; void *addr = p->addr; if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; else kprobe_type = "k"; if (!kallsyms_show_value(pi->file->f_cred)) addr = NULL; if (sym) seq_printf(pi, "%px %s %s+0x%x %s ", addr, kprobe_type, sym, offset, (modname ? modname : " ")); else /* try to use %pS */ seq_printf(pi, "%px %s %pS ", addr, kprobe_type, p->addr); if (!pp) pp = p; seq_printf(pi, "%s%s%s%s\n", (kprobe_gone(p) ? "[GONE]" : ""), ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } static void *kprobe_seq_start(struct seq_file *f, loff_t *pos) { return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL; } static void *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) { (*pos)++; if (*pos >= KPROBE_TABLE_SIZE) return NULL; return pos; } static void kprobe_seq_stop(struct seq_file *f, void *v) { /* Nothing to do */ } static int show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; struct kprobe *p, *kp; const char *sym = NULL; unsigned int i = *(loff_t *) v; unsigned long offset = 0; char *modname, namebuf[KSYM_NAME_LEN]; head = &kprobe_table[i]; preempt_disable(); hlist_for_each_entry_rcu(p, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); if (kprobe_aggrprobe(p)) { list_for_each_entry_rcu(kp, &p->list, list) report_probe(pi, kp, sym, offset, modname, p); } else report_probe(pi, p, sym, offset, modname, NULL); } preempt_enable(); return 0; } static const struct seq_operations kprobes_sops = { .start = kprobe_seq_start, .next = kprobe_seq_next, .stop = kprobe_seq_stop, .show = show_kprobe_addr }; DEFINE_SEQ_ATTRIBUTE(kprobes); /* kprobes/blacklist -- shows which functions can not be probed */ static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos) { mutex_lock(&kprobe_mutex); return seq_list_start(&kprobe_blacklist, *pos); } static void *kprobe_blacklist_seq_next(struct seq_file *m, void *v, loff_t *pos) { return seq_list_next(v, &kprobe_blacklist, pos); } static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) { struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); /* * If /proc/kallsyms is not showing kernel address, we won't * show them here either. */ if (!kallsyms_show_value(m->file->f_cred)) seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, (void *)ent->start_addr); else seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, (void *)ent->end_addr, (void *)ent->start_addr); return 0; } static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v) { mutex_unlock(&kprobe_mutex); } static const struct seq_operations kprobe_blacklist_sops = { .start = kprobe_blacklist_seq_start, .next = kprobe_blacklist_seq_next, .stop = kprobe_blacklist_seq_stop, .show = kprobe_blacklist_seq_show, }; DEFINE_SEQ_ATTRIBUTE(kprobe_blacklist); static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i, total = 0, errors = 0; int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are armed, just return */ if (!kprobes_all_disarmed) goto already_enabled; /* * optimize_kprobe() called by arm_kprobe() checks * kprobes_all_disarmed, so set kprobes_all_disarmed before * arm_kprobe. */ kprobes_all_disarmed = false; /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Arm all kprobes on a best-effort basis */ hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) { err = arm_kprobe(p); if (err) { errors++; ret = err; } total++; } } } if (errors) pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", errors, total); else pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); return ret; } static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i, total = 0, errors = 0; int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); return 0; } kprobes_all_disarmed = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry(p, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { err = disarm_kprobe(p, false); if (err) { errors++; ret = err; } total++; } } } if (errors) pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", errors, total); else pr_info("Kprobes globally disabled\n"); mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); return ret; } /* * XXX: The debugfs bool file interface doesn't allow for callbacks * when the bool state is switched. We can reuse that facility when * available */ static ssize_t read_enabled_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[3]; if (!kprobes_all_disarmed) buf[0] = '1'; else buf[0] = '0'; buf[1] = '\n'; buf[2] = 0x00; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t write_enabled_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { char buf[32]; size_t buf_size; int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; buf[buf_size] = '\0'; switch (buf[0]) { case 'y': case 'Y': case '1': ret = arm_all_kprobes(); break; case 'n': case 'N': case '0': ret = disarm_all_kprobes(); break; default: return -EINVAL; } if (ret) return ret; return count; } static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, .llseek = default_llseek, }; static int __init debugfs_kprobe_init(void) { struct dentry *dir; dir = debugfs_create_dir("kprobes", NULL); debugfs_create_file("list", 0400, dir, NULL, &kprobes_fops); debugfs_create_file("enabled", 0600, dir, NULL, &fops_kp); debugfs_create_file("blacklist", 0400, dir, NULL, &kprobe_blacklist_fops); return 0; } late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 | // SPDX-License-Identifier: GPL-2.0 #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/tracehook.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the * it will interrupt the targeted task and run the task_work. @TWA_RESUME * work is run only when the task exits the kernel and returns to user mode, * or before entering guest mode. Fails if the @task is exiting/exited and thus * it can't process this @work. Otherwise @work->func() will be called when the * @task goes through one of the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; do { head = READ_ONCE(task->task_works); if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (cmpxchg(&task->task_works, head, work) != head); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: set_notify_signal(task); break; default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task->task_works)) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); while ((work = READ_ONCE(*pprev))) { if (!match(work, data)) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } static bool task_work_func_match(struct callback_head *cb, void *data) { return cb->func == data; } /** * task_work_cancel_func - cancel a pending work matching a function added by task_work_add() * @task: the task which should execute the func's work * @func: identifies the func to match with a work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_func(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } static bool task_work_match(struct callback_head *cb, void *data) { return cb == data; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @cb: the callback to remove if queued * * Remove a callback from a task's queue if queued. * * RETURNS: * True if the callback was queued and got cancelled, false otherwise. */ bool task_work_cancel(struct task_struct *task, struct callback_head *cb) { struct callback_head *ret; ret = task_work_cancel_match(task, task_work_match, cb); return ret == cb; } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ do { head = NULL; work = READ_ONCE(task->task_works); if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (cmpxchg(&task->task_works, work, head) != work); if (!work) break; /* * Synchronize with task_work_cancel_match(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H #ifdef __KERNEL__ #include <asm/nops.h> #include <asm/processor-flags.h> #include <linux/irqflags.h> #include <linux/jump_label.h> /* * The compiler should not reorder volatile asm statements with respect to each * other: they should execute in program order. However GCC 4.9.x and 5.x have * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder * volatile asm. The write functions are not affected since they have memory * clobbers preventing reordering. To prevent reads from being reordered with * respect to writes, use a dummy memory operand. */ #define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL) void native_write_cr0(unsigned long val); static inline unsigned long native_read_cr0(void) { unsigned long val; asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline unsigned long native_read_cr2(void) { unsigned long val; asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline void native_write_cr2(unsigned long val) { asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); } static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static inline void native_write_cr3(unsigned long val) { asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); } static inline unsigned long native_read_cr4(void) { unsigned long val; #ifdef CONFIG_X86_32 /* * This could fault if CR4 does not exist. Non-existent CR4 * is functionally equivalent to CR4 == 0. Keep it simple and pretend * that CR4 == 0 on CPUs that don't have CR4. */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val) : "0" (0), __FORCE_ORDER); #else /* CR4 always exists on x86_64. */ asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER); #endif return val; } void native_write_cr4(unsigned long val); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline u32 rdpkru(void) { u32 ecx = 0; u32 edx, pkru; /* * "rdpkru" instruction. Places PKRU contents in to EAX, * clears EDX and requires that ecx=0. */ asm volatile(".byte 0x0f,0x01,0xee\n\t" : "=a" (pkru), "=d" (edx) : "c" (ecx)); return pkru; } static inline void wrpkru(u32 pkru) { u32 ecx = 0, edx = 0; /* * "wrpkru" instruction. Loads contents in EAX to PKRU, * requires that ecx = edx = 0. */ asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (pkru), "c"(ecx), "d"(edx)); } static inline void __write_pkru(u32 pkru) { /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru == rdpkru()) return; wrpkru(pkru); } #else static inline u32 rdpkru(void) { return 0; } static inline void __write_pkru(u32 pkru) { } #endif static inline void native_wbinvd(void) { asm volatile("wbinvd": : :"memory"); } extern asmlinkage void asm_load_gs_index(unsigned int selector); static inline void native_load_gs_index(unsigned int selector) { unsigned long flags; local_irq_save(flags); asm_load_gs_index(selector); local_irq_restore(flags); } static inline unsigned long __read_cr4(void) { return native_read_cr4(); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else static inline unsigned long read_cr0(void) { return native_read_cr0(); } static inline void write_cr0(unsigned long x) { native_write_cr0(x); } static __always_inline unsigned long read_cr2(void) { return native_read_cr2(); } static __always_inline void write_cr2(unsigned long x) { native_write_cr2(x); } /* * Careful! CR3 contains more than just an address. You probably want * read_cr3_pa() instead. */ static inline unsigned long __read_cr3(void) { return __native_read_cr3(); } static inline void write_cr3(unsigned long x) { native_write_cr3(x); } static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } static inline void wbinvd(void) { native_wbinvd(); } #ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int selector) { native_load_gs_index(selector); } #endif #endif /* CONFIG_PARAVIRT_XXL */ static inline void clflush(volatile void *__p) { asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } static inline void clflushopt(volatile void *__p) { alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0", ".byte 0x66; clflush %P0", X86_FEATURE_CLFLUSHOPT, "+m" (*(volatile char __force *)__p)); } static inline void clwb(volatile void *__p) { volatile struct { char x[64]; } *p = __p; asm volatile(ALTERNATIVE_2( ".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])", ".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */ X86_FEATURE_CLFLUSHOPT, ".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */ X86_FEATURE_CLWB) : [p] "+m" (*p) : [pax] "a" (p)); } #define nop() asm volatile ("nop") static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); } /* The dst parameter must be 64-bytes aligned */ static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. * * Both __src and __dst must be memory constraints in order to tell the * compiler that no other memory accesses should be reordered around * this one. * * Also, both must be supplied as lvalues because this tells * the compiler what the object is (its size) the instruction accesses. * I.e., not the pointers but what they point to, thus the deref'ing '*'. */ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" : "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); } /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: 512 bits memory operand * * The ENQCMDS instruction allows software to write a 512-bit command to * a 512-bit-aligned special MMIO region that supports the instruction. * A return status is loaded into the ZF flag in the RFLAGS register. * ZF = 0 equates to success, and ZF = 1 indicates retry or error. * * This function issues the ENQCMDS instruction to submit data from * kernel space to MMIO space, in a unit of 512 bits. Order of data access * is not guaranteed, nor is a memory barrier performed afterwards. It * returns 0 on success and -EAGAIN on failure. * * Warning: Do not use this helper unless your driver has checked that the * ENQCMDS instruction is supported on the platform and the device accepts * ENQCMDS. */ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; bool zf; /* * ENQCMDS %(rdx), rax * * See movdir64b()'s comment on operand specification. */ asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" CC_SET(z) : CC_OUT(z) (zf), "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); /* Submission failure is indicated via EFLAGS.ZF=1 */ if (zf) return -EAGAIN; return 0; } #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPU's in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/atomic.h> #include <linux/bug.h> /* Don't assign or return these: may not be this big! */ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; /** * cpumask_bits - get the bits in a cpumask * @maskp: the struct cpumask * * * You should only assume nr_cpu_ids bits of this mask are valid. This is * a macro so it's const-correct. */ #define cpumask_bits(maskp) ((maskp)->bits) /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if NR_CPUS == 1 #define nr_cpu_ids 1U #else extern unsigned int nr_cpu_ids; #endif #ifdef CONFIG_CPUMASK_OFFSTACK /* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, * not all bits may be allocated. */ #define nr_cpumask_bits nr_cpu_ids #else #define nr_cpumask_bits ((unsigned int)NR_CPUS) #endif /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU id's * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_possible_mask is forced to have * all NR_CPUS bits set, otherwise it is just the set of CPUs that * ACPI reports present at boot. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP arch's (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) extern atomic_t __num_online_cpus; #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. */ static inline unsigned int num_online_cpus(void) { return atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) #define cpu_online(cpu) cpumask_test_cpu((cpu), cpu_online_mask) #define cpu_possible(cpu) cpumask_test_cpu((cpu), cpu_possible_mask) #define cpu_present(cpu) cpumask_test_cpu((cpu), cpu_present_mask) #define cpu_active(cpu) cpumask_test_cpu((cpu), cpu_active_mask) #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U #define cpu_online(cpu) ((cpu) == 0) #define cpu_possible(cpu) ((cpu) == 0) #define cpu_present(cpu) ((cpu) == 0) #define cpu_active(cpu) ((cpu) == 0) #endif extern cpumask_t cpus_booted_once_mask; static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; } #if NR_CPUS == 1 /* Uniprocessor. Assume all masks are "1". */ static inline unsigned int cpumask_first(const struct cpumask *srcp) { return 0; } static inline unsigned int cpumask_last(const struct cpumask *srcp) { return 0; } /* Valid inputs for n are -1 and 0. */ static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { return n+1; } static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { return n+1; } static inline unsigned int cpumask_next_and(int n, const struct cpumask *srcp, const struct cpumask *andp) { return n+1; } static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { /* cpu0 unless stop condition, wrap and at cpu0, then nr_cpumask_bits */ return (wrap && n == 0); } /* cpu must be a valid cpu, ie 0, so there's no other choice. */ static inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { return 1; } static inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static inline int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_next_and(-1, src1p, src2p); } #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_wrap(cpu, mask, start) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start)) #define for_each_cpu_and(cpu, mask1, mask2) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2) #else /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no cpus set. */ static inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Returns >= nr_cpumask_bits if no CPUs set. */ static inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits); } unsigned int cpumask_next(int n, const struct cpumask *srcp); /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus unset. */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); unsigned int cpumask_local_spread(unsigned int i, int node); int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for ((cpu) = -1; \ (cpu) = cpumask_next((cpu), (mask)), \ (cpu) < nr_cpu_ids;) /** * for_each_cpu_not - iterate over every cpu in a complemented mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_not(cpu, mask) \ for ((cpu) = -1; \ (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask poiter * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ (cpu) < nr_cpumask_bits; \ (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for ((cpu) = -1; \ (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ (cpu) < nr_cpu_ids;) #endif /* SMP */ #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in @cpumask, else returns 0 */ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 * * test_and_set_bit wrapper for cpumasks. */ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 * * test_and_clear_bit wrapper for cpumasks. */ static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static inline void cpumask_setall(struct cpumask *dstp) { bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * If *@dstp is empty, returns 0, else returns 1 */ static inline int cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * If *@dstp is empty, returns 0, else returns 1 */ static inline int cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_complement - *dstp = ~*srcp * @dstp: the cpumask result * @srcp: the input to invert */ static inline void cpumask_complement(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_complement(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input */ static inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input */ static inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), nr_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input */ static inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Returns 1 if *@src1p is a subset of *@src2p, else returns 0 */ static inline int cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. */ static inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. */ static inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. */ static inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_any - pick a "random" cpu from *srcp * @srcp: the input cpumask * * Returns >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @src1p: the first input * @src2p: the second input * * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ #define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) /** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Returns >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - size to allocate for a 'struct cpumask' in bytes */ static inline unsigned int cpumask_size(void) { return bitmap_size(nr_cpumask_bits); } /* * cpumask_var_t: struct cpumask for stack usage. * * Oh, the wicked games we play! In order to make kernel coding a * little more difficult, we typedef cpumask_var_t to an array or a * pointer: doing &mask on an array is a noop, so it still works. * * ie. * cpumask_var_t tmpmask; * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) * return -ENOMEM; * * ... use 'tmpmask' like a normal struct cpumask * ... * * free_cpumask_var(tmpmask); * * * However, one notable exception is there. alloc_cpumask_var() allocates * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. * * cpumask_var_t tmpmask; * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) * return -ENOMEM; * * var = *tmpmask; * * This code makes NR_CPUS length memcopy and brings to a memory corruption. * cpumask_copy() provide safe copy functionality. * * Note that there is another evil here: If you define a cpumask_var_t * as a percpu variable then the way to obtain the address of the cpumask * structure differently influences what this_cpu_* operation needs to be * used. Please use this_cpu_cpumask_var_t in those cases. The direct use * of this_cpu_ptr() or this_cpu_read() will lead to failures when the * other type of cpumask_var_t implementation is configured. * * Please also note that __cpumask_var_read_mostly can be used to declare * a cpumask_var_t variable itself (not its content) as read mostly. */ #ifdef CONFIG_CPUMASK_OFFSTACK typedef struct cpumask *cpumask_var_t; #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static inline void free_cpumask_var(cpumask_var_t mask) { } static inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); static inline void reset_cpu_possible_mask(void) { bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); } static inline void set_cpu_possible(unsigned int cpu, bool possible) { if (possible) cpumask_set_cpu(cpu, &__cpu_possible_mask); else cpumask_clear_cpu(cpu, &__cpu_possible_mask); } static inline void set_cpu_present(unsigned int cpu, bool present) { if (present) cpumask_set_cpu(cpu, &__cpu_present_mask); else cpumask_clear_cpu(cpu, &__cpu_present_mask); } void set_cpu_online(unsigned int cpu, bool online); static inline void set_cpu_active(unsigned int cpu, bool active) { if (active) cpumask_set_cpu(cpu, &__cpu_active_mask); else cpumask_clear_cpu(cpu, &__cpu_active_mask); } /** * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Returns the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } #endif /* __LINUX_CPUMASK_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; int pid_max = PID_MAX_DEFAULT; #define RESERVED_PIDS 300 int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .kref = KREF_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); /* * Note: disable interrupts while the pidmap_lock is held as an * interrupt might come in and do read_lock(&tasklist_lock). * * If we don't disable interrupts there is a nasty deadlock between * detach_pid()->free_pid() and another cpu that does * spin_lock(&pidmap_lock) followed by an interrupt routine that does * read_lock(&tasklist_lock); * * After we clean up the tasklist_lock and know there are no * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { /* We can be called with write_lock_irq(&tasklist_lock) held */ int i; unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock_irq(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); put_pid_ns(ns); out_free: spin_lock_irq(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock_irq(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock_irq(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock_irq(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr = task_pid_ptr(task, type); struct pid *pid; int tmp; pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; free_pid(pid); } void detach_pid(struct task_struct *task, enum pid_type type) { __change_pid(task, type, NULL); } void change_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { if (type == PIDTYPE_PID) new->thread_pid = old->thread_pid; hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { struct fd f; struct pid *pid; f = fdget(fd); if (!f.file) return ERR_PTR(-EBADF); pid = pidfd_pid(f.file); if (!IS_ERR(pid)) { get_pid(pid); *flags = f.file->f_flags; } fdput(f); return pid; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ int pidfd_create(struct pid *pid, unsigned int flags) { int fd; if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) return -EINVAL; if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) return -EINVAL; fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), flags | O_RDWR | O_CLOEXEC); if (fd < 0) put_pid(pid); return fd; } /** * pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the process identified by @pid. Currently, the process identified by * @pid must be a thread-group leader. This restriction currently exists * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot * be used with CLONE_THREAD) and pidfd polling (only supports thread group * leaders). * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~PIDFD_NONBLOCK) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); return file ?: ERR_PTR(-EBADF); } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; struct fd f; int ret; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; f = fdget(pidfd); if (!f.file) return -EBADF; pid = pidfd_pid(f.file); if (IS_ERR(pid)) ret = PTR_ERR(pid); else ret = pidfd_getfd(pid, fd); fdput(f); return ret; } |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sock_diag.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/gfp.h> #include <net/inet_common.h> #include <net/ip.h> #include <net/protocol.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/skmsg.h> #include <net/sock.h> #include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/unaligned.h> #include <asm/cmpxchg.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> #include <linux/btf.h> #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> #include <net/dst.h> #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/udp.h> #include <linux/bpf_trace.h> #include <net/xdp_sock.h> #include <linux/inetdevice.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <linux/seg6_local.h> #include <net/seg6.h> #include <net/seg6_local.h> #include <net/lwtunnel.h> #include <net/ipv6_stubs.h> #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> #include <net/tls.h> /* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */ static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check"); static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { if (in_compat_syscall()) { struct compat_sock_fprog f32; if (len != sizeof(f32)) return -EINVAL; if (copy_from_sockptr(&f32, src, sizeof(f32))) return -EFAULT; memset(dst, 0, sizeof(*dst)); dst->len = f32.len; dst->filter = compat_ptr(f32.filter); } else { if (len != sizeof(*dst)) return -EINVAL; if (copy_from_sockptr(dst, src, sizeof(*dst))) return -EFAULT; } return 0; } EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); /** * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level * wrapper to BPF_PROG_RUN. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); return -ENOMEM; } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) return err; err = security_sock_rcv_skb(sk, skb); if (err) return err; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { struct sock *save_sk = skb->sk; unsigned int pkt_len; skb->sk = sk; pkt_len = bpf_prog_run_save_cb(filter->prog, skb); skb->sk = save_sk; err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(sk_filter_trim_cap); BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *) &skb->data[a]; if (nla->nla_len > skb->len - a) return 0; nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset) { if (likely(offset >= 0)) return offset; if (offset >= SKF_NET_OFF) return offset - SKF_NET_OFF + skb_network_offset(skb); if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb)) return offset - SKF_LL_OFF + skb_mac_offset(skb); return INT_MIN; } BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { u8 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return *(u8 *)(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return tmp; else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be16 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be16(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be16_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be32 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be32(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be32_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, offset); } static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; switch (skb_field) { case SKF_AD_MARK: BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); break; case SKF_AD_PKTTYPE: *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET()); *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); #endif break; case SKF_AD_QUEUE: BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET()); if (PKT_VLAN_PRESENT_BIT) *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT); if (PKT_VLAN_PRESENT_BIT < 7) *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1); break; } return insn - insn_buf; } static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PKTTYPE: cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); *insn++ = BPF_EXIT_INSN(); if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, ifindex)); else *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, type)); break; case SKF_AD_OFF + SKF_AD_MARK: cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); break; case SKF_AD_OFF + SKF_AD_QUEUE: cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: cnt = convert_skb_access(SKF_AD_VLAN_TAG, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, vlan_proto)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = CTX */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); bpf_user_rnd_init_once(); break; } break; case SKF_AD_OFF + SKF_AD_ALU_XOR_X: /* A ^= X */ *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break; default: /* This is just a dummy call to avoid letting the compiler * evict __bpf_call_base() as an optimization. Placed here * where no-one bothers. */ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); return false; } *insnp = insn; return true; } static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) { const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); bool endian = BPF_SIZE(fp->code) == BPF_H || BPF_SIZE(fp->code) == BPF_W; bool indirect = BPF_MODE(fp->code) == BPF_IND; const int ip_align = NET_IP_ALIGN; struct bpf_insn *insn = *insnp; int offset = fp->k; if (!indirect && ((unaligned_ok && offset >= 0) || (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { bool ldx_off_ok = offset <= S16_MAX; *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); if (offset) *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian + (!ldx_off_ok * 2)); if (ldx_off_ok) { *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_TMP, 0); } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); } *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); if (fp->k) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); } switch (BPF_SIZE(fp->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); break; default: return false; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn = BPF_EXIT_INSN(); *insnp = insn; return true; } /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_prog *new_prog, int *new_len, bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); if (len <= 0 || len > BPF_MAXINSNS) return -EINVAL; if (new_prog) { first_insn = new_prog->insnsi; addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } do_pass: new_insn = first_insn; fp = prog; /* Classic BPF related prologue emission. */ if (new_prog) { /* Classic BPF expects A and X to be reset first. These need * to be guaranteed to be the first two instructions. */ *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X); /* All programs must keep CTX in callee saved BPF_REG_CTX. * In eBPF case it's done by the compiler, here we need to * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); if (*seen_ld_abs) { /* For packet access in classic BPF, cache skb->data * in callee-saved BPF R8 and skb->len - skb->data_len * (headlen) in BPF R9. Since classic BPF is read-only * on CTX, we only need to cache it once. */ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), BPF_REG_D, BPF_REG_CTX, offsetof(struct sk_buff, data)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, offsetof(struct sk_buff, len)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, data_len)); *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - first_insn; switch (fp->code) { /* All arithmetic insns and skb loads map as-is. */ case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: /* Check for overloaded BPF extension and * directly convert it if found, otherwise * just move on with mapping. */ if (BPF_CLASS(fp->code) == BPF_LD && BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; if (BPF_CLASS(fp->code) == BPF_LD && convert_bpf_ld_abs(fp, &insn)) { *seen_ld_abs = true; break; } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); /* Error with exception code on div/mod by 0. * For cBPF programs, this was always return 0. */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn++ = BPF_EXIT_INSN(); } *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; /* Jump transformation cannot use BPF block macros * everywhere as offset calculation and target updates * require a bit more work than the rest, i.e. jump * opcodes map as-is, but offsets need adjustment. */ #define BPF_EMIT_JMP \ do { \ const s32 off_min = S16_MIN, off_max = S16_MAX; \ s32 off; \ \ if (target >= len || target < 0) \ goto err; \ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ /* Adjust pc relative offset for 2nd or 3rd insn. */ \ off -= insn - tmp_insns; \ /* Reject anything not fitting into insn->off. */ \ if (off < off_min || off > off_max) \ goto err; \ insn->off = off; \ } while (0) case BPF_JMP | BPF_JA: target = i + fp->k + 1; insn->code = fp->code; BPF_EMIT_JMP; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { /* BPF immediates are signed, zero extend * immediate into tmp register and use it * in compare insn. */ *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); insn->dst_reg = BPF_REG_A; insn->src_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; BPF_EMIT_JMP; break; } /* Convert some jumps when 'jump_true' is next insn. */ if (fp->jt == 0) { switch (BPF_OP(fp->code)) { case BPF_JEQ: insn->code = BPF_JMP | BPF_JNE | bpf_src; break; case BPF_JGT: insn->code = BPF_JMP | BPF_JLE | bpf_src; break; case BPF_JGE: insn->code = BPF_JMP | BPF_JLT | bpf_src; break; default: goto jmp_rest; } target = i + fp->jf + 1; BPF_EMIT_JMP; break; } jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; BPF_EMIT_JMP; insn++; insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; BPF_EMIT_JMP; break; /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: { struct sock_filter tmp = { .code = BPF_LD | BPF_ABS | BPF_B, .k = fp->k, }; *seen_ld_abs = true; /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ convert_bpf_ld_abs(&tmp, &insn); insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); /* tmp = X */ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; } /* RET_K is remaped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: if (BPF_RVAL(fp->code) == BPF_K) *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0, 0, fp->k); *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: stack_off = fp->k * 4 + 4; *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == BPF_ST ? BPF_REG_A : BPF_REG_X, -stack_off); /* check_load_and_stores() verifies that classic BPF can * load from stack only after write, so tracking * stack_depth for ST|STX insns is enough */ if (new_prog && new_prog->aux->stack_depth < stack_off) new_prog->aux->stack_depth = stack_off; break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: stack_off = fp->k * 4 + 4; *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_FP, -stack_off); break; /* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, fp->k); break; /* X = A */ case BPF_MISC | BPF_TAX: *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_CTX, offsetof(struct sk_buff, len)); break; /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: /* A = *(u32 *) (ctx + K) */ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; /* Unknown instruction. */ default: goto err; } insn++; if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); new_insn += insn - tmp_insns; } if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; if (*seen_ld_abs) *new_len += 4; /* Prologue bits. */ return 0; } pass++; if (new_flen != new_insn - first_insn) { new_flen = new_insn - first_insn; if (pass > 2) goto err; goto do_pass; } kfree(addrs); BUG_ON(*new_len != new_flen); return 0; err: kfree(addrs); return -EINVAL; } /* Security: * * As we dont want to clear mem[] array for each packet going through * __bpf_prog_run(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { case BPF_ST: case BPF_STX: memvalid |= (1 << filter[pc].k); break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; case BPF_JMP | BPF_JA: /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; break; } } error: kfree(masks); return ret; } static bool chk_code_allowed(u16 code_to_probe) { static const bool codes[] = { /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_K] = true, [BPF_ALU | BPF_ADD | BPF_X] = true, [BPF_ALU | BPF_SUB | BPF_K] = true, [BPF_ALU | BPF_SUB | BPF_X] = true, [BPF_ALU | BPF_MUL | BPF_K] = true, [BPF_ALU | BPF_MUL | BPF_X] = true, [BPF_ALU | BPF_DIV | BPF_K] = true, [BPF_ALU | BPF_DIV | BPF_X] = true, [BPF_ALU | BPF_MOD | BPF_K] = true, [BPF_ALU | BPF_MOD | BPF_X] = true, [BPF_ALU | BPF_AND | BPF_K] = true, [BPF_ALU | BPF_AND | BPF_X] = true, [BPF_ALU | BPF_OR | BPF_K] = true, [BPF_ALU | BPF_OR | BPF_X] = true, [BPF_ALU | BPF_XOR | BPF_K] = true, [BPF_ALU | BPF_XOR | BPF_X] = true, [BPF_ALU | BPF_LSH | BPF_K] = true, [BPF_ALU | BPF_LSH | BPF_X] = true, [BPF_ALU | BPF_RSH | BPF_K] = true, [BPF_ALU | BPF_RSH | BPF_X] = true, [BPF_ALU | BPF_NEG] = true, /* Load instructions */ [BPF_LD | BPF_W | BPF_ABS] = true, [BPF_LD | BPF_H | BPF_ABS] = true, [BPF_LD | BPF_B | BPF_ABS] = true, [BPF_LD | BPF_W | BPF_LEN] = true, [BPF_LD | BPF_W | BPF_IND] = true, [BPF_LD | BPF_H | BPF_IND] = true, [BPF_LD | BPF_B | BPF_IND] = true, [BPF_LD | BPF_IMM] = true, [BPF_LD | BPF_MEM] = true, [BPF_LDX | BPF_W | BPF_LEN] = true, [BPF_LDX | BPF_B | BPF_MSH] = true, [BPF_LDX | BPF_IMM] = true, [BPF_LDX | BPF_MEM] = true, /* Store instructions */ [BPF_ST] = true, [BPF_STX] = true, /* Misc instructions */ [BPF_MISC | BPF_TAX] = true, [BPF_MISC | BPF_TXA] = true, /* Return instructions */ [BPF_RET | BPF_K] = true, [BPF_RET | BPF_A] = true, /* Jump instructions */ [BPF_JMP | BPF_JA] = true, [BPF_JMP | BPF_JEQ | BPF_K] = true, [BPF_JMP | BPF_JEQ | BPF_X] = true, [BPF_JMP | BPF_JGE | BPF_K] = true, [BPF_JMP | BPF_JGE | BPF_X] = true, [BPF_JMP | BPF_JGT | BPF_K] = true, [BPF_JMP | BPF_JGT | BPF_X] = true, [BPF_JMP | BPF_JSET | BPF_K] = true, [BPF_JMP | BPF_JSET | BPF_X] = true, }; if (code_to_probe >= ARRAY_SIZE(codes)) return false; return codes[code_to_probe]; } static bool bpf_check_basics_ok(const struct sock_filter *filter, unsigned int flen) { if (filter == NULL) return false; if (flen == 0 || flen > BPF_MAXINSNS) return false; return true; } /** * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * * Check the user's filter code. If we let some ugly * filter code slip through kaboom! The filter must contain * no references or jumps that are out of range, no illegal * instructions, and must end with a RET instruction. * * All jumps are forward as they are not signed. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) return -EINVAL; /* Some instructions need special checks */ switch (ftest->code) { case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: if (ftest->k >= 32) return -EINVAL; break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; case BPF_JMP | BPF_JA: /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: anc_found = false; if (bpf_anc_helper(ftest) & BPF_ANC) anc_found = true; /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } } /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { case BPF_RET | BPF_K: case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } return -EINVAL; } static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); if (!fp->orig_prog) return -ENOMEM; fkprog = fp->orig_prog; fkprog->len = fprog->len; fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; } return 0; } static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; if (fprog) { kfree(fprog->filter); kfree(fprog); } } static void __bpf_prog_release(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); bpf_prog_free(prog); } } static void __sk_filter_release(struct sk_filter *fp) { __bpf_prog_release(fp->prog); kfree(fp); } /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); __sk_filter_release(fp); } /** * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. */ static void sk_filter_release(struct sk_filter *fp) { if (refcount_dec_and_test(&fp->refcnt)) call_rcu(&fp->rcu, sk_filter_release_rcu); } void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); atomic_sub(filter_size, &sk->sk_omem_alloc); sk_filter_release(fp); } /* try to charge the socket memory if there is space available * return true on success */ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); int optmem_max = READ_ONCE(sysctl_optmem_max); /* same check as in sock_kmalloc() */ if (filter_size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } return false; } bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { if (!refcount_inc_not_zero(&fp->refcnt)) return false; if (!__sk_filter_charge(sk, fp)) { sk_filter_release(fp); return false; } return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it * won't be used at this point in time anymore internally * after the migration to the internal BPF instruction * representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; } /* 1st pass: calculate the new program length. */ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. */ fp = old_fp; err = -ENOMEM; goto out_err_free; } fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ err = bpf_convert_filter(old_prog, old_len, fp, &new_len, &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released * by krealloc(). */ goto out_err_free; fp = bpf_prog_select_runtime(fp, &err); if (err) goto out_err_free; kfree(old_prog); return fp; out_err_free: kfree(old_prog); out_err: __bpf_prog_release(fp); return ERR_PTR(err); } static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, bpf_aux_classic_check_t trans) { int err; fp->bpf_func = NULL; fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } /* There might be additional checks and transformations * needed on classic filters, f.e. in case of seccomp. */ if (trans) { err = trans(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } } /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ bpf_jit_compile(fp); /* JIT compiler couldn't process this filter, so do the * internal BPF translation for the optimized interpreter. */ if (!fp->jited) fp = bpf_migrate_filter(fp); return fp; } /** * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold * a copy here, and can spare us the work. */ fp->orig_prog = NULL; /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create); /** * bpf_prog_create_from_user - create an unattached filter from user buffer * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; int err; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { __bpf_prog_free(fp); return -EFAULT; } fp->len = fprog->len; fp->orig_prog = NULL; if (save_orig) { err = bpf_prog_store_orig_filter(fp, fprog); if (err) { __bpf_prog_free(fp); return -ENOMEM; } } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, trans); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create_from_user); void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); } EXPORT_SYMBOL_GPL(bpf_prog_destroy); static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) { struct sk_filter *fp, *old_fp; fp = kmalloc(sizeof(*fp), GFP_KERNEL); if (!fp) return -ENOMEM; fp->prog = prog; if (!__sk_filter_charge(sk, fp)) { kfree(fp); return -ENOMEM; } refcount_set(&fp->refcnt, 1); old_fp = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) sk_filter_uncharge(sk, old_fp); return 0; } static struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return ERR_PTR(-EINVAL); prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!prog) return ERR_PTR(-ENOMEM); if (copy_from_user(prog->insns, fprog->filter, fsize)) { __bpf_prog_free(prog); return ERR_PTR(-EFAULT); } prog->len = fprog->len; err = bpf_prog_store_orig_filter(prog, fprog); if (err) { __bpf_prog_free(prog); return ERR_PTR(-ENOMEM); } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ return bpf_prepare_filter(prog, NULL); } /** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use * * Attach the user's filter code. We first run some sanity checks on * it to make sure it does not explode on us later. If an error * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { __bpf_prog_release(prog); return err; } return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); if (err) __bpf_prog_release(prog); return err; } static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) { if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); } int sk_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog = __get_bpf(ufd, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { bpf_prog_put(prog); return err; } return 0; } int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) { /* Like other non BPF_PROG_TYPE_SOCKET_FILTER * bpf prog (e.g. sockmap). It depends on the * limitation imposed by bpf_prog_load(). * Hence, sysctl_optmem_max is not checked. */ if ((sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_DGRAM) || (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_TCP) || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { err = -ENOTSUPP; goto err_prog_put; } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) { err = -ENOMEM; goto err_prog_put; } } err = reuseport_attach_prog(sk, prog); err_prog_put: if (err) bpf_prog_put(prog); return err; } void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) bpf_prog_put(prog); else bpf_prog_destroy(prog); } struct bpf_scratchpad { union { __be32 diff[MAX_BPF_STACK / sizeof(__be32)]; u8 buff[MAX_BPF_STACK]; }; }; static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_ensure_writable(skb, write_len); } static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { int err = __bpf_try_make_writable(skb, write_len); bpf_compute_data_pointers(skb); return err; } static int bpf_try_make_head_writable(struct sk_buff *skb) { return bpf_try_make_writable(skb, skb_headlen(skb)); } static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); } static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len, u64, flags) { void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_4(bpf_flow_dissector_load_bytes, const struct bpf_flow_dissector *, ctx, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > 0xffff)) goto err_clear; if (unlikely(!ctx->skb)) goto err_clear; ptr = skb_header_pointer(ctx->skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { .func = bpf_flow_dissector_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); u8 *start, *ptr; if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: if (unlikely(!skb_mac_header_was_set(skb))) goto err_clear; start = skb_mac_header(skb); break; case BPF_HDR_START_NET: start = skb_network_header(skb); break; default: goto err_clear; } ptr = start + offset; if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { .func = bpf_skb_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto bpf_skb_pull_data_proto = { .func = bpf_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) { return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; } static const struct bpf_func_proto bpf_sk_fullsock_proto = { .func = bpf_sk_fullsock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { int err = __bpf_try_make_writable(skb, write_len); bpf_compute_data_end_sk_skb(skb); return err; } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto sk_skb_pull_data_proto = { .func = sk_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; csum_replace_by_diff(ptr, to); break; case 2: csum_replace2(ptr, from, to); break; case 4: csum_replace4(ptr, from, to); break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; case 4: inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo); break; default: return -EINVAL; } if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; return 0; } static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, __be32 *, to, u32, to_size, __wsum, seed) { struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); u32 diff_size = from_size + to_size; int i, j = 0; /* This is quite flexible, some examples: * * from_size == 0, to_size > 0, seed := csum --> pushing data * from_size > 0, to_size == 0, seed := csum --> pulling data * from_size > 0, to_size > 0, seed := 0 --> diffing data * * Even for diffing, from_size and to_size don't need to be equal. */ if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) || diff_size > sizeof(sp->diff))) return -EINVAL; for (i = 0; i < from_size / sizeof(__be32); i++, j++) sp->diff[j] = ~from[i]; for (i = 0; i < to_size / sizeof(__be32); i++, j++) sp->diff[j] = to[i]; return csum_partial(sp->diff, diff_size, seed); } static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM_OR_NULL, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_MEM_OR_NULL, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) { /* The interface is to be used in combination with bpf_csum_diff() * for direct packet writes. csum rotation for alignment as well * as emulating csum_sub() can be done from the eBPF program. */ if (skb->ip_summed == CHECKSUM_COMPLETE) return (skb->csum = csum_add(skb->csum, csum)); return -ENOTSUPP; } static const struct bpf_func_proto bpf_csum_update_proto = { .func = bpf_csum_update, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level) { /* The interface is to be used in combination with bpf_skb_adjust_room() * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET * is passed as flags, for example. */ switch (level) { case BPF_CSUM_LEVEL_INC: __skb_incr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_DEC: __skb_decr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_RESET: __skb_reset_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_QUERY: return skb->ip_summed == CHECKSUM_UNNECESSARY ? skb->csum_level : -EACCES; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_csum_level_proto = { .func = bpf_csum_level, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb(dev, skb); } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { int ret = ____dev_forward_skb(dev, skb); if (likely(!ret)) { skb->dev = dev; ret = netif_rx(skb); } return ret; } static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; } skb->dev = dev; skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); dev_xmit_recursion_dec(); return ret; } static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { unsigned int mlen = skb_network_offset(skb); if (unlikely(skb->len <= mlen)) { kfree_skb(skb); return -ERANGE; } if (mlen) { __skb_pull(skb, mlen); if (unlikely(!skb->len)) { kfree_skb(skb); return -ERANGE; } /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that * the skb is originated from ingress (i.e. a forwarded skb) * to ensure that rcsum starts at net header. */ if (!skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } bpf_push_mac_rcsum(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, u32 flags) { if (dev_is_mac_header_xmit(dev)) return __bpf_redirect_common(skb, dev, flags); else return __bpf_redirect_no_mac(skb, dev, flags); } #if IS_ENABLED(CONFIG_IPV6) static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *nexthop; struct dst_entry *dst = NULL; struct neighbour *neigh; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb->tstamp = 0; if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { struct sk_buff *skb2; skb2 = skb_realloc_headroom(skb, hh_len); if (unlikely(!skb2)) { kfree_skb(skb); return -ENOMEM; } if (skb->sk) skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; } rcu_read_lock_bh(); if (!nh) { dst = skb_dst(skb); nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst), &ipv6_hdr(skb)->daddr); } else { nexthop = &nh->ipv6_nh; } neigh = ip_neigh_gw6(dev, nexthop); if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, false); dev_xmit_recursion_dec(); rcu_read_unlock_bh(); return ret; } rcu_read_unlock_bh(); if (dst) IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_flags = FLOWI_FLAG_ANYSRC, .flowi6_mark = skb->mark, .flowlabel = ip6_flowinfo(ip6h), .flowi6_oif = dev->ifindex, .flowi6_proto = ip6h->nexthdr, .daddr = ip6h->daddr, .saddr = ip6h->saddr, }; dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) goto out_drop; skb_dst_drop(skb); skb_dst_set(skb, dst); } else if (nh->nh_family != AF_INET6) { goto out_drop; } err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: dev->stats.tx_errors++; kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_IPV6 */ #if IS_ENABLED(CONFIG_INET) static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb->tstamp = 0; if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { struct sk_buff *skb2; skb2 = skb_realloc_headroom(skb, hh_len); if (unlikely(!skb2)) { kfree_skb(skb); return -ENOMEM; } if (skb->sk) skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; } rcu_read_lock_bh(); if (!nh) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = container_of(dst, struct rtable, dst); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { neigh = ip_neigh_gw4(dev, nh->ipv4_nh); } else { rcu_read_unlock_bh(); goto out_drop; } if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, is_v6gw); dev_xmit_recursion_dec(); rcu_read_unlock_bh(); return ret; } rcu_read_unlock_bh(); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct iphdr *ip4h = ip_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct flowi4 fl4 = { .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .flowi4_tos = RT_TOS(ip4h->tos), .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, .saddr = ip4h->saddr, }; struct rtable *rt; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out_drop; if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto out_drop; } skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: dev->stats.tx_errors++; kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_INET */ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { struct ethhdr *ethh = eth_hdr(skb); if (unlikely(skb->mac_header >= skb->network_header)) goto out; bpf_push_mac_rcsum(skb); if (is_multicast_ether_addr(ethh->h_dest)) goto out; skb_pull(skb, sizeof(*ethh)); skb_unset_mac_header(skb); skb_reset_network_header(skb); if (skb->protocol == htons(ETH_P_IP)) return __bpf_redirect_neigh_v4(skb, dev, nh); else if (skb->protocol == htons(ETH_P_IPV6)) return __bpf_redirect_neigh_v6(skb, dev, nh); out: kfree_skb(skb); return -ENOTSUPP; } /* Internal, non-exposed redirect flags. */ enum { BPF_F_NEIGH = (1ULL << 1), BPF_F_PEER = (1ULL << 2), BPF_F_NEXTHOP = (1ULL << 3), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; /* BPF test infra's convert___skb_to_skb() can create type-less * GSO packets. gso_features_check() will detect this as a bad * offload. However, lets not leak them out in the first place. */ if (unlikely(skb_is_gso(skb) && !skb_shinfo(skb)->gso_type)) return -EBADMSG; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; clone = skb_clone(skb, GFP_ATOMIC); if (unlikely(!clone)) return -ENOMEM; /* For direct write, we need to keep the invariant that the skbs * we're dealing with need to be uncloned. Should uncloning fail * here, we need to free the just generated clone to unclone once * again. */ ret = bpf_try_make_head_writable(skb); if (unlikely(ret)) { kfree_skb(clone); return -ENOMEM; } return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; dev = dev_get_by_index_rcu(net, ri->tgt_index); ri->tgt_index = 0; ri->flags = 0; if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { const struct net_device_ops *ops = dev->netdev_ops; if (unlikely(!ops->ndo_get_peer_dev || !skb_at_tc_ingress(skb))) goto out_drop; dev = ops->ndo_get_peer_dev(dev); if (unlikely(!dev || !is_skb_forwardable(dev, skb) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; return -EAGAIN; } return flags & BPF_F_NEIGH ? __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ? &ri->nh : NULL) : __bpf_redirect(skb, dev, flags); out_drop: kfree_skb(skb); return -EINVAL; } BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags)) return TC_ACT_SHOT; ri->flags = BPF_F_PEER; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_peer_proto = { .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); ri->tgt_index = ifindex; BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params)); if (plen) memcpy(&ri->nh, params, sizeof(ri->nh)); return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_neigh_proto = { .func = bpf_redirect_neigh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM_OR_NULL, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; return 0; } static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { .func = bpf_msg_apply_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) { msg->cork_bytes = bytes; return 0; } static void sk_msg_reset_curr(struct sk_msg *msg) { if (!msg->sg.size) { msg->sg.curr = msg->sg.start; msg->sg.copybreak = 0; } else { u32 i = msg->sg.end; sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } } static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, u32, end, u64, flags) { u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start; u32 first_sge, last_sge, i, shift, bytes_sg_total; struct scatterlist *sge; u8 *raw, *to, *from; struct page *page; if (unlikely(flags || end <= start)) return -EINVAL; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += len; len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (unlikely(start >= offset + len)) return -EINVAL; first_sge = i; /* The start may point into the sg element so we need to also * account for the headroom. */ bytes_sg_total = start - offset + bytes; if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to * copy into a linear buffer exclusively owned by BPF. Then * place the buffer in the scatterlist and fixup the original * entries by removing the entries now in the linear buffer * and shifting the remaining entries. For now we do not try * to copy partial entries to avoid complexity of running out * of sg_entry slots. The downside is reading a single byte * will copy the entire sg entry. */ do { copy += sk_msg_elem(msg, i)->length; sk_msg_iter_var_next(i); if (bytes_sg_total <= copy) break; } while (i != msg->sg.end); last_sge = i; if (unlikely(bytes_sg_total > copy)) return -EINVAL; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy)); if (unlikely(!page)) return -ENOMEM; raw = page_address(page); i = first_sge; do { sge = sk_msg_elem(msg, i); from = sg_virt(sge); len = sge->length; to = raw + poffset; memcpy(to, from, len); poffset += len; sge->length = 0; put_page(sg_page(sge)); sk_msg_iter_var_next(i); } while (i != last_sge); sg_set_page(&msg->sg.data[first_sge], page, copy, 0); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; i = first_sge; sk_msg_iter_var_next(i); do { u32 move_from; if (i + shift >= NR_MSG_FRAG_IDS) move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) break; msg->sg.data[i] = msg->sg.data[move_from]; msg->sg.data[move_from].length = 0; msg->sg.data[move_from].page_link = 0; msg->sg.data[move_from].offset = 0; sk_msg_iter_var_next(i); } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; } static const struct bpf_func_proto bpf_msg_pull_data_proto = { .func = bpf_msg_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; u32 new, i = 0, l = 0, space, copy = 0, offset = 0; u8 *raw, *to, *from; struct page *page; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (start > offset + l) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); /* If no space available will fallback to copy, we need at * least one scatterlist elem available to push data into * when start aligns to the beginning of an element or two * when it falls inside an element. We handle the start equals * offset case because its the common case for inserting a * header. */ if (!space || (space == 1 && start != offset)) copy = msg->sg.data[i].length; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy + len)); if (unlikely(!page)) return -ENOMEM; if (copy) { int front, back; raw = page_address(page); if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); front = start - offset; back = psge->length - front; from = sg_virt(psge); if (front) memcpy(raw, from, front); if (back) { from += front; to = raw + front + len; memcpy(to, from, back); } put_page(sg_page(psge)); new = i; goto place_new; } if (start - offset) { if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); rsge = sk_msg_elem_cpy(msg, i); psge->length = start - offset; rsge.length -= psge->length; rsge.offset += start; sk_msg_iter_var_next(i); sg_unmark_end(psge); sg_unmark_end(&rsge); } /* Slot(s) to place newly allocated data */ sk_msg_iter_next(msg, end); new = i; sk_msg_iter_var_next(i); if (i == msg->sg.end) { if (!rsge.length) goto place_new; sk_msg_iter_next(msg, end); goto place_new; } /* Shift one or two slots as needed */ sge = sk_msg_elem_cpy(msg, new); sg_unmark_end(&sge); nsge = sk_msg_elem_cpy(msg, i); if (rsge.length) { sk_msg_iter_var_next(i); nnsge = sk_msg_elem_cpy(msg, i); sk_msg_iter_next(msg, end); } while (i != msg->sg.end) { msg->sg.data[i] = sge; sge = nsge; sk_msg_iter_var_next(i); if (rsge.length) { nsge = nnsge; nnsge = sk_msg_elem_cpy(msg, i); } else { nsge = sk_msg_elem_cpy(msg, i); } } place_new: /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; __clear_bit(new, &msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); sk_msg_iter_var_next(new); msg->sg.data[new] = rsge; } sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_push_data_proto = { .func = bpf_msg_push_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static void sk_msg_shift_left(struct sk_msg *msg, int i) { struct scatterlist *sge = sk_msg_elem(msg, i); int prev; put_page(sg_page(sge)); do { prev = i; sk_msg_iter_var_next(i); msg->sg.data[prev] = msg->sg.data[i]; } while (i != msg->sg.end); sk_msg_iter_prev(msg, end); } static void sk_msg_shift_right(struct sk_msg *msg, int i) { struct scatterlist tmp, sge; sk_msg_iter_next(msg, end); sge = sk_msg_elem_cpy(msg, i); sk_msg_iter_var_next(i); tmp = sk_msg_elem_cpy(msg, i); while (i != msg->sg.end) { msg->sg.data[i] = sge; sk_msg_iter_var_next(i); sge = tmp; tmp = sk_msg_elem_cpy(msg, i); } } BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { u32 i = 0, l = 0, space, offset = 0; u64 last = start + len; int pop; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); /* Bounds checks: start and pop must be inside message */ if (start >= offset + l || last > msg->sg.size) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); pop = len; /* --------------| offset * -| start |-------- len -------| * * |----- a ----|-------- pop -------|----- b ----| * |______________________________________________| length * * * a: region at front of scatter element to save * b: region at back of scatter element to save when length > A + pop * pop: region to pop from element, same as input 'pop' here will be * decremented below per iteration. * * Two top-level cases to handle when start != offset, first B is non * zero and second B is zero corresponding to when a pop includes more * than one element. * * Then if B is non-zero AND there is no space allocate space and * compact A, B regions into page. If there is space shift ring to * the rigth free'ing the next element in ring to place B, leaving * A untouched except to reduce length. */ if (start != offset) { struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); int a = start - offset; int b = sge->length - pop - a; sk_msg_iter_var_next(i); if (b > 0) { if (space) { sge->length = a; sk_msg_shift_right(msg, i); nsge = sk_msg_elem(msg, i); get_page(sg_page(sge)); sg_set_page(nsge, sg_page(sge), b, sge->offset + pop + a); } else { struct page *page, *orig; u8 *to, *from; page = alloc_pages(__GFP_NOWARN | __GFP_COMP | GFP_ATOMIC, get_order(a + b)); if (unlikely(!page)) return -ENOMEM; orig = sg_page(sge); from = sg_virt(sge); to = page_address(page); memcpy(to, from, a); memcpy(to + a, from + a + pop, b); sg_set_page(sge, page, a + b, 0); put_page(orig); } pop = 0; } else { pop -= (sge->length - a); sge->length = a; } } /* From above the current layout _must_ be as follows, * * -| offset * -| start * * |---- pop ---|---------------- b ------------| * |____________________________________________| length * * Offset and start of the current msg elem are equal because in the * previous case we handled offset != start and either consumed the * entire element and advanced to the next element OR pop == 0. * * Two cases to handle here are first pop is less than the length * leaving some remainder b above. Simply adjust the element's layout * in this case. Or pop >= length of the element so that b = 0. In this * case advance to next element decrementing pop. */ while (pop) { struct scatterlist *sge = sk_msg_elem(msg, i); if (pop < sge->length) { sge->length -= pop; sge->offset += pop; pop = 0; } else { pop -= sge->length; sk_msg_shift_left(msg, i); } } sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_pop_data_proto = { .func = bpf_msg_pop_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; #ifdef CONFIG_CGROUP_NET_CLASSID BPF_CALL_0(bpf_get_cgroup_classid_curr) { return __task_get_classid(current); } static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .func = bpf_get_cgroup_classid_curr, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) { struct sock *sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return 0; return sock_cgroup_classid(&sk->sk_cgrp_data); } static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { .func = bpf_skb_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .func = bpf_get_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { .func = bpf_get_route_realm, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .func = bpf_get_hash_recalc, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) { /* After all direct packet write, this can be used once for * triggering a lazy recalc on next skb_get_hash() invocation. */ skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_set_hash_invalid_proto = { .func = bpf_set_hash_invalid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash) { /* Set user specified hash as L4(+), so that it gets returned * on skb_get_hash() call unless BPF prog later on triggers a * skb_clear_hash(). */ __skb_set_sw_hash(skb, hash, true); return 0; } static const struct bpf_func_proto bpf_set_hash_proto = { .func = bpf_set_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { int ret; bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with len as headroom, * so no need to do it here. */ skb_push(skb, len); memmove(skb->data, skb->data + len, off); memset(skb->data + off, 0, len); /* No skb_postpush_rcsum(skb, skb->data + off, len) * needed here as it does not change the skb->csum * result for checksum complete when summing over * zeroed blocks. */ return 0; } static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { void *old_data; /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; old_data = skb->data; __skb_pull(skb, len); skb_postpull_rcsum(skb, old_data + off, len); memmove(skb->data, old_data, off); return 0; } static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* There's no need for __skb_push()/__skb_pull() pair to * get to the start of the mac header as we're guaranteed * to always start from here under eBPF. */ ret = bpf_skb_generic_push(skb, off, len); if (likely(!ret)) { skb->mac_header -= len; skb->network_header -= len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* Same here, __skb_push()/__skb_pull() pair not needed. */ ret = bpf_skb_generic_pop(skb, off, len); if (likely(!ret)) { skb->mac_header += len; skb->network_header += len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV4 needs to be changed into * SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_6_to_4(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV6 needs to be changed into * SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { __be16 from_proto = skb->protocol; if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) return bpf_skb_proto_4_to_6(skb); if (from_proto == htons(ETH_P_IPV6) && to_proto == htons(ETH_P_IP)) return bpf_skb_proto_6_to_4(skb); return -ENOTSUPP; } BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, u64, flags) { int ret; if (unlikely(flags)) return -EINVAL; /* General idea is that this helper does the basic groundwork * needed for changing the protocol, and eBPF program fills the * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace() * and other helpers, rather than passing a raw buffer here. * * The rationale is to keep this minimal and without a need to * deal with raw packet data. F.e. even if we would pass buffers * here, the program still needs to call the bpf_lX_csum_replace() * helpers anyway. Plus, this way we keep also separation of * concerns, since f.e. bpf_skb_store_bytes() should only take * care of stores. * * Currently, additional options and extension header space are * not supported, but flags register is reserved so we can adapt * that. For offloads, we mark packet as dodgy, so that headers * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_proto_proto = { .func = bpf_skb_change_proto, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) return -EINVAL; skb->pkt_type = pkt_type; return 0; } static const struct bpf_func_proto bpf_skb_change_type_proto = { .func = bpf_skb_change_type, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): return sizeof(struct ipv6hdr); default: return ~0U; } } #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ BPF_ADJ_ROOM_ENCAP_L2_MASK)) static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT; bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK; u16 mac_len = 0, inner_net = 0, inner_trans = 0; unsigned int gso_type = SKB_GSO_DODGY; int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_cow_head(skb, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -ENOTSUPP; if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE && flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) return -EINVAL; if (skb->encapsulation) return -EALREADY; mac_len = skb->network_header - skb->mac_header; inner_net = skb->network_header; if (inner_mac_len > len_diff) return -EINVAL; inner_trans = skb->transport_header; } ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { skb->inner_mac_header = inner_net - inner_mac_len; skb->inner_network_header = inner_net; skb->inner_transport_header = inner_trans; skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_set_network_header(skb, mac_len); if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) gso_type |= SKB_GSO_UDP_TUNNEL; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE) gso_type |= SKB_GSO_GRE; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) gso_type |= SKB_GSO_IPXIP6; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) gso_type |= SKB_GSO_IPXIP4; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE || flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) { int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); skb_set_transport_header(skb, mac_len + nh_len); } /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) skb->protocol = htons(ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) skb->protocol = htons(ETH_P_IP); } if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; /* Due to header growth, MSS needs to be downgraded. * There is a BUG_ON() when segmenting the frag_list with * head_frag true, so linearize the skb after downgrading * the MSS. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { skb_decrease_gso_size(shinfo, len_diff); if (shinfo->frag_list) return skb_linearize(skb); } } return 0; } static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Due to header shrink, MSS can be upgraded. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } return 0; } #define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_diff_abs = abs(len_diff); bool shrink = len_diff < 0; int ret = 0; if (unlikely(flags || mode)) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (!shrink) { ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; __skb_push(skb, len_diff_abs); memset(skb->data, 0, len_diff_abs); } else { if (unlikely(!pskb_may_pull(skb, len_diff_abs))) return -ENOMEM; __skb_pull(skb, len_diff_abs); } bpf_compute_data_end_sk_skb(skb); if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); rxm->full_len += len_diff; } return ret; } static const struct bpf_func_proto sk_skb_adjust_room_proto = { .func = sk_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (unlikely(proto != htons(ETH_P_IP) && proto != htons(ETH_P_IPV6))) return -ENOTSUPP; off = skb_mac_header_len(skb); switch (mode) { case BPF_ADJ_ROOM_NET: off += bpf_skb_net_base_len(skb); break; case BPF_ADJ_ROOM_MAC: break; default: return -ENOTSUPP; } len_cur = skb->len - skb_network_offset(skb); if ((shrink && (len_diff_abs >= len_cur || len_cur - len_diff_abs < len_min)) || (!shrink && (skb->len + len_diff_abs > len_max && !skb_is_gso(skb)))) return -ENOTSUPP; ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) : bpf_skb_net_grow(skb, off, len_diff_abs, flags); if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET)) __skb_reset_checksum_unnecessary(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_adjust_room_proto = { .func = bpf_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static u32 __bpf_skb_min_len(const struct sk_buff *skb) { int offset = skb_network_offset(skb); u32 min_len = 0; if (offset > 0) min_len = offset; if (skb_transport_header_was_set(skb)) { offset = skb_transport_offset(skb); if (offset > 0) min_len = offset; } if (skb->ip_summed == CHECKSUM_PARTIAL) { offset = skb_checksum_start_offset(skb) + skb->csum_offset + sizeof(__sum16); if (offset > 0) min_len = offset; } return min_len; } static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) { unsigned int old_len = skb->len; int ret; ret = __skb_grow_rcsum(skb, new_len); if (!ret) memset(skb->data + old_len, 0, new_len - old_len); return ret; } static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) { return __skb_trim_rcsum(skb, new_len); } static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) return -EINVAL; if (skb->encapsulation) return -ENOTSUPP; /* The basic idea of this helper is that it's performing the * needed work to either grow or trim an skb, and eBPF program * rewrites the rest via helpers like bpf_skb_store_bytes(), * bpf_lX_csum_replace() and others rather than passing a raw * buffer here. This one is a slow path helper and intended * for replies with control messages. * * Like in bpf_skb_change_proto(), we want to keep this rather * minimal and without protocol specifics so that we are able * to separate concerns as in bpf_skb_store_bytes() should only * be the one responsible for writing buffers. * * It's really expected to be a slow path operation here for * control message replies, so we're implicitly linearizing, * uncloning and drop offloads from the skb by this. */ ret = __bpf_try_make_writable(skb, skb->len); if (!ret) { if (new_len > skb->len) ret = bpf_skb_grow_rcsum(skb, new_len); else if (new_len < skb->len) ret = bpf_skb_trim_rcsum(skb, new_len); if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } return ret; } BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_tail_proto = { .func = bpf_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_end_sk_skb(skb); return ret; } static const struct bpf_func_proto sk_skb_change_tail_proto = { .func = sk_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) || new_len < skb->len)) return -EINVAL; ret = skb_cow(skb, head_room); if (likely(!ret)) { /* Idea for this helper is that we currently only * allow to expand on mac header. This means that * skb->protocol network header, etc, stay as is. * Compared to bpf_skb_change_tail(), we're more * flexible due to not needing to linearize or * reset GSO. Intention for this helper is to be * used by an L3 skb that needs to push mac header * for redirection into L2 device. */ __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); skb_reset_mac_len(skb); } return ret; } BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { int ret = __bpf_skb_change_head(skb, head_room, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { .func = bpf_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { int ret = __bpf_skb_change_head(skb, head_room, flags); bpf_compute_data_end_sk_skb(skb); return ret; } static const struct bpf_func_proto sk_skb_change_head_proto = { .func = sk_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; } BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; if (metalen) memmove(xdp->data_meta + offset, xdp->data_meta, metalen); xdp->data_meta += offset; xdp->data = data; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .func = bpf_xdp_adjust_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; /* ALL drivers MUST init xdp->frame_sz, chicken check below */ if (unlikely(xdp->frame_sz > PAGE_SIZE)) { WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); return -EINVAL; } if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; /* Clear memory area on grow, can contain uninit kernel memory */ if (offset > 0) memset(xdp->data_end, 0, offset); xdp->data_end = data_end; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { .func = bpf_xdp_adjust_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely((metalen & (sizeof(__u32) - 1)) || (metalen > 32))) return -EACCES; xdp->data_meta = meta; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .func = bpf_xdp_adjust_meta, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, struct bpf_map *map, struct xdp_buff *xdp) { switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: return dev_map_enqueue(fwd, xdp, dev_rx); case BPF_MAP_TYPE_CPUMAP: return cpu_map_enqueue(fwd, xdp, dev_rx); case BPF_MAP_TYPE_XSKMAP: return __xsk_map_redirect(fwd, xdp); default: return -EBADRQC; } return 0; } void xdp_do_flush(void) { __dev_flush(); __cpu_map_flush(); __xsk_map_flush(); } EXPORT_SYMBOL_GPL(xdp_do_flush); static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) { switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: return __dev_map_lookup_elem(map, index); case BPF_MAP_TYPE_DEVMAP_HASH: return __dev_map_hash_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); case BPF_MAP_TYPE_XSKMAP: return __xsk_map_lookup_elem(map, index); default: return NULL; } } void bpf_clear_redirect_map(struct bpf_map *map) { struct bpf_redirect_info *ri; int cpu; for_each_possible_cpu(cpu) { ri = per_cpu_ptr(&bpf_redirect_info, cpu); /* Avoid polluting remote cacheline due to writes if * not needed. Once we pass this test, we need the * cmpxchg() to make sure it hasn't been changed in * the meantime by remote CPU. */ if (unlikely(READ_ONCE(ri->map) == map)) cmpxchg(&ri->map, map, NULL); } } int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map = READ_ONCE(ri->map); u32 index = ri->tgt_index; void *fwd = ri->tgt_value; int err; ri->tgt_index = 0; ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); if (unlikely(!map)) { fwd = dev_get_by_index_rcu(dev_net(dev), index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } err = dev_xdp_enqueue(fwd, xdp, dev); } else { err = __bpf_tx_xdp_map(dev, fwd, map, xdp); } if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_redirect); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct bpf_map *map) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); u32 index = ri->tgt_index; void *fwd = ri->tgt_value; int err = 0; ri->tgt_index = 0; ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); if (map->map_type == BPF_MAP_TYPE_DEVMAP || map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { struct bpf_dtab_netdev *dst = fwd; err = dev_map_generic_redirect(dst, skb, xdp_prog); if (unlikely(err)) goto err; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { struct xdp_sock *xs = fwd; err = xsk_generic_rcv(xs, xdp); if (err) goto err; consume_skb(skb); } else { /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ err = -EBADRQC; goto err; } _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); return err; } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map = READ_ONCE(ri->map); u32 index = ri->tgt_index; struct net_device *fwd; int err = 0; if (map) return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, map); ri->tgt_index = 0; fwd = dev_get_by_index_rcu(dev_net(dev), index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } err = xdp_ok_fwd_dev(fwd, skb->len); if (unlikely(err)) goto err; skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, index); generic_xdp_tx(skb, xdp_prog); return 0; err: _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags)) return XDP_ABORTED; ri->flags = flags; ri->tgt_index = ifindex; ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); return XDP_REDIRECT; } static const struct bpf_func_proto bpf_xdp_redirect_proto = { .func = bpf_xdp_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); /* Lower bits of the flags are used as return code on lookup failure */ if (unlikely(flags > XDP_TX)) return XDP_ABORTED; ri->tgt_value = __xdp_map_lookup_elem(map, ifindex); if (unlikely(!ri->tgt_value)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes * precedence. */ WRITE_ONCE(ri->map, NULL); return flags; } ri->flags = flags; ri->tgt_index = ifindex; WRITE_ONCE(ri->map, map); return XDP_REDIRECT; } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .func = bpf_xdp_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, unsigned long off, unsigned long len) { void *ptr = skb_header_pointer(skb, off, len, dst_buff); if (unlikely(!ptr)) return len; if (ptr != dst_buff) memcpy(dst_buff, ptr, len); return 0; } BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, bpf_skb_copy); } static const struct bpf_func_proto bpf_skb_event_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, u32, size, u64, flags) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; int err; if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6)))) { err = -EINVAL; goto err_clear; } if (ip_tunnel_info_af(info) != bpf_tunnel_key_af(flags)) { err = -EPROTO; goto err_clear; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) { err = -EINVAL; switch (size) { case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) goto err_clear; set_compat: to = (struct bpf_tunnel_key *)compat; break; default: goto err_clear; } } to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); to->tunnel_label = 0; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy(to_orig, to, size); return 0; err_clear: memset(to_orig, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; if (unlikely(!info || !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) { err = -ENOENT; goto err_clear; } if (unlikely(size < info->options_len)) { err = -ENOMEM; goto err_clear; } ip_tunnel_info_opts_get(to, info); if (size > info->options_len) memset(to + info->options_len, 0, size - info->options_len); return info->options_len; err_clear: memset(to, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { .func = bpf_skb_get_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; static struct metadata_dst __percpu *md_dst; BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, const struct bpf_tunnel_key *, from, u32, size, u64, flags) { struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; } } if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; if (flags & BPF_F_DONT_FRAGMENT) info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; if (flags & BPF_F_ZERO_CSUM_TX) info->key.tun_flags &= ~TUNNEL_CSUM; if (flags & BPF_F_SEQ_NUMBER) info->key.tun_flags |= TUNNEL_SEQ; info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; if (flags & BPF_F_TUNINFO_IPV6) { info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); info->key.label = cpu_to_be32(from->tunnel_label) & IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); } return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, const u8 *, from, u32, size) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT); return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .func = bpf_skb_set_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { struct metadata_dst __percpu *tmp; tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, METADATA_IP_TUNNEL, GFP_KERNEL); if (!tmp) return NULL; if (cmpxchg(&md_dst, NULL, tmp)) metadata_dst_free_percpu(tmp); } switch (which) { case BPF_FUNC_skb_set_tunnel_key: return &bpf_skb_set_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_opt: return &bpf_skb_set_tunnel_opt_proto; default: return NULL; } } BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return -ENOENT; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return sk_under_cgroup_hierarchy(sk, cgrp); } static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SOCK_CGROUP_DATA static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .func = bpf_skb_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, int ancestor_level) { struct cgroup *ancestor; struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) return 0; return cgroup_id(ancestor); } BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .func = bpf_skb_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk) { return __bpf_sk_cgroup_id(sk); } static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); } static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, unsigned long off, unsigned long len) { memcpy(dst_buff, src_buff + off, len); return 0; } BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!xdp || xdp_size > (unsigned long)(xdp->data_end - xdp->data))) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, xdp->data, xdp_size, bpf_xdp_copy); } static const struct bpf_func_proto bpf_xdp_event_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { .func = bpf_get_socket_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { .func = bpf_get_socket_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .func = bpf_get_socket_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { .func = bpf_get_socket_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static u64 __bpf_get_netns_cookie(struct sock *sk) { #ifdef CONFIG_NET_NS return __net_gen_cookie(sk ? sk->sk_net.net : &init_net); #else return 0; #endif } BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) { return __bpf_get_netns_cookie(ctx); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = { .func = bpf_get_netns_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { .func = bpf_get_netns_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); kuid_t kuid; if (!sk || !sk_fullsock(sk)) return overflowuid; kuid = sock_net_uid(sock_net(sk), sk); return from_kuid_munged(sock_net(sk)->user_ns, kuid); } static const struct bpf_func_proto bpf_get_socket_uid_proto = { .func = bpf_get_socket_uid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { char devname[IFNAMSIZ]; int val, valbool; struct net *net; int ifindex; int ret = 0; if (!sk_fullsock(sk)) return -EINVAL; sock_owned_by_me(sk); if (level == SOL_SOCKET) { if (optlen != sizeof(int) && optname != SO_BINDTODEVICE) return -EINVAL; val = *((int *)optval); valbool = val ? 1 : 0; /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: val = min_t(u32, val, READ_ONCE(sysctl_rmem_max)); val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); break; case SO_MAX_PACING_RATE: /* 32bit version */ if (val != ~0U) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : (unsigned int)val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); break; case SO_PRIORITY: sk->sk_priority = val; break; case SO_RCVLOWAT: if (val < 0) val = INT_MAX; WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_MARK: if (sk->sk_mark != val) { sk->sk_mark = val; sk_dst_reset(sk); } break; case SO_BINDTODEVICE: optlen = min_t(long, optlen, IFNAMSIZ - 1); strncpy(devname, optval, optlen); devname[optlen] = 0; ifindex = 0; if (devname[0] != '\0') { struct net_device *dev; ret = -ENODEV; net = sock_net(sk); dev = dev_get_by_name(net, devname); if (!dev) break; ifindex = dev->ifindex; dev_put(dev); } ret = sock_bindtoindex(sk, ifindex, false); break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; default: ret = -EINVAL; } #ifdef CONFIG_INET } else if (level == SOL_IP) { if (optlen != sizeof(int) || sk->sk_family != AF_INET) return -EINVAL; val = *((int *)optval); /* Only some options are supported */ switch (optname) { case IP_TOS: if (val < -1 || val > 0xff) { ret = -EINVAL; } else { struct inet_sock *inet = inet_sk(sk); if (val == -1) val = 0; inet->tos = val; } break; default: ret = -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) } else if (level == SOL_IPV6) { if (optlen != sizeof(int) || sk->sk_family != AF_INET6) return -EINVAL; val = *((int *)optval); /* Only some options are supported */ switch (optname) { case IPV6_TCLASS: if (val < -1 || val > 0xff) { ret = -EINVAL; } else { struct ipv6_pinfo *np = inet6_sk(sk); if (val == -1) val = 0; np->tclass = val; } break; default: ret = -EINVAL; } #endif } else if (level == SOL_TCP && sk->sk_prot->setsockopt == tcp_setsockopt) { if (optname == TCP_CONGESTION) { char name[TCP_CA_NAME_MAX]; strncpy(name, optval, min_t(long, optlen, TCP_CA_NAME_MAX-1)); name[TCP_CA_NAME_MAX-1] = 0; ret = tcp_set_congestion_control(sk, name, false, true); } else { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned long timeout; if (optlen != sizeof(int)) return -EINVAL; val = *((int *)optval); /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: if (val <= 0 || tp->data_segs_out > tp->syn_data) ret = -EINVAL; else tp->snd_cwnd = val; break; case TCP_BPF_SNDCWND_CLAMP: if (val <= 0) { ret = -EINVAL; } else { tp->snd_cwnd_clamp = val; tp->snd_ssthresh = val; } break; case TCP_BPF_DELACK_MAX: timeout = usecs_to_jiffies(val); if (timeout > TCP_DELACK_MAX || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; case TCP_BPF_RTO_MIN: timeout = usecs_to_jiffies(val); if (timeout > TCP_RTO_MIN || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; else tp->save_syn = val; break; case TCP_KEEPIDLE: ret = tcp_sock_set_keepidle_locked(sk, val); break; case TCP_KEEPINTVL: if (val < 1 || val > MAX_TCP_KEEPINTVL) ret = -EINVAL; else tp->keepalive_intvl = val * HZ; break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) ret = -EINVAL; else tp->keepalive_probes = val; break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) ret = -EINVAL; else icsk->icsk_syn_retries = val; break; case TCP_USER_TIMEOUT: if (val < 0) ret = -EINVAL; else icsk->icsk_user_timeout = val; break; case TCP_NOTSENT_LOWAT: tp->notsent_lowat = val; sk->sk_write_space(sk); break; default: ret = -EINVAL; } } #endif } else { ret = -EINVAL; } return ret; } static int _bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (!sk_fullsock(sk)) goto err_clear; sock_owned_by_me(sk); #ifdef CONFIG_INET if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { struct inet_connection_sock *icsk; struct tcp_sock *tp; switch (optname) { case TCP_CONGESTION: icsk = inet_csk(sk); if (!icsk->icsk_ca_ops || optlen <= 1) goto err_clear; strncpy(optval, icsk->icsk_ca_ops->name, optlen); optval[optlen - 1] = 0; break; case TCP_SAVED_SYN: tp = tcp_sk(sk); if (optlen <= 0 || !tp->saved_syn || optlen > tcp_saved_syn_len(tp->saved_syn)) goto err_clear; memcpy(optval, tp->saved_syn->data, optlen); break; default: goto err_clear; } } else if (level == SOL_IP) { struct inet_sock *inet = inet_sk(sk); if (optlen != sizeof(int) || sk->sk_family != AF_INET) goto err_clear; /* Only some options are supported */ switch (optname) { case IP_TOS: *((int *)optval) = (int)inet->tos; break; default: goto err_clear; } #if IS_ENABLED(CONFIG_IPV6) } else if (level == SOL_IPV6) { struct ipv6_pinfo *np = inet6_sk(sk); if (optlen != sizeof(int) || sk->sk_family != AF_INET6) goto err_clear; /* Only some options are supported */ switch (optname) { case IPV6_TCLASS: *((int *)optval) = (int)np->tclass; break; default: goto err_clear; } #endif } else { goto err_clear; } return 0; #endif err_clear: memset(optval, 0, optlen); return -EINVAL; } BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { .func = bpf_sock_addr_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { .func = bpf_sock_addr_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .func = bpf_sock_ops_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE, }; static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, int optname, const u8 **start) { struct sk_buff *syn_skb = bpf_sock->syn_skb; const u8 *hdr_start; int ret; if (syn_skb) { /* sk is a request_sock here */ if (optname == TCP_BPF_SYN) { hdr_start = syn_skb->data; ret = tcp_hdrlen(syn_skb); } else if (optname == TCP_BPF_SYN_IP) { hdr_start = skb_network_header(syn_skb); ret = skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } else { /* optname == TCP_BPF_SYN_MAC */ hdr_start = skb_mac_header(syn_skb); ret = skb_mac_header_len(syn_skb) + skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } } else { struct sock *sk = bpf_sock->sk; struct saved_syn *saved_syn; if (sk->sk_state == TCP_NEW_SYN_RECV) /* synack retransmit. bpf_sock->syn_skb will * not be available. It has to resort to * saved_syn (if it is saved). */ saved_syn = inet_reqsk(sk)->saved_syn; else saved_syn = tcp_sk(sk)->saved_syn; if (!saved_syn) return -ENOENT; if (optname == TCP_BPF_SYN) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen + saved_syn->network_hdrlen; ret = saved_syn->tcp_hdrlen; } else if (optname == TCP_BPF_SYN_IP) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen; ret = saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } else { /* optname == TCP_BPF_SYN_MAC */ /* TCP_SAVE_SYN may not have saved the mac hdr */ if (!saved_syn->mac_hdrlen) return -ENOENT; hdr_start = saved_syn->data; ret = saved_syn->mac_hdrlen + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } } *start = hdr_start; return ret; } BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; const u8 *start; ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); if (ret > 0) { copy_len = ret; if (optlen < copy_len) { copy_len = optlen; ret = -ENOSPC; } memcpy(optval, start, copy_len); } /* Zero out unused buffer at the end */ memset(optval + copy_len, 0, optlen - copy_len); return ret; } return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = { .func = bpf_sock_ops_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, int, argval) { struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; tcp_sk(sk)->bpf_sock_ops_cb_flags = val; return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS); } static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = { .func = bpf_sock_ops_cb_flags_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; EXPORT_SYMBOL_GPL(ipv6_bpf_stub); BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, int, addr_len) { #ifdef CONFIG_INET struct sock *sk = ctx->sk; u32 flags = BIND_FROM_BPF; int err; err = -EINVAL; if (addr_len < offsetofend(struct sockaddr, sa_family)) return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; if (((struct sockaddr_in *)addr)->sin_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; return __inet_bind(sk, addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) return err; if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; /* ipv6_bpf_stub cannot be NULL, since it's called from * bpf_cgroup_inet6_connect hook and ipv6 is already loaded */ return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_bind_proto = { .func = bpf_bind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, }; #ifdef CONFIG_XFRM BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, struct bpf_xfrm_state *, to, u32, size, u64, flags) { const struct sec_path *sp = skb_sec_path(skb); const struct xfrm_state *x; if (!sp || unlikely(index >= sp->len || flags)) goto err_clear; x = sp->xvec[index]; if (unlikely(size != sizeof(struct bpf_xfrm_state))) goto err_clear; to->reqid = x->props.reqid; to->spi = x->id.spi; to->family = x->props.family; to->ext = 0; if (to->family == AF_INET6) { memcpy(to->remote_ipv6, x->props.saddr.a6, sizeof(to->remote_ipv6)); } else { to->remote_ipv4 = x->props.saddr.a4; memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); } return 0; err_clear: memset(to, 0, size); return -EINVAL; } static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { .func = bpf_skb_get_xfrm_state, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, const struct neighbour *neigh, const struct net_device *dev) { memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; return 0; } #endif #if IS_ENABLED(CONFIG_INET) static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct fib_nh_common *nhc; struct in_device *in_dev; struct neighbour *neigh; struct net_device *dev; struct fib_result res; struct flowi4 fl4; int err; u32 mtu; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; fl4.flowi4_oif = params->ifindex; } else { fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } fl4.flowi4_tos = params->tos & IPTOS_RT_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.flowi4_proto = params->l4_protocol; fl4.daddr = params->ipv4_dst; fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } if (err) { /* map fib lookup errors to RTN_ type */ if (err == -EINVAL) return BPF_FIB_LKUP_RET_BLACKHOLE; if (err == -EHOSTUNREACH) return BPF_FIB_LKUP_RET_UNREACHABLE; if (err == -EACCES) return BPF_FIB_LKUP_RET_PROHIBIT; return BPF_FIB_LKUP_RET_NOT_FWDED; } if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED; if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL); if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) return BPF_FIB_LKUP_RET_FRAG_NEEDED; } nhc = res.nhc; /* do not handle lwt encaps right now */ if (nhc->nhc_lwtstate) return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); } if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; return bpf_fib_set_fwd_params(params, neigh, dev); } #endif #if IS_ENABLED(CONFIG_IPV6) static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct in6_addr *src = (struct in6_addr *) params->ipv6_src; struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; struct fib6_result res = {}; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; struct flowi6 fl6; int strict = 0; int oif, err; u32 mtu; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !idev->cnf.forwarding)) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; oif = fl6.flowi6_oif = params->ifindex; } else { oif = fl6.flowi6_iif = params->ifindex; fl6.flowi6_oif = 0; strict = RT6_LOOKUP_F_HAS_SADDR; } fl6.flowlabel = params->flowinfo; fl6.flowi6_scope = 0; fl6.flowi6_flags = 0; fl6.mp_hash = 0; fl6.flowi6_proto = params->l4_protocol; fl6.daddr = *dst; fl6.saddr = *src; fl6.fl6_sport = params->sport; fl6.fl6_dport = params->dport; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict); } if (unlikely(err || IS_ERR_OR_NULL(res.f6i) || res.f6i == net->ipv6.fib6_null_entry)) return BPF_FIB_LKUP_RET_NOT_FWDED; switch (res.fib6_type) { /* only unicast is forwarded */ case RTN_UNICAST: break; case RTN_BLACKHOLE: return BPF_FIB_LKUP_RET_BLACKHOLE; case RTN_UNREACHABLE: return BPF_FIB_LKUP_RET_UNREACHABLE; case RTN_PROHIBIT: return BPF_FIB_LKUP_RET_PROHIBIT; default: return BPF_FIB_LKUP_RET_NOT_FWDED; } ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif, fl6.flowi6_oif != 0, NULL, strict); if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); if (params->tot_len > mtu) return BPF_FIB_LKUP_RET_FRAG_NEEDED; } if (res.nh->fib_nh_lws) return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (res.nh->fib_nh_gw_family) *dst = res.nh->fib_nh_gw6; dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; return bpf_fib_set_fwd_params(params, neigh, dev); } #endif BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) return -EINVAL; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif } return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { .func = bpf_xdp_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) return -EINVAL; if (params->tot_len) check_mtu = true; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; /* When tot_len isn't provided by user, check skb * against MTU of FIB lookup resulting net_device */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; } return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .func = bpf_skb_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { int err; struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr; if (!seg6_validate_srh(srh, len, false)) return -EINVAL; switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); break; case BPF_LWT_ENCAP_SEG6: skb_reset_inner_headers(skb); skb->encapsulation = 1; err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6); break; default: return -EINVAL; } bpf_compute_data_pointers(skb); if (err) return err; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); } #endif /* CONFIG_IPV6_SEG6_BPF */ #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) { return bpf_lwt_push_ip_encap(skb, hdr, len, ingress); } #endif BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_LWT_ENCAP_SEG6: case BPF_LWT_ENCAP_SEG6_INLINE: return bpf_push_seg6_encap(skb, type, hdr, len); #endif #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, true /* ingress */); #endif default: return -EINVAL; } } BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, false /* egress */); #endif default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { .func = bpf_lwt_in_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM, .arg4_type = ARG_CONST_SIZE }; static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { .func = bpf_lwt_xmit_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM, .arg4_type = ARG_CONST_SIZE }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; if (srh == NULL) return -EINVAL; srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (ptr >= srh_tlvs && ptr + len <= srh_end) srh_state->valid = false; else if (ptr < (void *)&srh->flags || ptr + len > (void *)&srh->segments) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); memcpy(skb->data + offset, from, len); return 0; } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .func = bpf_lwt_seg6_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM, .arg4_type = ARG_CONST_SIZE }; static void bpf_update_srh_state(struct sk_buff *skb) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) { srh_state->srh = NULL; } else { srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen = srh_state->srh->hdrlen << 3; srh_state->valid = true; } } BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int hdroff = 0; int err; switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(struct in6_addr)) return -EINVAL; return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); case SEG6_LOCAL_ACTION_END_T: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_DT6: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0) return -EBADMSG; if (!pskb_pull(skb, hdroff)) return -EBADMSG; skb_postpull_rcsum(skb, skb_network_header(skb), hdroff); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; bpf_compute_data_pointers(skb); bpf_update_srh_state(skb); return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_B6: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, param, param_len); if (!err) bpf_update_srh_state(skb); return err; case SEG6_LOCAL_ACTION_END_B6_ENCAP: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, param, param_len); if (!err) bpf_update_srh_state(skb); return err; default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { .func = bpf_lwt_seg6_action, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM, .arg4_type = ARG_CONST_SIZE }; BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_end, *srh_tlvs, *ptr; struct ipv6hdr *hdr; int srhoff = 0; int ret; if (unlikely(srh == NULL)) return -EINVAL; srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + ((srh->first_segment + 1) << 4)); srh_end = (void *)((unsigned char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (unlikely(ptr < srh_tlvs || ptr > srh_end)) return -EFAULT; if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end)) return -EFAULT; if (len > 0) { ret = skb_cow_head(skb, len); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, offset, len); } else { ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len); } bpf_compute_data_pointers(skb); if (unlikely(ret < 0)) return ret; hdr = (struct ipv6hdr *)skb->data; hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen += len; srh_state->valid = false; return 0; } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .func = bpf_lwt_seg6_adjust_srh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_IPV6_SEG6_BPF */ #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) { bool refcounted = false; struct sock *sk = NULL; if (family == AF_INET) { __be32 src4 = tuple->ipv4.saddr; __be32 dst4 = tuple->ipv4.daddr; if (proto == IPPROTO_TCP) sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &udp_table, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0, src6, tuple->ipv6.sport, dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, dst6, tuple->ipv6.dport, dif, sdif, &udp_table, NULL); #endif } if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); sk = NULL; } return sk; } /* bpf_skc_lookup performs the core lookup for different types of sockets, * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. * Returns the socket as an 'unsigned long' to simplify the casting in the * callers to satisfy BPF_CALL declarations. */ static struct sock * __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = NULL; u8 family = AF_UNSPEC; struct net *net; int sdif; if (len == sizeof(tuple->ipv4)) family = AF_INET; else if (len == sizeof(tuple->ipv6)) family = AF_INET6; else return NULL; if (unlikely(family == AF_UNSPEC || flags || !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (family == AF_INET) sdif = inet_sdif(skb); else sdif = inet6_sdif(skb); if ((s32)netns_id < 0) { net = caller_net; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); put_net(net); } out: return sk; } static struct sock * __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (!sk_fullsock(sk2)) sk2 = NULL; if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } static struct sock * bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct net *caller_net; int ifindex; if (skb->dev) { caller_net = dev_net(skb->dev); ifindex = skb->dev->ifindex; } else { caller_net = sock_net(skb->sk); ifindex = 0; } return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags); } static struct sock * bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id, flags); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (!sk_fullsock(sk2)) sk2 = NULL; if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .func = bpf_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .func = bpf_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .func = bpf_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_release, struct sock *, sk) { if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net *caller_net = dev_net(ctx->rxq->dev); int ifindex = ctx->rxq->dev->ifindex; return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .func = bpf_xdp_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net *caller_net = dev_net(ctx->rxq->dev); int ifindex = ctx->rxq->dev->ifindex; return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .func = bpf_xdp_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net *caller_net = dev_net(ctx->rxq->dev); int ifindex = ctx->rxq->dev->ifindex; return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .func = bpf_xdp_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .func = bpf_sock_addr_skc_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .func = bpf_sock_addr_sk_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .func = bpf_sock_addr_sk_lookup_udp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, icsk_retransmits)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_tcp_sock, bytes_received): case offsetof(struct bpf_tcp_sock, bytes_acked): return size == sizeof(__u64); default: return size == sizeof(__u32); } } u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ } while (0) #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ si->dst_reg, si->src_reg, \ offsetof( \ struct inet_connection_sock, \ FIELD)); \ } while (0) if (insn > insn_buf) return insn - insn_buf; switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; case offsetof(struct bpf_tcp_sock, snd_cwnd): BPF_TCP_SOCK_GET_COMMON(snd_cwnd); break; case offsetof(struct bpf_tcp_sock, srtt_us): BPF_TCP_SOCK_GET_COMMON(srtt_us); break; case offsetof(struct bpf_tcp_sock, snd_ssthresh): BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); break; case offsetof(struct bpf_tcp_sock, rcv_nxt): BPF_TCP_SOCK_GET_COMMON(rcv_nxt); break; case offsetof(struct bpf_tcp_sock, snd_nxt): BPF_TCP_SOCK_GET_COMMON(snd_nxt); break; case offsetof(struct bpf_tcp_sock, snd_una): BPF_TCP_SOCK_GET_COMMON(snd_una); break; case offsetof(struct bpf_tcp_sock, mss_cache): BPF_TCP_SOCK_GET_COMMON(mss_cache); break; case offsetof(struct bpf_tcp_sock, ecn_flags): BPF_TCP_SOCK_GET_COMMON(ecn_flags); break; case offsetof(struct bpf_tcp_sock, rate_delivered): BPF_TCP_SOCK_GET_COMMON(rate_delivered); break; case offsetof(struct bpf_tcp_sock, rate_interval_us): BPF_TCP_SOCK_GET_COMMON(rate_interval_us); break; case offsetof(struct bpf_tcp_sock, packets_out): BPF_TCP_SOCK_GET_COMMON(packets_out); break; case offsetof(struct bpf_tcp_sock, retrans_out): BPF_TCP_SOCK_GET_COMMON(retrans_out); break; case offsetof(struct bpf_tcp_sock, total_retrans): BPF_TCP_SOCK_GET_COMMON(total_retrans); break; case offsetof(struct bpf_tcp_sock, segs_in): BPF_TCP_SOCK_GET_COMMON(segs_in); break; case offsetof(struct bpf_tcp_sock, data_segs_in): BPF_TCP_SOCK_GET_COMMON(data_segs_in); break; case offsetof(struct bpf_tcp_sock, segs_out): BPF_TCP_SOCK_GET_COMMON(segs_out); break; case offsetof(struct bpf_tcp_sock, data_segs_out): BPF_TCP_SOCK_GET_COMMON(data_segs_out); break; case offsetof(struct bpf_tcp_sock, lost_out): BPF_TCP_SOCK_GET_COMMON(lost_out); break; case offsetof(struct bpf_tcp_sock, sacked_out): BPF_TCP_SOCK_GET_COMMON(sacked_out); break; case offsetof(struct bpf_tcp_sock, bytes_received): BPF_TCP_SOCK_GET_COMMON(bytes_received); break; case offsetof(struct bpf_tcp_sock, bytes_acked): BPF_TCP_SOCK_GET_COMMON(bytes_acked); break; case offsetof(struct bpf_tcp_sock, dsack_dups): BPF_TCP_SOCK_GET_COMMON(dsack_dups); break; case offsetof(struct bpf_tcp_sock, delivered): BPF_TCP_SOCK_GET_COMMON(delivered); break; case offsetof(struct bpf_tcp_sock, delivered_ce): BPF_TCP_SOCK_GET_COMMON(delivered_ce); break; case offsetof(struct bpf_tcp_sock, icsk_retransmits): BPF_INET_SOCK_GET_COMMON(icsk_retransmits); break; } return insn - insn_buf; } BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) { sk = sk_to_full_sk(sk); if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) return (unsigned long)sk; return (unsigned long)NULL; } static const struct bpf_func_proto bpf_get_listener_sock_proto = { .func = bpf_get_listener_sock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); break; case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); break; default: return 0; } if (skb_headlen(skb) < iphdr_len) return 0; if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len)) return 0; return INET_ECN_set_ce(skb); } bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) return false; if (off % size != 0) return false; switch (off) { default: return size == sizeof(__u32); } } u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_XDP_SOCK_GET(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ } while (0) switch (si->off) { case offsetof(struct bpf_xdp_sock, queue_id): BPF_XDP_SOCK_GET(queue_id); break; } return insn - insn_buf; } static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES u32 cookie; int ret; if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) return -ENOENT; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (ret > 0) return 0; return -ENOENT; #else return -ENOTSUPP; #endif } static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .func = bpf_tcp_check_syncookie, .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES u32 cookie; u16 mss; if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) return -EINVAL; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && sk->sk_ipv6only) return -EINVAL; mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (mss == 0) return -ENOENT; return cookie | ((u64)mss << 32); #else return -EOPNOTSUPP; #endif /* CONFIG_SYN_COOKIES */ } static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .func = bpf_tcp_gen_syncookie, .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) return -ESOCKTNOSUPPORT; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_pfree; return 0; } static const struct bpf_func_proto bpf_sk_assign_proto = { .func = bpf_sk_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, u8 search_kind, const u8 *magic, u8 magic_len, bool *eol) { u8 kind, kind_len; *eol = false; while (op < opend) { kind = op[0]; if (kind == TCPOPT_EOL) { *eol = true; return ERR_PTR(-ENOMSG); } else if (kind == TCPOPT_NOP) { op++; continue; } if (opend - op < 2 || opend - op < op[1] || op[1] < 2) /* Something is wrong in the received header. * Follow the TCP stack's tcp_parse_options() * and just bail here. */ return ERR_PTR(-EFAULT); kind_len = op[1]; if (search_kind == kind) { if (!magic_len) return op; if (magic_len > kind_len - 2) return ERR_PTR(-ENOMSG); if (!memcmp(&op[2], magic, magic_len)) return op; } op += kind_len; } return ERR_PTR(-ENOMSG); } BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, void *, search_res, u32, len, u64, flags) { bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; const u8 *op, *opend, *magic, *search = search_res; u8 search_kind, search_len, copy_len, magic_len; int ret; /* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also. */ if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) return -EINVAL; search_kind = search[0]; search_len = search[1]; if (search_len > len || search_kind == TCPOPT_NOP || search_kind == TCPOPT_EOL) return -EINVAL; if (search_kind == TCPOPT_EXP || search_kind == 253) { /* 16 or 32 bit magic. +2 for kind and kind length */ if (search_len != 4 && search_len != 6) return -EINVAL; magic = &search[2]; magic_len = search_len - 2; } else { if (search_len) return -EINVAL; magic = NULL; magic_len = 0; } if (load_syn) { ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); if (ret < 0) return ret; opend = op + ret; op += sizeof(struct tcphdr); } else { if (!bpf_sock->skb || bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) /* This bpf_sock->op cannot call this helper */ return -EPERM; opend = bpf_sock->skb_data_end; op = bpf_sock->skb->data + sizeof(struct tcphdr); } op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, &eol); if (IS_ERR(op)) return PTR_ERR(op); copy_len = op[1]; ret = copy_len; if (copy_len > len) { ret = -ENOSPC; copy_len = len; } memcpy(search_res, op, copy_len); return ret; } static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { .func = bpf_sock_ops_load_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, const void *, from, u32, len, u64, flags) { u8 new_kind, new_kind_len, magic_len = 0, *opend; const u8 *op, *new_op, *magic = NULL; struct sk_buff *skb; bool eol; if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) return -EPERM; if (len < 2 || flags) return -EINVAL; new_op = from; new_kind = new_op[0]; new_kind_len = new_op[1]; if (new_kind_len > len || new_kind == TCPOPT_NOP || new_kind == TCPOPT_EOL) return -EINVAL; if (new_kind_len > bpf_sock->remaining_opt_len) return -ENOSPC; /* 253 is another experimental kind */ if (new_kind == TCPOPT_EXP || new_kind == 253) { if (new_kind_len < 4) return -EINVAL; /* Match for the 2 byte magic also. * RFC 6994: the magic could be 2 or 4 bytes. * Hence, matching by 2 byte only is on the * conservative side but it is the right * thing to do for the 'search-for-duplication' * purpose. */ magic = &new_op[2]; magic_len = 2; } /* Check for duplication */ skb = bpf_sock->skb; op = skb->data + sizeof(struct tcphdr); opend = bpf_sock->skb_data_end; op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, &eol); if (!IS_ERR(op)) return -EEXIST; if (PTR_ERR(op) != -ENOMSG) return PTR_ERR(op); if (eol) /* The option has been ended. Treat it as no more * header option can be written. */ return -ENOSPC; /* No duplication found. Store the header option. */ memcpy(opend, from, new_kind_len); bpf_sock->remaining_opt_len -= new_kind_len; bpf_sock->skb_data_end += new_kind_len; return 0; } static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { .func = bpf_sock_ops_store_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, u32, len, u64, flags) { if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) return -EPERM; if (flags || len < 2) return -EINVAL; if (len > bpf_sock->remaining_opt_len) return -ENOSPC; bpf_sock->remaining_opt_len -= len; return 0; } static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .func = bpf_sock_ops_reserve_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) { if (func == bpf_skb_vlan_push || func == bpf_skb_vlan_pop || func == bpf_skb_store_bytes || func == bpf_skb_change_proto || func == bpf_skb_change_head || func == sk_skb_change_head || func == bpf_skb_change_tail || func == sk_skb_change_tail || func == bpf_skb_adjust_room || func == sk_skb_adjust_room || func == bpf_skb_pull_data || func == sk_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || func == bpf_xdp_adjust_head || func == bpf_xdp_adjust_meta || func == bpf_msg_pull_data || func == bpf_msg_push_data || func == bpf_msg_pop_data || func == bpf_xdp_adjust_tail || #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) func == bpf_lwt_seg6_store_bytes || func == bpf_lwt_seg6_adjust_srh || func == bpf_lwt_seg6_action || #endif #ifdef CONFIG_INET func == bpf_sock_ops_store_hdr_opt || #endif func == bpf_lwt_in_push_encap || func == bpf_lwt_xmit_push_encap) return true; return false; } const struct bpf_func_proto bpf_event_output_data_proto __weak; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { /* inet and inet6 sockets are created in a process * context so there is always a valid uid/gid */ case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; #endif case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; default: return bpf_base_func_proto(func_id); } } static const struct bpf_func_proto * sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { /* inet and inet6 sockets are created in a process * context so there is always a valid uid/gid */ case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_bind: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_bind_proto; default: return NULL; } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_addr_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sock_addr_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_sock_addr_setsockopt_proto; default: return NULL; } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_sock_addr_getsockopt_proto; default: return NULL; } default: return bpf_sk_base_func_proto(func_id); } } static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: return bpf_sk_base_func_proto(func_id); } } const struct bpf_func_proto bpf_sk_storage_get_proto __weak; const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; case BPF_FUNC_sk_cgroup_id: return &bpf_sk_cgroup_id_proto; case BPF_FUNC_sk_ancestor_cgroup_id: return &bpf_sk_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif default: return sk_filter_func_proto(func_id, prog); } } static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_skb_vlan_push: return &bpf_skb_vlan_push_proto; case BPF_FUNC_skb_vlan_pop: return &bpf_skb_vlan_pop_proto; case BPF_FUNC_skb_change_proto: return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; case BPF_FUNC_skb_adjust_room: return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_redirect_neigh: return &bpf_redirect_neigh_proto; case BPF_FUNC_redirect_peer: return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_set_hash: return &bpf_set_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_skb_cgroup_classid: return &bpf_skb_cgroup_classid_proto; #endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; #endif default: return bpf_sk_base_func_proto(func_id); } } static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; case BPF_FUNC_xdp_adjust_meta: return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; case BPF_FUNC_sk_lookup_tcp: return &bpf_xdp_sk_lookup_tcp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #endif default: return bpf_sk_base_func_proto(func_id); } } const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sock_ops_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sock_ops_getsockopt_proto; case BPF_FUNC_sock_ops_cb_flags_set: return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; case BPF_FUNC_sock_hash_update: return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET case BPF_FUNC_load_hdr_opt: return &bpf_sock_ops_load_hdr_opt_proto; case BPF_FUNC_store_hdr_opt: return &bpf_sock_ops_store_hdr_opt_proto; case BPF_FUNC_reserve_hdr_opt: return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: return bpf_sk_base_func_proto(func_id); } } const struct bpf_func_proto bpf_msg_redirect_map_proto __weak; const struct bpf_func_proto bpf_msg_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_msg_redirect_map: return &bpf_msg_redirect_map_proto; case BPF_FUNC_msg_redirect_hash: return &bpf_msg_redirect_hash_proto; case BPF_FUNC_msg_apply_bytes: return &bpf_msg_apply_bytes_proto; case BPF_FUNC_msg_cork_bytes: return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; case BPF_FUNC_msg_push_data: return &bpf_msg_push_data_proto; case BPF_FUNC_msg_pop_data: return &bpf_msg_pop_data_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; #endif default: return bpf_sk_base_func_proto(func_id); } } const struct bpf_func_proto bpf_sk_redirect_map_proto __weak; const struct bpf_func_proto bpf_sk_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; case BPF_FUNC_skb_adjust_room: return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_sk_redirect_map: return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; #endif default: return bpf_sk_base_func_proto(func_id); } } static const struct bpf_func_proto * flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: return bpf_sk_base_func_proto(func_id); } } static const struct bpf_func_proto * lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: return bpf_sk_base_func_proto(func_id); } } static const struct bpf_func_proto * lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_lwt_push_encap: return &bpf_lwt_in_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_lwt_push_encap: return &bpf_lwt_xmit_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; #endif default: return lwt_out_func_proto(func_id, prog); } } static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, sk): if (type == BPF_WRITE || size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { if (size != size_default) return false; } else { bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } } return true; } static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool cg_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (!bpf_capable()) return false; break; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): if (!bpf_capable()) return false; break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } /* Attach type specific accesses */ static bool __sock_filter_check_attach_type(int off, enum bpf_access_type access_type, enum bpf_attach_type attach_type) { switch (off) { case offsetof(struct bpf_sock, bound_dev_if): case offsetof(struct bpf_sock, mark): case offsetof(struct bpf_sock, priority): switch (attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: goto full_access; default: return false; } case bpf_ctx_range(struct bpf_sock, src_ip4): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): switch (attach_type) { case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range(struct bpf_sock, src_port): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } } read_only: return access_type == BPF_READ; full_access: return true; } bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range_till(struct bpf_sock, type, priority): return false; default: return bpf_sock_is_valid_access(off, size, type, info); } } bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_sock, state): case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): case bpf_ctx_range(struct bpf_sock, dst_ip4): case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock, dst_port): field_size = size == size_default ? size_default : sizeof_field(struct bpf_sock, dst_port); bpf_ctx_record_field_size(info, field_size); return bpf_ctx_narrow_access_ok(off, size, field_size); case offsetofend(struct bpf_sock, dst_port) ... offsetof(struct bpf_sock, dst_ip4) - 1: return false; } return size == size_default; } static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_sock_is_valid_access(off, size, type, info)) return false; return __sock_filter_check_attach_type(off, type, prog->expected_attach_type); } static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Neither direct read nor direct write requires any preliminary * action. */ return 0; } static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { struct bpf_insn *insn = insn_buf; if (!direct_write) return 0; /* if (!skb->cloned) * goto start; * * (Fast-path, otherwise approximation that we might be * a clone, do the rest in helper.) */ *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET()); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); /* ret = bpf_skb_pull_data(skb, 0); */ *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_pull_data); /* if (!ret) * goto restore; * return TC_ACT_SHOT; */ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, drop_verdict); *insn++ = BPF_EXIT_INSN(); /* restore: */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); /* start: */ *insn++ = prog->insnsi[0]; return insn - insn_buf; } static int bpf_gen_ld_abs(const struct bpf_insn *orig, struct bpf_insn *insn_buf) { bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } /* We're guaranteed here that CTX is in R6. */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); break; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); *insn++ = BPF_EXIT_INSN(); return insn - insn_buf; } static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, TC_ACT_SHOT); } static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, queue_mapping): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) return false; if (off % size != 0) return false; if (size != sizeof(__u32)) return false; return true; } static bool xdp_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (prog->expected_attach_type != BPF_XDP_DEVMAP) { switch (off) { case offsetof(struct xdp_md, egress_ifindex): return false; } } if (type == BPF_WRITE) { if (bpf_prog_is_dev_bound(prog->aux)) { switch (off) { case offsetof(struct xdp_md, rx_queue_index): return __is_valid_xdp_access(off, size); } } return false; } switch (off) { case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; case offsetof(struct xdp_md, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return __is_valid_xdp_access(off, size); } void bpf_warn_invalid_xdp_action(u32 act) { const u32 act_max = XDP_REDIRECT; pr_warn_once("%s XDP return value %u, expect packet loss!\n", act > act_max ? "Illegal" : "Driver unsupported", act); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_addr)) return false; if (off % size != 0) return false; /* Disallow access to IPv6 fields from IPv4 contex and vise * versa. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP6_RECVMSG: break; default: return false; } break; case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; } break; } switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, user_port): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (size != size_default) return false; } break; case bpf_ctx_range_ptr(struct bpf_sock_addr, sk): if (type != BPF_READ) return false; if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct bpf_sock_addr, user_family): case bpf_ctx_range(struct bpf_sock_addr, family): case bpf_ctx_range(struct bpf_sock_addr, type): case bpf_ctx_range(struct bpf_sock_addr, protocol): if (type != BPF_READ) return false; if (size != size_default) return false; break; default: return false; } return true; } static bool sock_ops_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_ops)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sock_ops, reply): case offsetof(struct bpf_sock_ops, sk_txhash): if (size != size_default) return false; break; default: return false; } } else { switch (off) { case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received, bytes_acked): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); default: if (size != size_default) return false; break; } } return true; } static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, SK_DROP); } static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, mark): return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool sk_msg_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) return false; if (off % size != 0) return false; switch (off) { case bpf_ctx_range_ptr(struct sk_msg_md, data): info->reg_type = PTR_TO_PACKET; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, data_end): info->reg_type = PTR_TO_PACKET_END; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct sk_msg_md, family): case bpf_ctx_range(struct sk_msg_md, remote_ip4): case bpf_ctx_range(struct sk_msg_md, local_ip4): case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct sk_msg_md, remote_port): case bpf_ctx_range(struct sk_msg_md, local_port): case bpf_ctx_range(struct sk_msg_md, size): if (size != sizeof(__u32)) return false; break; default: return false; } return true; } static bool flow_dissector_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): if (size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_FLOW_KEYS; return true; default: return false; } } static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data)); break; case offsetof(struct __sk_buff, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data_end)); break; case offsetof(struct __sk_buff, flow_keys): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, flow_keys)); break; } return insn - insn_buf; } static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), si->dst_reg, si->src_reg, offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), si->dst_reg, si->src_reg, offsetof(struct sk_buff, end)); #endif return insn; } static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, len): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, len, 4, target_size)); break; case offsetof(struct __sk_buff, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, protocol, 2, target_size)); break; case offsetof(struct __sk_buff, vlan_proto): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_proto, 2, target_size)); break; case offsetof(struct __sk_buff, priority): if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, priority, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, priority, 4, target_size)); break; case offsetof(struct __sk_buff, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, skb_iif, 4, target_size)); break; case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; case offsetof(struct __sk_buff, hash): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, hash, 4, target_size)); break; case offsetof(struct __sk_buff, mark): if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, mark, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, mark, 4, target_size)); break; case offsetof(struct __sk_buff, pkt_type): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, PKT_TYPE_OFFSET()); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); #endif break; case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, queue_mapping, 2, target_size)); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, queue_mapping, 2, target_size)); } break; case offsetof(struct __sk_buff, vlan_present): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, PKT_VLAN_PRESENT_OFFSET()); if (PKT_VLAN_PRESENT_BIT) *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT); if (PKT_VLAN_PRESENT_BIT < 7) *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_tci, 2, target_size)); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_classid): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, tc_classid); *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg, off); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->src_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct __sk_buff, data_meta): off = si->off; off -= offsetof(struct __sk_buff, data_meta); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_meta); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_end); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, napi_id): #if defined(CONFIG_NET_RX_BUSY_POLL) *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, napi_id, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_family, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_daddr, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, 4, target_size)); break; case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_dport, 2, target_size)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct __sk_buff, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_num, 2, target_size)); break; case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tstamp, 8, target_size)); else *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tstamp, 8, target_size)); break; case offsetof(struct __sk_buff, gso_segs): insn = bpf_convert_shinfo_access(si, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_segs, 2, target_size)); break; case offsetof(struct __sk_buff, gso_size): insn = bpf_convert_shinfo_access(si, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_size, 2, target_size)); break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, pkt_len); *target_size = 4; *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; } return insn - insn_buf; } u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); break; case offsetof(struct bpf_sock, mark): BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_mark)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_mark)); break; case offsetof(struct bpf_sock, priority): BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_priority)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_priority)); break; case offsetof(struct bpf_sock, family): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_family), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, sizeof_field(struct sock_common, skc_family), target_size)); break; case offsetof(struct bpf_sock, type): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_type), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_type, sizeof_field(struct sock, sk_type), target_size)); break; case offsetof(struct bpf_sock, protocol): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_protocol), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_protocol, sizeof_field(struct sock, sk_protocol), target_size)); break; case offsetof(struct bpf_sock, src_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; case offsetof(struct bpf_sock, dst_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, sizeof_field(struct sock_common, skc_daddr), target_size)); break; case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, src_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else (void)off; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, dst_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); *target_size = 4; #endif break; case offsetof(struct bpf_sock, src_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, sizeof_field(struct sock_common, skc_num), target_size)); break; case offsetof(struct bpf_sock, dst_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, sizeof_field(struct sock_common, skc_dport), target_size)); break; case offsetof(struct bpf_sock, state): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, sizeof_field(struct sock_common, skc_state), target_size)); break; case offsetof(struct bpf_sock, rx_queue_mapping): #ifdef CONFIG_XPS *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_rx_queue_mapping, sizeof_field(struct sock, sk_rx_queue_mapping), target_size)); *insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); #else *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); *target_size = 2; #endif break; } return insn - insn_buf; } static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 xdp_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct xdp_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_meta): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_meta)); break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_end)); break; case offsetof(struct xdp_md, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; case offsetof(struct xdp_md, rx_queue_index): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, queue_index)); break; case offsetof(struct xdp_md, egress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, txq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_txq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; } return insn - insn_buf; } /* SOCK_ADDR_LOAD_NESTED_FIELD() loads Nested Field S.F.NF where S is type of * context Structure, F is Field in context structure that contains a pointer * to Nested Structure of type NS that has the field NF. * * SIZE encodes the load size (BPF_B, BPF_H, etc). It's up to caller to make * sure that SIZE is not greater than actual size of S.F.NF. * * If offset OFF is provided, the load happens from that offset relative to * offset of NF. */ #define SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF) \ do { \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), si->dst_reg, \ si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) #define SOCK_ADDR_LOAD_NESTED_FIELD(S, NS, F, NF) \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, \ BPF_FIELD_SIZEOF(NS, NF), 0) /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation. * * In addition it uses Temporary Field TF (member of struct S) as the 3rd * "register" since two registers available in convert_ctx_access are not * enough: we can't override neither SRC, since it contains value to store, nor * DST since it contains pointer to context that may be used by later * instructions. But we need a temporary place to save pointer to nested * structure whose field we want to store to. */ #define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF) \ do { \ int tmp_reg = BPF_REG_9; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, tmp_reg, \ offsetof(S, TF)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ offsetof(S, TF)); \ } while (0) #define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF, \ TF) \ do { \ if (type == BPF_WRITE) { \ SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, \ OFF, TF); \ } else { \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( \ S, NS, F, NF, SIZE, OFF); \ } \ } while (0) #define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(S, NS, F, NF, TF) \ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( \ S, NS, F, NF, BPF_FIELD_SIZEOF(NS, NF), 0, TF) static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port); struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sock_addr, user_family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr, uaddr, sa_family); break; case offsetof(struct bpf_sock_addr, user_ip4): SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in, uaddr, sin_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, user_ip6[0]); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_addr.s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, user_port): /* To get port we need to know sa_family first and then treat * sockaddr as either sockaddr_in or sockaddr_in6. * Though we can simplify since port field has same offset and * size in both structures. * Here we check this invariant and use just one of the * structures if it's true. */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != sizeof_field(struct sockaddr_in6, sin6_port)); /* Account for sin6_port being smaller than user_port. */ port_size = min(port_size, BPF_LDST_BYTES(si)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg); break; case offsetof(struct bpf_sock_addr, family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_family); break; case offsetof(struct bpf_sock_addr, type): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): /* Treat t_ctx as struct in_addr for msg_src_ip4. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in_addr, t_ctx, s_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_addr_kern, sk)); break; } return insn - insn_buf; } static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_SK() \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) /* Helper macro for adding write access to tcp_sock or sock fields. * The macro is called with two registers, dst_reg which contains a pointer * to ctx (context) and src_reg which contains the value that should be * stored. However, we need an additional register since we cannot overwrite * dst_reg because it may be used later in the program. * Instead we "borrow" one of the other register. We first save its value * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore * it at the end of the macro. */ #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD), \ reg, si->src_reg, \ offsetof(OBJ, OBJ_FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } while (0) #define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ do { \ if (TYPE == BPF_WRITE) \ SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ else \ SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0) if (insn > insn_buf) return insn - insn_buf; switch (si->off) { case offsetof(struct bpf_sock_ops, op): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, op), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, op)); break; case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, replylong[0]); off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, off); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct bpf_sock_ops, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct bpf_sock_ops, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct bpf_sock_ops, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct bpf_sock_ops, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct bpf_sock_ops, is_fullsock): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, is_fullsock), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, is_fullsock)); break; case offsetof(struct bpf_sock_ops, state): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_state)); break; case offsetof(struct bpf_sock_ops, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags, struct tcp_sock); break; case offsetof(struct bpf_sock_ops, sk_txhash): SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; case offsetof(struct bpf_sock_ops, snd_cwnd): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); break; case offsetof(struct bpf_sock_ops, srtt_us): SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); break; case offsetof(struct bpf_sock_ops, snd_ssthresh): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); break; case offsetof(struct bpf_sock_ops, rcv_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); break; case offsetof(struct bpf_sock_ops, snd_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); break; case offsetof(struct bpf_sock_ops, snd_una): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); break; case offsetof(struct bpf_sock_ops, mss_cache): SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); break; case offsetof(struct bpf_sock_ops, ecn_flags): SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); break; case offsetof(struct bpf_sock_ops, rate_delivered): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); break; case offsetof(struct bpf_sock_ops, rate_interval_us): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); break; case offsetof(struct bpf_sock_ops, packets_out): SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); break; case offsetof(struct bpf_sock_ops, retrans_out): SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); break; case offsetof(struct bpf_sock_ops, total_retrans): SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); break; case offsetof(struct bpf_sock_ops, segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); break; case offsetof(struct bpf_sock_ops, data_segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); break; case offsetof(struct bpf_sock_ops, segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); break; case offsetof(struct bpf_sock_ops, data_segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); break; case offsetof(struct bpf_sock_ops, lost_out): SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); break; case offsetof(struct bpf_sock_ops, sacked_out): SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); break; case offsetof(struct bpf_sock_ops, bytes_received): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); break; case offsetof(struct bpf_sock_ops, bytes_acked): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; case offsetof(struct bpf_sock_ops, skb_data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb_data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb_data_end)); break; case offsetof(struct bpf_sock_ops, skb_data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct bpf_sock_ops, skb_len): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, len)); break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): off = offsetof(struct sk_buff, cb); off += offsetof(struct tcp_skb_cb, tcp_flags); *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, tcp_flags), si->dst_reg, si->dst_reg, off); break; } return insn - insn_buf; } static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); off += offsetof(struct sk_buff, cb); off += offsetof(struct tcp_skb_cb, bpf.data_end); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct sk_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #if IS_ENABLED(CONFIG_IPV6) int off; #endif /* convert ctx uses the fact sg element is first in struct */ BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0); switch (si->off) { case offsetof(struct sk_msg_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data)); break; case offsetof(struct sk_msg_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data_end), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct sk_msg_md, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct sk_msg_md, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct sk_msg_md, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct sk_msg_md, size): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size), si->dst_reg, si->src_reg, offsetof(struct sk_msg_sg, size)); break; case offsetof(struct sk_msg_md, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, }; const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = cg_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_in_verifier_ops = { .get_func_proto = lwt_in_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_in_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_out_verifier_ops = { .get_func_proto = lwt_out_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_out_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, }; const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { .get_func_proto = lwt_seg6local_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_seg6local_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { }; const struct bpf_verifier_ops cg_sock_addr_verifier_ops = { .get_func_proto = sock_addr_func_proto, .is_valid_access = sock_addr_is_valid_access, .convert_ctx_access = sock_addr_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_addr_prog_ops = { }; const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; const struct bpf_prog_ops sock_ops_prog_ops = { }; const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; const struct bpf_prog_ops sk_skb_prog_ops = { }; const struct bpf_verifier_ops sk_msg_verifier_ops = { .get_func_proto = sk_msg_func_proto, .is_valid_access = sk_msg_is_valid_access, .convert_ctx_access = sk_msg_convert_ctx_access, .gen_prologue = bpf_noop_prologue, }; const struct bpf_prog_ops sk_msg_prog_ops = { }; const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; struct sk_filter *filter; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); ret = 0; } return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; int ret = 0; lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (!filter) goto out; /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. eBPF programs that * have no original program cannot be dumped through this. */ ret = -EACCES; fprog = filter->prog->orig_prog; if (!fprog) goto out; ret = fprog->len; if (!len) /* User space only enquires number of filter blocks. */ goto out; ret = -EINVAL; if (len < fprog->len) goto out; ret = -EFAULT; if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number * of filter blocks. */ ret = fprog->len; out: release_sock(sk); return ret; } #ifdef CONFIG_INET static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; reuse_kern->bind_inany = reuse->bind_inany; } struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); action = BPF_PROG_RUN(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; else return ERR_PTR(-ECONNREFUSED); } BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. * * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ err = is_sockarray ? -ENOENT : -EINVAL; goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) { err = -EPROTOTYPE; } else if (sk->sk_family != selected_sk->sk_family) { err = -EAFNOSUPPORT; } else { /* Catch all. Likely bound to a different sockaddr. */ err = -EBADFD; } goto error; } reuse_kern->selected_sk = selected_sk; return 0; error: /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ if (sk_is_refcounted(selected_sk)) sock_put(selected_sk); return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { .func = sk_select_reuseport, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(sk_reuseport_load_bytes, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len) { return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len); } static const struct bpf_func_proto sk_reuseport_load_bytes_proto = { .func = sk_reuseport_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(sk_reuseport_load_bytes_relative, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len, u32, start_header) { return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to, len, start_header); } static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = { .func = sk_reuseport_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_reuseport_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sk_select_reuseport: return &sk_select_reuseport_proto; case BPF_FUNC_skb_load_bytes: return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; default: return bpf_base_func_proto(func_id); } } static bool sk_reuseport_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const u32 size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct sk_reuseport_md) || off % size || type != BPF_READ) return false; switch (off) { case offsetof(struct sk_reuseport_md, data): info->reg_type = PTR_TO_PACKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, data_end): info->reg_type = PTR_TO_PACKET_END; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, hash): return size == size_default; /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) return false; fallthrough; case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): case bpf_ctx_range(struct sk_reuseport_md, bind_inany): case bpf_ctx_range(struct sk_reuseport_md, len): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); default: return false; } } #define SK_REUSEPORT_LOAD_FIELD(F) ({ \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) #define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sk_buff, \ skb, \ SKB_FIELD) #define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sock, \ sk, \ SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct sk_reuseport_md, data): SK_REUSEPORT_LOAD_SKB_FIELD(data); break; case offsetof(struct sk_reuseport_md, len): SK_REUSEPORT_LOAD_SKB_FIELD(len); break; case offsetof(struct sk_reuseport_md, eth_protocol): SK_REUSEPORT_LOAD_SKB_FIELD(protocol); break; case offsetof(struct sk_reuseport_md, ip_protocol): SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): SK_REUSEPORT_LOAD_FIELD(data_end); break; case offsetof(struct sk_reuseport_md, hash): SK_REUSEPORT_LOAD_FIELD(hash); break; case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_reuseport_verifier_ops = { .get_func_proto = sk_reuseport_func_proto, .is_valid_access = sk_reuseport_is_valid_access, .convert_ctx_access = sk_reuseport_convert_ctx_access, }; const struct bpf_prog_ops sk_reuseport_prog_ops = { }; DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled); EXPORT_SYMBOL(bpf_sk_lookup_enabled); BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, struct sock *, sk, u64, flags) { if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE | BPF_SK_LOOKUP_F_NO_REUSEPORT))) return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED)) return -ESOCKTNOSUPPORT; /* reject connected sockets */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) return -EPROTOTYPE; if (sk && sk->sk_family != ctx->family && (sk->sk_family == AF_INET || ipv6_only_sock(sk))) return -EAFNOSUPPORT; if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE)) return -EEXIST; /* Select socket as lookup result */ ctx->selected_sk = sk; ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT; return 0; } static const struct bpf_func_proto bpf_sk_lookup_assign_proto = { .func = bpf_sk_lookup_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_SOCKET_OR_NULL, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_assign: return &bpf_sk_lookup_assign_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: return bpf_sk_base_func_proto(func_id); } } static bool sk_lookup_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sk_lookup)) return false; if (off % size != 0) return false; if (type != BPF_READ) return false; switch (off) { case bpf_ctx_range_ptr(struct bpf_sk_lookup, sk): info->reg_type = PTR_TO_SOCKET_OR_NULL; return size == sizeof(__u64); case bpf_ctx_range(struct bpf_sk_lookup, family): case bpf_ctx_range(struct bpf_sk_lookup, protocol): case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4): case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, remote_port): case bpf_ctx_range(struct bpf_sk_lookup, local_port): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); default: return false; } } static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sk_lookup, sk): *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, selected_sk)); break; case offsetof(struct bpf_sk_lookup, family): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, family, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, protocol, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, remote_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.saddr, 4, target_size)); break; case offsetof(struct bpf_sk_lookup, local_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.daddr, 4, target_size)); break; case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.saddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, local_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.daddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case offsetof(struct bpf_sk_lookup, remote_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, sport, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, local_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; } return insn - insn_buf; } const struct bpf_prog_ops sk_lookup_prog_ops = { .test_run = bpf_prog_test_run_sk_lookup, }; const struct bpf_verifier_ops sk_lookup_verifier_ops = { .get_func_proto = sk_lookup_func_proto, .is_valid_access = sk_lookup_is_valid_access, .convert_ctx_access = sk_lookup_convert_ctx_access, }; #endif /* CONFIG_INET */ DEFINE_BPF_DISPATCHER(xdp) void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } #ifdef CONFIG_DEBUG_INFO_BTF BTF_ID_LIST_GLOBAL(btf_sock_ids) #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) BTF_SOCK_TYPE_xxx #undef BTF_SOCK_TYPE #else u32 btf_sock_ids[MAX_BTF_SOCK_TYPE]; #endif BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { /* BTF types for tcp_timewait_sock and inet_timewait_sock are not * generated if CONFIG_INET=n. Trigger an explicit generation here. */ BTF_TYPE_EMIT(struct inet_timewait_sock); BTF_TYPE_EMIT(struct tcp_timewait_sock); #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) { /* udp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id) { const struct bpf_func_proto *func; switch (func_id) { case BPF_FUNC_skc_to_tcp6_sock: func = &bpf_skc_to_tcp6_sock_proto; break; case BPF_FUNC_skc_to_tcp_sock: func = &bpf_skc_to_tcp_sock_proto; break; case BPF_FUNC_skc_to_tcp_timewait_sock: func = &bpf_skc_to_tcp_timewait_sock_proto; break; case BPF_FUNC_skc_to_tcp_request_sock: func = &bpf_skc_to_tcp_request_sock_proto; break; case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; default: return bpf_base_func_proto(func_id); } if (!perfmon_capable()) return NULL; return func; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/integrity.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsnotify.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/msg.h> #include <net/flow.h> #define MAX_LSM_EVM_XATTR 2 /* How many LSMs were built into the kernel? */ #define LSM_COUNT (__end_lsm_info - __start_lsm_info) /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_XEN_USER_ACTIONS] = "Xen guest user action", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; struct security_hook_heads security_hook_heads __lsm_ro_after_init; static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; static struct kmem_cache *lsm_inode_cache; char *lsm_names; static struct lsm_blob_sizes blob_sizes __lsm_ro_after_init; /* Boot-time LSM user choice */ static __initdata const char *chosen_lsm_order; static __initdata const char *chosen_major_lsm; static __initconst const char * const builtin_lsm_order = CONFIG_LSM; /* Ordered list of LSMs to initialize. */ static __initdata struct lsm_info **ordered_lsms; static __initdata struct lsm_info *exclusive; static __initdata bool debug; #define init_debug(...) \ do { \ if (debug) \ pr_info(__VA_ARGS__); \ } while (0) static bool __init is_enabled(struct lsm_info *lsm) { if (!lsm->enabled) return false; return *lsm->enabled; } /* Mark an LSM's enabled flag. */ static int lsm_enabled_true __initdata = 1; static int lsm_enabled_false __initdata = 0; static void __init set_enabled(struct lsm_info *lsm, bool enabled) { /* * When an LSM hasn't configured an enable variable, we can use * a hard-coded location for storing the default enabled state. */ if (!lsm->enabled) { if (enabled) lsm->enabled = &lsm_enabled_true; else lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_true) { if (!enabled) lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_false) { if (enabled) lsm->enabled = &lsm_enabled_true; } else { *lsm->enabled = enabled; } } /* Is an LSM already listed in the ordered LSMs list? */ static bool __init exists_ordered_lsm(struct lsm_info *lsm) { struct lsm_info **check; for (check = ordered_lsms; *check; check++) if (*check == lsm) return true; return false; } /* Append an LSM to the list of ordered LSMs to initialize. */ static int last_lsm __initdata; static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) { /* Ignore duplicate selections. */ if (exists_ordered_lsm(lsm)) return; if (WARN(last_lsm == LSM_COUNT, "%s: out of LSM slots!?\n", from)) return; /* Enable this LSM, if it is not already set. */ if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; ordered_lsms[last_lsm++] = lsm; init_debug("%s ordering: %s (%sabled)\n", from, lsm->name, is_enabled(lsm) ? "en" : "dis"); } /* Is an LSM allowed to be initialized? */ static bool __init lsm_allowed(struct lsm_info *lsm) { /* Skip if the LSM is disabled. */ if (!is_enabled(lsm)) return false; /* Not allowed if another exclusive LSM already initialized. */ if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) { init_debug("exclusive disabled: %s\n", lsm->name); return false; } return true; } static void __init lsm_set_blob_size(int *need, int *lbs) { int offset; if (*need > 0) { offset = *lbs; *lbs += *need; *need = offset; } } static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) { if (!needed) return; lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); /* * The inode blob gets an rcu_head in addition to * what the modules might need. */ if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); } /* Prepare LSM for initialization. */ static void __init prepare_lsm(struct lsm_info *lsm) { int enabled = lsm_allowed(lsm); /* Record enablement (to handle any following exclusive LSMs). */ set_enabled(lsm, enabled); /* If enabled, do pre-initialization work. */ if (enabled) { if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) { exclusive = lsm; init_debug("exclusive chosen: %s\n", lsm->name); } lsm_set_blob_sizes(lsm->blobs); } } /* Initialize a given LSM, if it is enabled. */ static void __init initialize_lsm(struct lsm_info *lsm) { if (is_enabled(lsm)) { int ret; init_debug("initializing %s\n", lsm->name); ret = lsm->init(); WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); } } /* Populate ordered LSMs list from comma-separated LSM name list. */ static void __init ordered_lsm_parse(const char *order, const char *origin) { struct lsm_info *lsm; char *sep, *name, *next; /* LSM_ORDER_FIRST is always first. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_FIRST) append_ordered_lsm(lsm, "first"); } /* Process "security=", if given. */ if (chosen_major_lsm) { struct lsm_info *major; /* * To match the original "security=" behavior, this * explicitly does NOT fallback to another Legacy Major * if the selected one was separately disabled: disable * all non-matching Legacy Major LSMs. */ for (major = __start_lsm_info; major < __end_lsm_info; major++) { if ((major->flags & LSM_FLAG_LEGACY_MAJOR) && strcmp(major->name, chosen_major_lsm) != 0) { set_enabled(major, false); init_debug("security=%s disabled: %s\n", chosen_major_lsm, major->name); } } } sep = kstrdup(order, GFP_KERNEL); next = sep; /* Walk the list, looking for matching LSMs. */ while ((name = strsep(&next, ",")) != NULL) { bool found = false; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_MUTABLE && strcmp(lsm->name, name) == 0) { append_ordered_lsm(lsm, origin); found = true; } } if (!found) init_debug("%s ignored: %s\n", origin, name); } /* Process "security=", if given. */ if (chosen_major_lsm) { for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; if (strcmp(lsm->name, chosen_major_lsm) == 0) append_ordered_lsm(lsm, "security="); } } /* Disable all LSMs not in the ordered list. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; set_enabled(lsm, false); init_debug("%s disabled: %s\n", origin, lsm->name); } kfree(sep); } static void __init lsm_early_cred(struct cred *cred); static void __init lsm_early_task(struct task_struct *task); static int lsm_append(const char *new, char **result); static void __init ordered_lsm_init(void) { struct lsm_info **lsm; ordered_lsms = kcalloc(LSM_COUNT + 1, sizeof(*ordered_lsms), GFP_KERNEL); if (chosen_lsm_order) { if (chosen_major_lsm) { pr_info("security= is ignored because it is superseded by lsm=\n"); chosen_major_lsm = NULL; } ordered_lsm_parse(chosen_lsm_order, "cmdline"); } else ordered_lsm_parse(builtin_lsm_order, "builtin"); for (lsm = ordered_lsms; *lsm; lsm++) prepare_lsm(*lsm); init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("task blob size = %d\n", blob_sizes.lbs_task); /* * Create any kmem_caches needed for blobs */ if (blob_sizes.lbs_file) lsm_file_cache = kmem_cache_create("lsm_file_cache", blob_sizes.lbs_file, 0, SLAB_PANIC, NULL); if (blob_sizes.lbs_inode) lsm_inode_cache = kmem_cache_create("lsm_inode_cache", blob_sizes.lbs_inode, 0, SLAB_PANIC, NULL); lsm_early_cred((struct cred *) current->cred); lsm_early_task(current); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); kfree(ordered_lsms); } int __init early_security_init(void) { int i; struct hlist_head *list = (struct hlist_head *) &security_hook_heads; struct lsm_info *lsm; for (i = 0; i < sizeof(security_hook_heads) / sizeof(struct hlist_head); i++) INIT_HLIST_HEAD(&list[i]); for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; prepare_lsm(lsm); initialize_lsm(lsm); } return 0; } /** * security_init - initializes the security framework * * This should be called early in the kernel initialization sequence. */ int __init security_init(void) { struct lsm_info *lsm; pr_info("Security Framework initializing\n"); /* * Append the names of the early LSM modules now that kmalloc() is * available */ for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (lsm->enabled) lsm_append(lsm->name, &lsm_names); } /* Load LSMs in specified order. */ ordered_lsm_init(); return 0; } /* Save user chosen LSM */ static int __init choose_major_lsm(char *str) { chosen_major_lsm = str; return 1; } __setup("security=", choose_major_lsm); /* Explicitly choose LSM initialization order. */ static int __init choose_lsm_order(char *str) { chosen_lsm_order = str; return 1; } __setup("lsm=", choose_lsm_order); /* Enable LSM order debugging. */ static int __init enable_debug(char *str) { debug = true; return 1; } __setup("lsm.debug", enable_debug); static bool match_last_lsm(const char *list, const char *lsm) { const char *last; if (WARN_ON(!list || !lsm)) return false; last = strrchr(list, ','); if (last) /* Pass the comma, strcmp() will check for '\0' */ last++; else last = list; return !strcmp(last, lsm); } static int lsm_append(const char *new, char **result) { char *cp; if (*result == NULL) { *result = kstrdup(new, GFP_KERNEL); if (*result == NULL) return -ENOMEM; } else { /* Check if it is the last registered name */ if (match_last_lsm(*result, new)) return 0; cp = kasprintf(GFP_KERNEL, "%s,%s", *result, new); if (cp == NULL) return -ENOMEM; kfree(*result); *result = cp; } return 0; } /** * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add * @count: the number of hooks to add * @lsm: the name of the security module * * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, char *lsm) { int i; for (i = 0; i < count; i++) { hooks[i].lsm = lsm; hlist_add_tail_rcu(&hooks[i].list, hooks[i].head); } /* * Don't try to append during early_security_init(), we'll come back * and fix this up afterwards. */ if (slab_is_available()) { if (lsm_append(lsm, &lsm_names) < 0) panic("%s - Cannot get early memory.\n", __func__); } } int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return blocking_notifier_call_chain(&blocking_lsm_notifier_chain, event, data); } EXPORT_SYMBOL(call_blocking_lsm_notifier); int register_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(register_blocking_lsm_notifier); int unregister_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(unregister_blocking_lsm_notifier); /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { if (blob_sizes.lbs_cred == 0) { cred->security = NULL; return 0; } cred->security = kzalloc(blob_sizes.lbs_cred, gfp); if (cred->security == NULL) return -ENOMEM; return 0; } /** * lsm_early_cred - during initialization allocate a composite cred blob * @cred: the cred that needs a blob * * Allocate the cred blob for all the modules */ static void __init lsm_early_cred(struct cred *cred) { int rc = lsm_cred_alloc(cred, GFP_KERNEL); if (rc) panic("%s: Early cred alloc failed.\n", __func__); } /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_inode_alloc(struct inode *inode) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, GFP_NOFS); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_task_alloc(struct task_struct *task) { if (blob_sizes.lbs_task == 0) { task->security = NULL; return 0; } task->security = kzalloc(blob_sizes.lbs_task, GFP_KERNEL); if (task->security == NULL) return -ENOMEM; return 0; } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { if (blob_sizes.lbs_ipc == 0) { kip->security = NULL; return 0; } kip->security = kzalloc(blob_sizes.lbs_ipc, GFP_KERNEL); if (kip->security == NULL) return -ENOMEM; return 0; } /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { if (blob_sizes.lbs_msg_msg == 0) { mp->security = NULL; return 0; } mp->security = kzalloc(blob_sizes.lbs_msg_msg, GFP_KERNEL); if (mp->security == NULL) return -ENOMEM; return 0; } /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules */ static void __init lsm_early_task(struct task_struct *task) { int rc = lsm_task_alloc(task); if (rc) panic("%s: Early task alloc failed.\n", __func__); } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define call_void_hook(FUNC, ...) \ do { \ struct security_hook_list *P; \ \ hlist_for_each_entry(P, &security_hook_heads.FUNC, list) \ P->hook.FUNC(__VA_ARGS__); \ } while (0) #define call_int_hook(FUNC, IRC, ...) ({ \ int RC = IRC; \ do { \ struct security_hook_list *P; \ \ hlist_for_each_entry(P, &security_hook_heads.FUNC, list) { \ RC = P->hook.FUNC(__VA_ARGS__); \ if (RC != 0) \ break; \ } \ } while (0); \ RC; \ }) /* Security operations */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, 0, mgr); } int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, 0, from, to); } int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, 0, from, to); } int security_binder_transfer_file(const struct cred *from, const struct cred *to, struct file *file) { return call_int_hook(binder_transfer_file, 0, from, to, file); } int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, 0, child, mode); } int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, 0, parent); } int security_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, 0, target, effective, inheritable, permitted); } int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, 0, new, old, effective, inheritable, permitted); } int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, 0, cred, ns, cap, opts); } int security_quotactl(int cmds, int type, int id, struct super_block *sb) { return call_int_hook(quotactl, 0, cmds, type, id, sb); } int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, 0, dentry); } int security_syslog(int type) { return call_int_hook(syslog, 0, type); } int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, 0, ts, tz); } int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct security_hook_list *hp; int cap_sys_admin = 1; int rc; /* * The module will respond with a positive value if * it thinks the __vm_enough_memory() call should be * made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module * thinks it should not be set it won't. */ hlist_for_each_entry(hp, &security_hook_heads.vm_enough_memory, list) { rc = hp->hook.vm_enough_memory(mm, pages); if (rc <= 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, 0, bprm); } int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { return call_int_hook(bprm_creds_from_file, 0, bprm, file); } int security_bprm_check(struct linux_binprm *bprm) { int ret; ret = call_int_hook(bprm_check_security, 0, bprm); if (ret) return ret; return ima_bprm_check(bprm); } void security_bprm_committing_creds(struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } void security_bprm_committed_creds(struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, 0, fc, src_fc); } int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct security_hook_list *hp; int trc; int rc = -ENOPARAM; hlist_for_each_entry(hp, &security_hook_heads.fs_context_parse_param, list) { trc = hp->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } int security_sb_alloc(struct super_block *sb) { return call_int_hook(sb_alloc_security, 0, sb); } void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); } void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, 0, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, 0, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); int security_sb_kern_mount(struct super_block *sb) { return call_int_hook(sb_kern_mount, 0, sb); } int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, 0, m, sb); } int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, 0, dentry); } int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, 0, dev_name, path, type, flags, data); } int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, 0, mnt, flags); } int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, 0, old_path, new_path); } int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_set_mnt_opts, mnt_opts ? -EOPNOTSUPP : 0, sb, mnt_opts, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_set_mnt_opts); int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, 0, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); int security_add_mnt_opt(const char *option, const char *val, int len, void **mnt_opts) { return call_int_hook(sb_add_mnt_opt, -EINVAL, option, val, len, mnt_opts); } EXPORT_SYMBOL(security_add_mnt_opt); int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, 0, from_path, to_path); } int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, 0, path, mask, obj_type); } int security_inode_alloc(struct inode *inode) { int rc = lsm_inode_alloc(inode); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, 0, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* * The rcu head is at the start of the inode blob */ kmem_cache_free(lsm_inode_cache, head); } void security_inode_free(struct inode *inode) { integrity_inode_free(inode); call_void_hook(inode_free_security, inode); /* * The inode may still be referenced in a path walk and * a call to security_inode_permission() can be made * after inode_free_security() is called. Ideally, the VFS * wouldn't do this, but fixing that is a much harder * job. For now, simply free the i_security via RCU, and * leave the current inode->i_security pointer intact. * The inode will be freed after the RCU grace period too. */ if (inode->i_security) call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, u32 *ctxlen) { return call_int_hook(dentry_init_security, -EOPNOTSUPP, dentry, mode, name, ctx, ctxlen); } EXPORT_SYMBOL(security_dentry_init_security); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, 0, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct xattr new_xattrs[MAX_LSM_EVM_XATTR + 1]; struct xattr *lsm_xattr, *evm_xattr, *xattr; int ret; if (unlikely(IS_PRIVATE(inode))) return 0; if (!initxattrs) return call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, NULL, NULL, NULL); memset(new_xattrs, 0, sizeof(new_xattrs)); lsm_xattr = new_xattrs; ret = call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, &lsm_xattr->name, &lsm_xattr->value, &lsm_xattr->value_len); if (ret) goto out; evm_xattr = lsm_xattr + 1; ret = evm_inode_init_security(inode, lsm_xattr, evm_xattr); if (ret) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (xattr = new_xattrs; xattr->value != NULL; xattr++) kfree(xattr->value); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) { if (unlikely(IS_PRIVATE(inode))) return -EOPNOTSUPP; return call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, name, value, len); } EXPORT_SYMBOL(security_old_inode_init_security); #ifdef CONFIG_SECURITY_PATH int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, 0, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, 0, dir, dentry, mode); } EXPORT_SYMBOL(security_path_mkdir); int security_path_rmdir(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_rmdir, 0, dir, dentry); } int security_path_unlink(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_unlink, 0, dir, dentry); } EXPORT_SYMBOL(security_path_unlink); int security_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_symlink, 0, dir, dentry, old_name); } int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry); } int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(path_rename, 0, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(path_rename, 0, old_dir, old_dentry, new_dir, new_dentry); } EXPORT_SYMBOL(security_path_rename); int security_path_truncate(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_truncate, 0, path); } int security_path_chmod(const struct path *path, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chmod, 0, path, mode); } int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chown, 0, path, uid, gid); } int security_path_chroot(const struct path *path) { return call_int_hook(path_chroot, 0, path); } #endif int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_create, 0, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_create); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(inode_link, 0, old_dentry, dir, new_dentry); } int security_inode_unlink(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_unlink, 0, dir, dentry); } int security_inode_symlink(struct inode *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_symlink, 0, dir, dentry, old_name); } int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mkdir, 0, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_mkdir); int security_inode_rmdir(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_rmdir, 0, dir, dentry); } int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mknod, 0, dir, dentry, mode, dev); } int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(inode_rename, 0, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(inode_rename, 0, old_dir, old_dentry, new_dir, new_dentry); } int security_inode_readlink(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_readlink, 0, dentry); } int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_follow_link, 0, dentry, inode, rcu); } int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_permission, 0, inode, mask); } int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; ret = call_int_hook(inode_setattr, 0, dentry, attr); if (ret) return ret; return evm_inode_setattr(dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); int security_inode_getattr(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(inode_getattr, 0, path); } int security_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ ret = call_int_hook(inode_setxattr, 1, dentry, name, value, size, flags); if (ret == 1) ret = cap_inode_setxattr(dentry, name, value, size, flags); if (ret) return ret; ret = ima_inode_setxattr(dentry, name, value, size); if (ret) return ret; return evm_inode_setxattr(dentry, name, value, size); } void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); evm_inode_post_setxattr(dentry, name, value, size); } int security_inode_getxattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_getxattr, 0, dentry, name); } int security_inode_listxattr(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_listxattr, 0, dentry); } int security_inode_removexattr(struct dentry *dentry, const char *name) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ ret = call_int_hook(inode_removexattr, 1, dentry, name); if (ret == 1) ret = cap_inode_removexattr(dentry, name); if (ret) return ret; ret = ima_inode_removexattr(dentry, name); if (ret) return ret; return evm_inode_removexattr(dentry, name); } int security_inode_need_killpriv(struct dentry *dentry) { return call_int_hook(inode_need_killpriv, 0, dentry); } int security_inode_killpriv(struct dentry *dentry) { return call_int_hook(inode_killpriv, 0, dentry); } int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { struct security_hook_list *hp; int rc; if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_getsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) { rc = hp->hook.inode_getsecurity(inode, name, buffer, alloc); if (rc != LSM_RET_DEFAULT(inode_getsecurity)) return rc; } return LSM_RET_DEFAULT(inode_getsecurity); } int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct security_hook_list *hp; int rc; if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_setsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_setsecurity, list) { rc = hp->hook.inode_setsecurity(inode, name, value, size, flags); if (rc != LSM_RET_DEFAULT(inode_setsecurity)) return rc; } return LSM_RET_DEFAULT(inode_setsecurity); } int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_listsecurity, 0, inode, buffer, buffer_size); } EXPORT_SYMBOL(security_inode_listsecurity); void security_inode_getsecid(struct inode *inode, u32 *secid) { call_void_hook(inode_getsecid, inode, secid); } int security_inode_copy_up(struct dentry *src, struct cred **new) { return call_int_hook(inode_copy_up, 0, src, new); } EXPORT_SYMBOL(security_inode_copy_up); int security_inode_copy_up_xattr(const char *name) { struct security_hook_list *hp; int rc; /* * The implementation can return 0 (accept the xattr), 1 (discard the * xattr), -EOPNOTSUPP if it does not know anything about the xattr or * any other error code incase of an error. */ hlist_for_each_entry(hp, &security_hook_heads.inode_copy_up_xattr, list) { rc = hp->hook.inode_copy_up_xattr(name); if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) return rc; } return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return call_int_hook(kernfs_init_security, 0, kn_dir, kn); } int security_file_permission(struct file *file, int mask) { int ret; ret = call_int_hook(file_permission, 0, file, mask); if (ret) return ret; return fsnotify_perm(file, mask); } int security_file_alloc(struct file *file) { int rc = lsm_file_alloc(file); if (rc) return rc; rc = call_int_hook(file_alloc_security, 0, file); if (unlikely(rc)) security_file_free(file); return rc; } void security_file_free(struct file *file) { void *blob; call_void_hook(file_free_security, file); blob = file->f_security; if (blob) { file->f_security = NULL; kmem_cache_free(lsm_file_cache, blob); } } int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl, 0, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl); /** * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Compat version of security_file_ioctl() that correctly handles 32-bit * processes running on 64-bit kernels. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl_compat, 0, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl_compat); static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* * Does we have PROT_READ and does the application expect * it to imply PROT_EXEC? If not, nothing to talk about... */ if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) return prot; if (!(current->personality & READ_IMPLIES_EXEC)) return prot; /* * if that's an anonymous mapping, let it. */ if (!file) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!path_noexec(&file->f_path)) { #ifndef CONFIG_MMU if (file->f_op->mmap_capabilities) { unsigned caps = file->f_op->mmap_capabilities(file); if (!(caps & NOMMU_MAP_EXEC)) return prot; } #endif return prot | PROT_EXEC; } /* anything on noexec mount won't get PROT_EXEC */ return prot; } int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { unsigned long prot_adj = mmap_prot(file, prot); int ret; ret = call_int_hook(mmap_file, 0, file, prot, prot_adj, flags); if (ret) return ret; return ima_file_mmap(file, prot, prot_adj, flags); } int security_mmap_addr(unsigned long addr) { return call_int_hook(mmap_addr, 0, addr); } int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { int ret; ret = call_int_hook(file_mprotect, 0, vma, reqprot, prot); if (ret) return ret; return ima_file_mprotect(vma, prot); } int security_file_lock(struct file *file, unsigned int cmd) { return call_int_hook(file_lock, 0, file, cmd); } int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_fcntl, 0, file, cmd, arg); } void security_file_set_fowner(struct file *file) { call_void_hook(file_set_fowner, file); } int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig) { return call_int_hook(file_send_sigiotask, 0, tsk, fown, sig); } int security_file_receive(struct file *file) { return call_int_hook(file_receive, 0, file); } int security_file_open(struct file *file) { int ret; ret = call_int_hook(file_open, 0, file); if (ret) return ret; return fsnotify_perm(file, MAY_OPEN); } int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { int rc = lsm_task_alloc(task); if (rc) return rc; rc = call_int_hook(task_alloc, 0, task, clone_flags); if (unlikely(rc)) security_task_free(task); return rc; } void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); kfree(task->security); task->security = NULL; } int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { int rc = lsm_cred_alloc(cred, gfp); if (rc) return rc; rc = call_int_hook(cred_alloc_blank, 0, cred, gfp); if (unlikely(rc)) security_cred_free(cred); return rc; } void security_cred_free(struct cred *cred) { /* * There is a failure case in prepare_creds() that * may result in a call here with ->security being NULL. */ if (unlikely(cred->security == NULL)) return; call_void_hook(cred_free, cred); kfree(cred->security); cred->security = NULL; } int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { int rc = lsm_cred_alloc(new, gfp); if (rc) return rc; rc = call_int_hook(cred_prepare, 0, new, old, gfp); if (unlikely(rc)) security_cred_free(new); return rc; } void security_transfer_creds(struct cred *new, const struct cred *old) { call_void_hook(cred_transfer, new, old); } void security_cred_getsecid(const struct cred *c, u32 *secid) { *secid = 0; call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); int security_kernel_act_as(struct cred *new, u32 secid) { return call_int_hook(kernel_act_as, 0, new, secid); } int security_kernel_create_files_as(struct cred *new, struct inode *inode) { return call_int_hook(kernel_create_files_as, 0, new, inode); } int security_kernel_module_request(char *kmod_name) { int ret; ret = call_int_hook(kernel_module_request, 0, kmod_name); if (ret) return ret; return integrity_kernel_module_request(kmod_name); } int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int ret; ret = call_int_hook(kernel_read_file, 0, file, id, contents); if (ret) return ret; return ima_read_file(file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { int ret; ret = call_int_hook(kernel_post_read_file, 0, file, buf, size, id); if (ret) return ret; return ima_post_read_file(file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { int ret; ret = call_int_hook(kernel_load_data, 0, id, contents); if (ret) return ret; return ima_load_data(id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { int ret; ret = call_int_hook(kernel_post_load_data, 0, buf, size, id, description); if (ret) return ret; return ima_post_load_data(buf, size, id, description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setuid, 0, new, old, flags); } int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setgid, 0, new, old, flags); } int security_task_setpgid(struct task_struct *p, pid_t pgid) { return call_int_hook(task_setpgid, 0, p, pgid); } int security_task_getpgid(struct task_struct *p) { return call_int_hook(task_getpgid, 0, p); } int security_task_getsid(struct task_struct *p) { return call_int_hook(task_getsid, 0, p); } void security_task_getsecid(struct task_struct *p, u32 *secid) { *secid = 0; call_void_hook(task_getsecid, p, secid); } EXPORT_SYMBOL(security_task_getsecid); int security_task_setnice(struct task_struct *p, int nice) { return call_int_hook(task_setnice, 0, p, nice); } int security_task_setioprio(struct task_struct *p, int ioprio) { return call_int_hook(task_setioprio, 0, p, ioprio); } int security_task_getioprio(struct task_struct *p) { return call_int_hook(task_getioprio, 0, p); } int security_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { return call_int_hook(task_prlimit, 0, cred, tcred, flags); } int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { return call_int_hook(task_setrlimit, 0, p, resource, new_rlim); } int security_task_setscheduler(struct task_struct *p) { return call_int_hook(task_setscheduler, 0, p); } int security_task_getscheduler(struct task_struct *p) { return call_int_hook(task_getscheduler, 0, p); } int security_task_movememory(struct task_struct *p) { return call_int_hook(task_movememory, 0, p); } int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, 0, p, info, sig, cred); } int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.task_prctl, list) { thisrc = hp->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; } } return rc; } void security_task_to_inode(struct task_struct *p, struct inode *inode) { call_void_hook(task_to_inode, p, inode); } int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { return call_int_hook(ipc_permission, 0, ipcp, flag); } void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { *secid = 0; call_void_hook(ipc_getsecid, ipcp, secid); } int security_msg_msg_alloc(struct msg_msg *msg) { int rc = lsm_msg_msg_alloc(msg); if (unlikely(rc)) return rc; rc = call_int_hook(msg_msg_alloc_security, 0, msg); if (unlikely(rc)) security_msg_msg_free(msg); return rc; } void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; } int security_msg_queue_alloc(struct kern_ipc_perm *msq) { int rc = lsm_ipc_alloc(msq); if (unlikely(rc)) return rc; rc = call_int_hook(msg_queue_alloc_security, 0, msq); if (unlikely(rc)) security_msg_queue_free(msq); return rc; } void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); kfree(msq->security); msq->security = NULL; } int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { return call_int_hook(msg_queue_associate, 0, msq, msqflg); } int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { return call_int_hook(msg_queue_msgctl, 0, msq, cmd); } int security_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { return call_int_hook(msg_queue_msgsnd, 0, msq, msg, msqflg); } int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { return call_int_hook(msg_queue_msgrcv, 0, msq, msg, target, type, mode); } int security_shm_alloc(struct kern_ipc_perm *shp) { int rc = lsm_ipc_alloc(shp); if (unlikely(rc)) return rc; rc = call_int_hook(shm_alloc_security, 0, shp); if (unlikely(rc)) security_shm_free(shp); return rc; } void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); kfree(shp->security); shp->security = NULL; } int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) { return call_int_hook(shm_associate, 0, shp, shmflg); } int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { return call_int_hook(shm_shmctl, 0, shp, cmd); } int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { return call_int_hook(shm_shmat, 0, shp, shmaddr, shmflg); } int security_sem_alloc(struct kern_ipc_perm *sma) { int rc = lsm_ipc_alloc(sma); if (unlikely(rc)) return rc; rc = call_int_hook(sem_alloc_security, 0, sma); if (unlikely(rc)) security_sem_free(sma); return rc; } void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); kfree(sma->security); sma->security = NULL; } int security_sem_associate(struct kern_ipc_perm *sma, int semflg) { return call_int_hook(sem_associate, 0, sma, semflg); } int security_sem_semctl(struct kern_ipc_perm *sma, int cmd) { return call_int_hook(sem_semctl, 0, sma, cmd); } int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { return call_int_hook(sem_semop, 0, sma, sops, nsops, alter); } void security_d_instantiate(struct dentry *dentry, struct inode *inode) { if (unlikely(inode && IS_PRIVATE(inode))) return; call_void_hook(d_instantiate, dentry, inode); } EXPORT_SYMBOL(security_d_instantiate); int security_getprocattr(struct task_struct *p, const char *lsm, char *name, char **value) { struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { if (lsm != NULL && strcmp(lsm, hp->lsm)) continue; return hp->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } int security_setprocattr(const char *lsm, const char *name, void *value, size_t size) { struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) { if (lsm != NULL && strcmp(lsm, hp->lsm)) continue; return hp->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } int security_netlink_send(struct sock *sk, struct sk_buff *skb) { return call_int_hook(netlink_send, 0, sk, skb); } int security_ismaclabel(const char *name) { return call_int_hook(ismaclabel, 0, name); } EXPORT_SYMBOL(security_ismaclabel); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { struct security_hook_list *hp; int rc; /* * Currently, only one LSM can implement secid_to_secctx (i.e this * LSM hook is not "stackable"). */ hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) { rc = hp->hook.secid_to_secctx(secid, secdata, seclen); if (rc != LSM_RET_DEFAULT(secid_to_secctx)) return rc; } return LSM_RET_DEFAULT(secid_to_secctx); } EXPORT_SYMBOL(security_secid_to_secctx); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { *secid = 0; return call_int_hook(secctx_to_secid, 0, secdata, seclen, secid); } EXPORT_SYMBOL(security_secctx_to_secid); void security_release_secctx(char *secdata, u32 seclen) { call_void_hook(release_secctx, secdata, seclen); } EXPORT_SYMBOL(security_release_secctx); void security_inode_invalidate_secctx(struct inode *inode) { call_void_hook(inode_invalidate_secctx, inode); } EXPORT_SYMBOL(security_inode_invalidate_secctx); int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { return call_int_hook(inode_notifysecctx, 0, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_notifysecctx); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return call_int_hook(inode_setsecctx, 0, dentry, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_setsecctx); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); if (rc != LSM_RET_DEFAULT(inode_getsecctx)) return rc; } return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_WATCH_QUEUE int security_post_notification(const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) { return call_int_hook(post_notification, 0, w_cred, cred, n); } #endif /* CONFIG_WATCH_QUEUE */ #ifdef CONFIG_KEY_NOTIFICATIONS int security_watch_key(struct key *key) { return call_int_hook(watch_key, 0, key); } #endif #ifdef CONFIG_SECURITY_NETWORK int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return call_int_hook(unix_stream_connect, 0, sock, other, newsk); } EXPORT_SYMBOL(security_unix_stream_connect); int security_unix_may_send(struct socket *sock, struct socket *other) { return call_int_hook(unix_may_send, 0, sock, other); } EXPORT_SYMBOL(security_unix_may_send); int security_socket_create(int family, int type, int protocol, int kern) { return call_int_hook(socket_create, 0, family, type, protocol, kern); } int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { return call_int_hook(socket_post_create, 0, sock, family, type, protocol, kern); } int security_socket_socketpair(struct socket *socka, struct socket *sockb) { return call_int_hook(socket_socketpair, 0, socka, sockb); } EXPORT_SYMBOL(security_socket_socketpair); int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_bind, 0, sock, address, addrlen); } int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_connect, 0, sock, address, addrlen); } int security_socket_listen(struct socket *sock, int backlog) { return call_int_hook(socket_listen, 0, sock, backlog); } int security_socket_accept(struct socket *sock, struct socket *newsock) { return call_int_hook(socket_accept, 0, sock, newsock); } int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return call_int_hook(socket_sendmsg, 0, sock, msg, size); } int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return call_int_hook(socket_recvmsg, 0, sock, msg, size, flags); } int security_socket_getsockname(struct socket *sock) { return call_int_hook(socket_getsockname, 0, sock); } int security_socket_getpeername(struct socket *sock) { return call_int_hook(socket_getpeername, 0, sock); } int security_socket_getsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_getsockopt, 0, sock, level, optname); } int security_socket_setsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_setsockopt, 0, sock, level, optname); } int security_socket_shutdown(struct socket *sock, int how) { return call_int_hook(socket_shutdown, 0, sock, how); } int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { return call_int_hook(socket_sock_rcv_skb, 0, sk, skb); } EXPORT_SYMBOL(security_sock_rcv_skb); int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream, list) { rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen, len); if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream)) return rc; } return LSM_RET_DEFAULT(socket_getpeersec_stream); } int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram, list) { rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid); if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram)) return rc; } return LSM_RET_DEFAULT(socket_getpeersec_dgram); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { return call_int_hook(sk_alloc_security, 0, sk, family, priority); } void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); } void security_sk_clone(const struct sock *sk, struct sock *newsk) { call_void_hook(sk_clone_security, sk, newsk); } EXPORT_SYMBOL(security_sk_clone); void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } EXPORT_SYMBOL(security_sk_classify_flow); void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { call_void_hook(req_classify_flow, req, flic); } EXPORT_SYMBOL(security_req_classify_flow); void security_sock_graft(struct sock *sk, struct socket *parent) { call_void_hook(sock_graft, sk, parent); } EXPORT_SYMBOL(security_sock_graft); int security_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { return call_int_hook(inet_conn_request, 0, sk, skb, req); } EXPORT_SYMBOL(security_inet_conn_request); void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { call_void_hook(inet_csk_clone, newsk, req); } void security_inet_conn_established(struct sock *sk, struct sk_buff *skb) { call_void_hook(inet_conn_established, sk, skb); } EXPORT_SYMBOL(security_inet_conn_established); int security_secmark_relabel_packet(u32 secid) { return call_int_hook(secmark_relabel_packet, 0, secid); } EXPORT_SYMBOL(security_secmark_relabel_packet); void security_secmark_refcount_inc(void) { call_void_hook(secmark_refcount_inc); } EXPORT_SYMBOL(security_secmark_refcount_inc); void security_secmark_refcount_dec(void) { call_void_hook(secmark_refcount_dec); } EXPORT_SYMBOL(security_secmark_refcount_dec); int security_tun_dev_alloc_security(void **security) { return call_int_hook(tun_dev_alloc_security, 0, security); } EXPORT_SYMBOL(security_tun_dev_alloc_security); void security_tun_dev_free_security(void *security) { call_void_hook(tun_dev_free_security, security); } EXPORT_SYMBOL(security_tun_dev_free_security); int security_tun_dev_create(void) { return call_int_hook(tun_dev_create, 0); } EXPORT_SYMBOL(security_tun_dev_create); int security_tun_dev_attach_queue(void *security) { return call_int_hook(tun_dev_attach_queue, 0, security); } EXPORT_SYMBOL(security_tun_dev_attach_queue); int security_tun_dev_attach(struct sock *sk, void *security) { return call_int_hook(tun_dev_attach, 0, sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); int security_tun_dev_open(void *security) { return call_int_hook(tun_dev_open, 0, security); } EXPORT_SYMBOL(security_tun_dev_open); int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb) { return call_int_hook(sctp_assoc_request, 0, ep, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { return call_int_hook(sctp_bind_connect, 0, sk, optname, address, addrlen); } EXPORT_SYMBOL(security_sctp_bind_connect); void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, struct sock *newsk) { call_void_hook(sctp_sk_clone, ep, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) { return call_int_hook(ib_pkey_access, 0, sec, subnet_prefix, pkey); } EXPORT_SYMBOL(security_ib_pkey_access); int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) { return call_int_hook(ib_endport_manage_subnet, 0, sec, dev_name, port_num); } EXPORT_SYMBOL(security_ib_endport_manage_subnet); int security_ib_alloc_security(void **sec) { return call_int_hook(ib_alloc_security, 0, sec); } EXPORT_SYMBOL(security_ib_alloc_security); void security_ib_free_security(void *sec) { call_void_hook(ib_free_security, sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) { return call_int_hook(xfrm_policy_alloc_security, 0, ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp) { return call_int_hook(xfrm_policy_clone_security, 0, old_ctx, new_ctxp); } void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx) { call_void_hook(xfrm_policy_free_security, ctx); } EXPORT_SYMBOL(security_xfrm_policy_free); int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { return call_int_hook(xfrm_policy_delete_security, 0, ctx); } int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { return call_int_hook(xfrm_state_alloc, 0, x, sec_ctx); } EXPORT_SYMBOL(security_xfrm_state_alloc); int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) { return call_int_hook(xfrm_state_alloc_acquire, 0, x, polsec, secid); } int security_xfrm_state_delete(struct xfrm_state *x) { return call_int_hook(xfrm_state_delete_security, 0, x); } EXPORT_SYMBOL(security_xfrm_state_delete); void security_xfrm_state_free(struct xfrm_state *x) { call_void_hook(xfrm_state_free_security, x); } int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) { return call_int_hook(xfrm_policy_lookup, 0, ctx, fl_secid, dir); } int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { struct security_hook_list *hp; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment * becomes difficult if multiple LSMs supply this call. Fortunately, * we can use the first LSM's judgment because currently only SELinux * supplies this call. * * For speed optimization, we explicitly break the loop rather than * using the macro */ hlist_for_each_entry(hp, &security_hook_heads.xfrm_state_pol_flow_match, list) { rc = hp->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; } int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return call_int_hook(xfrm_decode_session, 0, skb, secid, 1); } void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic) { int rc = call_int_hook(xfrm_decode_session, 0, skb, &flic->flowic_secid, 0); BUG_ON(rc); } EXPORT_SYMBOL(security_skb_classify_flow); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { return call_int_hook(key_alloc, 0, key, cred, flags); } void security_key_free(struct key *key) { call_void_hook(key_free, key); } int security_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { return call_int_hook(key_permission, 0, key_ref, cred, need_perm); } int security_key_getsecurity(struct key *key, char **_buffer) { *_buffer = NULL; return call_int_hook(key_getsecurity, 0, key, _buffer); } #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) { return call_int_hook(audit_rule_init, 0, field, op, rulestr, lsmrule, gfp); } int security_audit_rule_known(struct audit_krule *krule) { return call_int_hook(audit_rule_known, 0, krule); } void security_audit_rule_free(void *lsmrule) { call_void_hook(audit_rule_free, lsmrule); } int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule) { return call_int_hook(audit_rule_match, 0, secid, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) { return call_int_hook(bpf, 0, cmd, attr, size); } int security_bpf_map(struct bpf_map *map, fmode_t fmode) { return call_int_hook(bpf_map, 0, map, fmode); } int security_bpf_prog(struct bpf_prog *prog) { return call_int_hook(bpf_prog, 0, prog); } int security_bpf_map_alloc(struct bpf_map *map) { return call_int_hook(bpf_map_alloc_security, 0, map); } int security_bpf_prog_alloc(struct bpf_prog_aux *aux) { return call_int_hook(bpf_prog_alloc_security, 0, aux); } void security_bpf_map_free(struct bpf_map *map) { call_void_hook(bpf_map_free_security, map); } void security_bpf_prog_free(struct bpf_prog_aux *aux) { call_void_hook(bpf_prog_free_security, aux); } #endif /* CONFIG_BPF_SYSCALL */ int security_locked_down(enum lockdown_reason what) { return call_int_hook(locked_down, 0, what); } EXPORT_SYMBOL(security_locked_down); #ifdef CONFIG_PERF_EVENTS int security_perf_event_open(struct perf_event_attr *attr, int type) { return call_int_hook(perf_event_open, 0, attr, type); } int security_perf_event_alloc(struct perf_event *event) { return call_int_hook(perf_event_alloc, 0, event); } void security_perf_event_free(struct perf_event *event) { call_void_hook(perf_event_free, event); } int security_perf_event_read(struct perf_event *event) { return call_int_hook(perf_event_read, 0, event); } int security_perf_event_write(struct perf_event *event) { return call_int_hook(perf_event_write, 0, event); } #endif /* CONFIG_PERF_EVENTS */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_SECTIONS_H_ #define _ASM_GENERIC_SECTIONS_H_ /* References to section boundaries */ #include <linux/compiler.h> #include <linux/types.h> /* * Usage guidelines: * _text, _data: architecture specific, don't use them in arch-independent code * [_stext, _etext]: contains .text.* sections, may also contain .rodata.* * and/or .init.* sections * [_sdata, _edata]: contains .data.* sections, may also contain .rodata.* * and/or .init.* sections. * [__start_rodata, __end_rodata]: contains .rodata.* sections * [__start_ro_after_init, __end_ro_after_init]: * contains .data..ro_after_init section * [__init_begin, __init_end]: contains .init.* sections, but .init.text.* * may be out of this range on some architectures. * [_sinittext, _einittext]: contains .init.text.* sections * [__bss_start, __bss_stop]: contains BSS sections * * Following global variables are optional and may be unavailable on some * architectures and/or kernel configurations. * _text, _data * __kprobes_text_start, __kprobes_text_end * __entry_text_start, __entry_text_end * __ctors_start, __ctors_end * __irqentry_text_start, __irqentry_text_end * __softirqentry_text_start, __softirqentry_text_end * __start_opd, __end_opd */ extern char _text[], _stext[], _etext[]; extern char _data[], _sdata[], _edata[]; extern char __bss_start[], __bss_stop[]; extern char __init_begin[], __init_end[]; extern char _sinittext[], _einittext[]; extern char __start_ro_after_init[], __end_ro_after_init[]; extern char _end[]; extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; extern char __entry_text_start[], __entry_text_end[]; extern char __start_rodata[], __end_rodata[]; extern char __irqentry_text_start[], __irqentry_text_end[]; extern char __softirqentry_text_start[], __softirqentry_text_end[]; extern char __start_once[], __end_once[]; /* Start and end of .ctors section - used for constructor calls. */ extern char __ctors_start[], __ctors_end[]; /* Start and end of .opd section - used for function descriptors. */ extern char __start_opd[], __end_opd[]; /* Start and end of instrumentation protected text section */ extern char __noinstr_text_start[], __noinstr_text_end[]; extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ #ifndef dereference_function_descriptor #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) #endif /* random extra sections (if any). Override * in asm/sections.h */ #ifndef arch_is_kernel_text static inline int arch_is_kernel_text(unsigned long addr) { return 0; } #endif #ifndef arch_is_kernel_data static inline int arch_is_kernel_data(unsigned long addr) { return 0; } #endif /* * Check if an address is part of freed initmem. This is needed on architectures * with virt == phys kernel mapping, for code that wants to check if an address * is part of a static object within [_stext, _end]. After initmem is freed, * memory can be allocated from it, and such allocations would then have * addresses within the range [_stext, _end]. */ #ifndef arch_is_kernel_initmem_freed static inline int arch_is_kernel_initmem_freed(unsigned long addr) { return 0; } #endif /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the memory region defined by @begin and @end, false * otherwise. */ static inline bool memory_contains(void *begin, void *end, void *virt, size_t size) { return virt >= begin && virt + size <= end; } /** * memory_intersects - checks if the region occupied by an object intersects * with another memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the region specified by @begin and @end, false otherwise. */ static inline bool memory_intersects(void *begin, void *end, void *virt, size_t size) { void *vend = virt + size; if (virt < end && vend > begin) return true; return false; } /** * init_section_contains - checks if an object is contained within the init * section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the init section, false otherwise. */ static inline bool init_section_contains(void *virt, size_t size) { return memory_contains(__init_begin, __init_end, virt, size); } /** * init_section_intersects - checks if the region occupied by an object * intersects with the init section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the init section, false otherwise. */ static inline bool init_section_intersects(void *virt, size_t size) { return memory_intersects(__init_begin, __init_end, virt, size); } /** * is_kernel_rodata - checks if the pointer address is located in the * .rodata section * * @addr: address to check * * Returns: true if the address is located in .rodata, false otherwise. */ static inline bool is_kernel_rodata(unsigned long addr) { return addr >= (unsigned long)__start_rodata && addr < (unsigned long)__end_rodata; } #endif /* _ASM_GENERIC_SECTIONS_H_ */ |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); loff_t cloned; int ret; if (!src_file.file) return -EBADF; ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; fdput: fdput(src_file); return ret; } static long ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } #ifdef CONFIG_BLOCK static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) { return (offset >> inode->i_blkbits); } static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) { return (blk << inode->i_blkbits); } /** * __generic_block_fiemap - FIEMAP for block based inodes (no locking) * @inode: the inode to map * @fieinfo: the fiemap info struct that will be passed back to userspace * @start: where to start mapping in the inode * @len: how much space to map * @get_block: the fs's get_block function * * This does FIEMAP for block based inodes. Basically it will just loop * through get_block until we hit the number of extents we want to map, or we * go past the end of the file and hit a hole. * * If it is possible to have data blocks beyond a hole past @inode->i_size, then * please do not use this function, it will stop at the first unmapped block * beyond i_size. * * If you use this function directly, you need to do your own locking. Use * generic_block_fiemap if you want the locking done for you. */ static int __generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, get_block_t *get_block) { struct buffer_head map_bh; sector_t start_blk, last_blk; loff_t isize = i_size_read(inode); u64 logical = 0, phys = 0, size = 0; u32 flags = FIEMAP_EXTENT_MERGED; bool past_eof = false, whole_file = false; int ret = 0; ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_SYNC); if (ret) return ret; /* * Either the i_mutex or other appropriate locking needs to be held * since we expect isize to not change at all through the duration of * this call. */ if (len >= isize) { whole_file = true; len = isize; } /* * Some filesystems can't deal with being asked to map less than * blocksize, so make sure our len is at least block length. */ if (logical_to_blk(inode, len) == 0) len = blk_to_logical(inode, 1); start_blk = logical_to_blk(inode, start); last_blk = logical_to_blk(inode, start + len - 1); do { /* * we set b_size to the total size we want so it will map as * many contiguous blocks as possible at once */ memset(&map_bh, 0, sizeof(struct buffer_head)); map_bh.b_size = len; ret = get_block(inode, start_blk, &map_bh, 0); if (ret) break; /* HOLE */ if (!buffer_mapped(&map_bh)) { start_blk++; /* * We want to handle the case where there is an * allocated block at the front of the file, and then * nothing but holes up to the end of the file properly, * to make sure that extent at the front gets properly * marked with FIEMAP_EXTENT_LAST */ if (!past_eof && blk_to_logical(inode, start_blk) >= isize) past_eof = 1; /* * First hole after going past the EOF, this is our * last extent */ if (past_eof && size) { flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST; ret = fiemap_fill_next_extent(fieinfo, logical, phys, size, flags); } else if (size) { ret = fiemap_fill_next_extent(fieinfo, logical, phys, size, flags); size = 0; } /* if we have holes up to/past EOF then we're done */ if (start_blk > last_blk || past_eof || ret) break; } else { /* * We have gone over the length of what we wanted to * map, and it wasn't the entire file, so add the extent * we got last time and exit. * * This is for the case where say we want to map all the * way up to the second to the last block in a file, but * the last block is a hole, making the second to last * block FIEMAP_EXTENT_LAST. In this case we want to * see if there is a hole after the second to last block * so we can mark it properly. If we found data after * we exceeded the length we were requesting, then we * are good to go, just add the extent to the fieinfo * and break */ if (start_blk > last_blk && !whole_file) { ret = fiemap_fill_next_extent(fieinfo, logical, phys, size, flags); break; } /* * if size != 0 then we know we already have an extent * to add, so add it. */ if (size) { ret = fiemap_fill_next_extent(fieinfo, logical, phys, size, flags); if (ret) break; } logical = blk_to_logical(inode, start_blk); phys = blk_to_logical(inode, map_bh.b_blocknr); size = map_bh.b_size; flags = FIEMAP_EXTENT_MERGED; start_blk += logical_to_blk(inode, size); /* * If we are past the EOF, then we need to make sure as * soon as we find a hole that the last extent we found * is marked with FIEMAP_EXTENT_LAST */ if (!past_eof && logical + size >= isize) past_eof = true; } cond_resched(); if (fatal_signal_pending(current)) { ret = -EINTR; break; } } while (1); /* If ret is 1 then we just hit the end of the extent array */ if (ret == 1) ret = 0; return ret; } /** * generic_block_fiemap - FIEMAP for block based inodes * @inode: The inode to map * @fieinfo: The mapping information * @start: The initial block to map * @len: The length of the extect to attempt to map * @get_block: The block mapping function for the fs * * Calls __generic_block_fiemap to map the inode, after taking * the inode's mutex lock. */ int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block) { int ret; inode_lock(inode); ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block); inode_unlock(inode); return ret; } EXPORT_SYMBOL(generic_block_fiemap); #endif /* CONFIG_BLOCK */ /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb); return freeze_super(sb); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb); return thaw_super(sb); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = offsetof(struct file_dedupe_range __user, info[count]); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl(f.file, cmd, arg); if (error) goto out; error = do_vfs_ioctl(f.file, fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(f.file, cmd, arg); out: fdput(f); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(f.file, arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(f.file, fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (f.file->f_op->compat_ioctl) error = f.file->f_op->compat_ioctl(f.file, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } out: fdput(f); return error; } #endif |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 | // SPDX-License-Identifier: GPL-2.0+ /* * Driver core for serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright 1999 ARM Limited * Copyright (C) 2000-2001 Deep Blue Solutions Ltd. */ #include <linux/module.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/init.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/of.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/device.h> #include <linux/serial.h> /* for serial_state and serial_icounter_struct */ #include <linux/serial_core.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/security.h> #include <linux/irq.h> #include <linux/uaccess.h> /* * This is used to lock changes in serial line configuration. */ static DEFINE_MUTEX(port_mutex); /* * lockdep: port->lock is initialized in two places, but we * want only one lock-class: */ static struct lock_class_key port_lock_key; #define HIGH_BITS_OFFSET ((sizeof(long)-sizeof(int))*8) /* * Max time with active RTS before/after data is sent. */ #define RS485_MAX_RTS_DELAY 100 /* msecs */ static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, struct ktermios *old_termios); static void uart_wait_until_sent(struct tty_struct *tty, int timeout); static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state); static void uart_port_shutdown(struct tty_port *port); static int uart_dcd_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_DCD_ENABLE); } static inline struct uart_port *uart_port_ref(struct uart_state *state) { if (atomic_add_unless(&state->refcount, 1, 0)) return state->uart_port; return NULL; } static inline void uart_port_deref(struct uart_port *uport) { if (atomic_dec_and_test(&uport->state->refcount)) wake_up(&uport->state->remove_wait); } #define uart_port_lock(state, flags) \ ({ \ struct uart_port *__uport = uart_port_ref(state); \ if (__uport) \ spin_lock_irqsave(&__uport->lock, flags); \ __uport; \ }) #define uart_port_unlock(uport, flags) \ ({ \ struct uart_port *__uport = uport; \ if (__uport) { \ spin_unlock_irqrestore(&__uport->lock, flags); \ uart_port_deref(__uport); \ } \ }) static inline struct uart_port *uart_port_check(struct uart_state *state) { lockdep_assert_held(&state->port.mutex); return state->uart_port; } /* * This routine is used by the interrupt handler to schedule processing in * the software interrupt portion of the driver. */ void uart_write_wakeup(struct uart_port *port) { struct uart_state *state = port->state; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ BUG_ON(!state); tty_port_tty_wakeup(&state->port); } static void uart_stop(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_lock(state, flags); if (port) port->ops->stop_tx(port); uart_port_unlock(port, flags); } static void __uart_start(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port = state->uart_port; if (port && !uart_tx_stopped(port)) port->ops->start_tx(port); } static void uart_start(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_lock(state, flags); __uart_start(tty); uart_port_unlock(port, flags); } static void uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) { unsigned long flags; unsigned int old; spin_lock_irqsave(&port->lock, flags); old = port->mctrl; port->mctrl = (old & ~clear) | set; if (old != port->mctrl && !(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); } #define uart_set_mctrl(port, set) uart_update_mctrl(port, set, 0) #define uart_clear_mctrl(port, clear) uart_update_mctrl(port, 0, clear) static void uart_port_dtr_rts(struct uart_port *uport, int raise) { if (raise) uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); else uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); } /* * Startup the port. This will be called once per open. All calls * will be serialised by the per-port mutex. */ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, int init_hw) { struct uart_port *uport = uart_port_check(state); unsigned long page; unsigned long flags = 0; int retval = 0; if (uport->type == PORT_UNKNOWN) return 1; /* * Make sure the device is in D0 state. */ uart_change_pm(state, UART_PM_STATE_ON); /* * Initialise and allocate the transmit and temporary * buffer. */ page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; uart_port_lock(state, flags); if (!state->xmit.buf) { state->xmit.buf = (unsigned char *) page; uart_circ_clear(&state->xmit); uart_port_unlock(uport, flags); } else { uart_port_unlock(uport, flags); /* * Do not free() the page under the port lock, see * uart_shutdown(). */ free_page(page); } retval = uport->ops->startup(uport); if (retval == 0) { if (uart_console(uport) && uport->cons->cflag) { tty->termios.c_cflag = uport->cons->cflag; tty->termios.c_ispeed = uport->cons->ispeed; tty->termios.c_ospeed = uport->cons->ospeed; uport->cons->cflag = 0; uport->cons->ispeed = 0; uport->cons->ospeed = 0; } /* * Initialise the hardware port settings. */ uart_change_speed(tty, state, NULL); /* * Setup the RTS and DTR signals once the * port is open and ready to respond. */ if (init_hw && C_BAUD(tty)) uart_port_dtr_rts(uport, 1); } /* * This is to allow setserial on this port. People may want to set * port/irq/type and then reconfigure the port properly if it failed * now. */ if (retval && capable(CAP_SYS_ADMIN)) return 1; return retval; } static int uart_startup(struct tty_struct *tty, struct uart_state *state, int init_hw) { struct tty_port *port = &state->port; int retval; if (tty_port_initialized(port)) return 0; retval = uart_port_startup(tty, state, init_hw); if (retval) set_bit(TTY_IO_ERROR, &tty->flags); return retval; } /* * This routine will shutdown a serial port; interrupts are disabled, and * DTR is dropped if the hangup on close termio flag is on. Calls to * uart_shutdown are serialised by the per-port semaphore. * * uport == NULL if uart_port has already been removed */ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) { struct uart_port *uport = uart_port_check(state); struct tty_port *port = &state->port; unsigned long flags = 0; char *xmit_buf = NULL; /* * Set the TTY IO error marker */ if (tty) set_bit(TTY_IO_ERROR, &tty->flags); if (tty_port_initialized(port)) { tty_port_set_initialized(port, 0); /* * Turn off DTR and RTS early. */ if (uport) { if (uart_console(uport) && tty) { uport->cons->cflag = tty->termios.c_cflag; uport->cons->ispeed = tty->termios.c_ispeed; uport->cons->ospeed = tty->termios.c_ospeed; } if (!tty || C_HUPCL(tty)) uart_port_dtr_rts(uport, 0); } uart_port_shutdown(port); } /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, 0); /* * Do not free() the transmit buffer page under the port lock since * this can create various circular locking scenarios. For instance, * console driver may need to allocate/free a debug object, which * can endup in printk() recursion. */ uart_port_lock(state, flags); xmit_buf = state->xmit.buf; state->xmit.buf = NULL; uart_port_unlock(uport, flags); if (xmit_buf) free_page((unsigned long)xmit_buf); } /** * uart_update_timeout - update per-port FIFO timeout. * @port: uart_port structure describing the port * @cflag: termios cflag value * @baud: speed of the port * * Set the port FIFO timeout value. The @cflag value should * reflect the actual hardware settings. */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud) { unsigned int bits; /* byte size and parity */ switch (cflag & CSIZE) { case CS5: bits = 7; break; case CS6: bits = 8; break; case CS7: bits = 9; break; default: bits = 10; break; /* CS8 */ } if (cflag & CSTOPB) bits++; if (cflag & PARENB) bits++; /* * The total number of bits to be transmitted in the fifo. */ bits = bits * port->fifosize; /* * Figure the timeout to send the above number of bits. * Add .02 seconds of slop */ port->timeout = (HZ * bits) / baud + HZ/50; } EXPORT_SYMBOL(uart_update_timeout); /** * uart_get_baud_rate - return baud rate for a particular port * @port: uart_port structure describing the port in question. * @termios: desired termios settings. * @old: old termios (or NULL) * @min: minimum acceptable baud rate * @max: maximum acceptable baud rate * * Decode the termios structure into a numeric baud rate, * taking account of the magic 38400 baud rate (with spd_* * flags), and mapping the %B0 rate to 9600 baud. * * If the new baud rate is invalid, try the old termios setting. * If it's still invalid, we try 9600 baud. * * Update the @termios structure to reflect the baud rate * we're actually going to be using. Don't do this for the case * where B0 is requested ("hang up"). */ unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, struct ktermios *old, unsigned int min, unsigned int max) { unsigned int try; unsigned int baud; unsigned int altbaud; int hung_up = 0; upf_t flags = port->flags & UPF_SPD_MASK; switch (flags) { case UPF_SPD_HI: altbaud = 57600; break; case UPF_SPD_VHI: altbaud = 115200; break; case UPF_SPD_SHI: altbaud = 230400; break; case UPF_SPD_WARP: altbaud = 460800; break; default: altbaud = 38400; break; } for (try = 0; try < 2; try++) { baud = tty_termios_baud_rate(termios); /* * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ if (try == 0 && baud == 38400) baud = altbaud; /* * Special case: B0 rate. */ if (baud == 0) { hung_up = 1; baud = 9600; } if (baud >= min && baud <= max) return baud; /* * Oops, the quotient was zero. Try again with * the old baud rate if possible. */ termios->c_cflag &= ~CBAUD; if (old) { baud = tty_termios_baud_rate(old); if (!hung_up) tty_termios_encode_baud_rate(termios, baud, baud); old = NULL; continue; } /* * As a last resort, if the range cannot be met then clip to * the nearest chip supported rate. */ if (!hung_up) { if (baud <= min) tty_termios_encode_baud_rate(termios, min + 1, min + 1); else tty_termios_encode_baud_rate(termios, max - 1, max - 1); } } /* Should never happen */ WARN_ON(1); return 0; } EXPORT_SYMBOL(uart_get_baud_rate); /** * uart_get_divisor - return uart clock divisor * @port: uart_port structure describing the port. * @baud: desired baud rate * * Calculate the uart clock divisor for the port. */ unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud) { unsigned int quot; /* * Old custom speed handling. */ if (baud == 38400 && (port->flags & UPF_SPD_MASK) == UPF_SPD_CUST) quot = port->custom_divisor; else quot = DIV_ROUND_CLOSEST(port->uartclk, 16 * baud); return quot; } EXPORT_SYMBOL(uart_get_divisor); /* Caller holds port mutex */ static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, struct ktermios *old_termios) { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; int hw_stopped; /* * If we have no tty, termios, or the port does not exist, * then we can't set the parameters for this port. */ if (!tty || uport->type == PORT_UNKNOWN) return; termios = &tty->termios; uport->ops->set_termios(uport, termios, old_termios); /* * Set modem status enables based on termios cflag */ spin_lock_irq(&uport->lock); if (termios->c_cflag & CRTSCTS) uport->status |= UPSTAT_CTS_ENABLE; else uport->status &= ~UPSTAT_CTS_ENABLE; if (termios->c_cflag & CLOCAL) uport->status &= ~UPSTAT_DCD_ENABLE; else uport->status |= UPSTAT_DCD_ENABLE; /* reset sw-assisted CTS flow control based on (possibly) new mode */ hw_stopped = uport->hw_stopped; uport->hw_stopped = uart_softcts_mode(uport) && !(uport->ops->get_mctrl(uport) & TIOCM_CTS); if (uport->hw_stopped) { if (!hw_stopped) uport->ops->stop_tx(uport); } else { if (hw_stopped) __uart_start(tty); } spin_unlock_irq(&uport->lock); } static int uart_put_char(struct tty_struct *tty, unsigned char c) { struct uart_state *state = tty->driver_data; struct uart_port *port; struct circ_buf *circ; unsigned long flags; int ret = 0; circ = &state->xmit; port = uart_port_lock(state, flags); if (!circ->buf) { uart_port_unlock(port, flags); return 0; } if (port && uart_circ_chars_free(circ) != 0) { circ->buf[circ->head] = c; circ->head = (circ->head + 1) & (UART_XMIT_SIZE - 1); ret = 1; } uart_port_unlock(port, flags); return ret; } static void uart_flush_chars(struct tty_struct *tty) { uart_start(tty); } static int uart_write(struct tty_struct *tty, const unsigned char *buf, int count) { struct uart_state *state = tty->driver_data; struct uart_port *port; struct circ_buf *circ; unsigned long flags; int c, ret = 0; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (!state) { WARN_ON(1); return -EL3HLT; } port = uart_port_lock(state, flags); circ = &state->xmit; if (!circ->buf) { uart_port_unlock(port, flags); return 0; } while (port) { c = CIRC_SPACE_TO_END(circ->head, circ->tail, UART_XMIT_SIZE); if (count < c) c = count; if (c <= 0) break; memcpy(circ->buf + circ->head, buf, c); circ->head = (circ->head + c) & (UART_XMIT_SIZE - 1); buf += c; count -= c; ret += c; } __uart_start(tty); uart_port_unlock(port, flags); return ret; } static int uart_write_room(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret; port = uart_port_lock(state, flags); ret = uart_circ_chars_free(&state->xmit); uart_port_unlock(port, flags); return ret; } static int uart_chars_in_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret; port = uart_port_lock(state, flags); ret = uart_circ_chars_pending(&state->xmit); uart_port_unlock(port, flags); return ret; } static void uart_flush_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (!state) { WARN_ON(1); return; } pr_debug("uart_flush_buffer(%d) called\n", tty->index); port = uart_port_lock(state, flags); if (!port) return; uart_circ_clear(&state->xmit); if (port->ops->flush_buffer) port->ops->flush_buffer(port); uart_port_unlock(port, flags); tty_port_tty_wakeup(&state->port); } /* * This function performs low-level write of high-priority XON/XOFF * character and accounting for it. * * Requires uart_port to implement .serial_out(). */ void uart_xchar_out(struct uart_port *uport, int offset) { serial_port_out(uport, offset, uport->x_char); uport->icount.tx++; uport->x_char = 0; } EXPORT_SYMBOL_GPL(uart_xchar_out); /* * This function is used to send a high-priority XON/XOFF character to * the device */ static void uart_send_xchar(struct tty_struct *tty, char ch) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_ref(state); if (!port) return; if (port->ops->send_xchar) port->ops->send_xchar(port, ch); else { spin_lock_irqsave(&port->lock, flags); port->x_char = ch; if (ch) port->ops->start_tx(port); spin_unlock_irqrestore(&port->lock, flags); } uart_port_deref(port); } static void uart_throttle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->throttle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_clear_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, STOP_CHAR(tty)); uart_port_deref(port); } static void uart_unthrottle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->unthrottle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_set_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, START_CHAR(tty)); uart_port_deref(port); } static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int ret = -ENODEV; memset(retinfo, 0, sizeof(*retinfo)); /* * Ensure the state we copy is consistent and no hardware changes * occur as we go */ mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport) goto out; retinfo->type = uport->type; retinfo->line = uport->line; retinfo->port = uport->iobase; if (HIGH_BITS_OFFSET) retinfo->port_high = (long) uport->iobase >> HIGH_BITS_OFFSET; retinfo->irq = uport->irq; retinfo->flags = (__force int)uport->flags; retinfo->xmit_fifo_size = uport->fifosize; retinfo->baud_base = uport->uartclk / 16; retinfo->close_delay = jiffies_to_msecs(port->close_delay) / 10; retinfo->closing_wait = port->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : jiffies_to_msecs(port->closing_wait) / 10; retinfo->custom_divisor = uport->custom_divisor; retinfo->hub6 = uport->hub6; retinfo->io_type = uport->iotype; retinfo->iomem_reg_shift = uport->regshift; retinfo->iomem_base = (void *)(unsigned long)uport->mapbase; ret = 0; out: mutex_unlock(&port->mutex); return ret; } static int uart_get_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; return uart_get_info(port, ss) < 0 ? -EIO : 0; } static int uart_set_info(struct tty_struct *tty, struct tty_port *port, struct uart_state *state, struct serial_struct *new_info) { struct uart_port *uport = uart_port_check(state); unsigned long new_port; unsigned int change_irq, change_port, closing_wait; unsigned int old_custom_divisor, close_delay; upf_t old_flags, new_flags; int retval = 0; if (!uport) return -EIO; new_port = new_info->port; if (HIGH_BITS_OFFSET) new_port += (unsigned long) new_info->port_high << HIGH_BITS_OFFSET; new_info->irq = irq_canonicalize(new_info->irq); close_delay = msecs_to_jiffies(new_info->close_delay * 10); closing_wait = new_info->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : msecs_to_jiffies(new_info->closing_wait * 10); change_irq = !(uport->flags & UPF_FIXED_PORT) && new_info->irq != uport->irq; /* * Since changing the 'type' of the port changes its resource * allocations, we should treat type changes the same as * IO port changes. */ change_port = !(uport->flags & UPF_FIXED_PORT) && (new_port != uport->iobase || (unsigned long)new_info->iomem_base != uport->mapbase || new_info->hub6 != uport->hub6 || new_info->io_type != uport->iotype || new_info->iomem_reg_shift != uport->regshift || new_info->type != uport->type); old_flags = uport->flags; new_flags = (__force upf_t)new_info->flags; old_custom_divisor = uport->custom_divisor; if (!(uport->flags & UPF_FIXED_PORT)) { unsigned int uartclk = new_info->baud_base * 16; /* check needs to be done here before other settings made */ if (uartclk == 0) { retval = -EINVAL; goto exit; } } if (!capable(CAP_SYS_ADMIN)) { retval = -EPERM; if (change_irq || change_port || (new_info->baud_base != uport->uartclk / 16) || (close_delay != port->close_delay) || (closing_wait != port->closing_wait) || (new_info->xmit_fifo_size && new_info->xmit_fifo_size != uport->fifosize) || (((new_flags ^ old_flags) & ~UPF_USR_MASK) != 0)) goto exit; uport->flags = ((uport->flags & ~UPF_USR_MASK) | (new_flags & UPF_USR_MASK)); uport->custom_divisor = new_info->custom_divisor; goto check_and_exit; } if (change_irq || change_port) { retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); if (retval) goto exit; } /* * Ask the low level driver to verify the settings. */ if (uport->ops->verify_port) retval = uport->ops->verify_port(uport, new_info); if ((new_info->irq >= nr_irqs) || (new_info->irq < 0) || (new_info->baud_base < 9600)) retval = -EINVAL; if (retval) goto exit; if (change_port || change_irq) { retval = -EBUSY; /* * Make sure that we are the sole user of this port. */ if (tty_port_users(port) > 1) goto exit; /* * We need to shutdown the serial port at the old * port/type/irq combination. */ uart_shutdown(tty, state); } if (change_port) { unsigned long old_iobase, old_mapbase; unsigned int old_type, old_iotype, old_hub6, old_shift; old_iobase = uport->iobase; old_mapbase = uport->mapbase; old_type = uport->type; old_hub6 = uport->hub6; old_iotype = uport->iotype; old_shift = uport->regshift; /* * Free and release old regions */ if (old_type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); uport->iobase = new_port; uport->type = new_info->type; uport->hub6 = new_info->hub6; uport->iotype = new_info->io_type; uport->regshift = new_info->iomem_reg_shift; uport->mapbase = (unsigned long)new_info->iomem_base; /* * Claim and map the new regions */ if (uport->type != PORT_UNKNOWN && uport->ops->request_port) { retval = uport->ops->request_port(uport); } else { /* Always success - Jean II */ retval = 0; } /* * If we fail to request resources for the * new port, try to restore the old settings. */ if (retval) { uport->iobase = old_iobase; uport->type = old_type; uport->hub6 = old_hub6; uport->iotype = old_iotype; uport->regshift = old_shift; uport->mapbase = old_mapbase; if (old_type != PORT_UNKNOWN) { retval = uport->ops->request_port(uport); /* * If we failed to restore the old settings, * we fail like this. */ if (retval) uport->type = PORT_UNKNOWN; /* * We failed anyway. */ retval = -EBUSY; } /* Added to return the correct error -Ram Gupta */ goto exit; } } if (change_irq) uport->irq = new_info->irq; if (!(uport->flags & UPF_FIXED_PORT)) uport->uartclk = new_info->baud_base * 16; uport->flags = (uport->flags & ~UPF_CHANGE_MASK) | (new_flags & UPF_CHANGE_MASK); uport->custom_divisor = new_info->custom_divisor; port->close_delay = close_delay; port->closing_wait = closing_wait; if (new_info->xmit_fifo_size) uport->fifosize = new_info->xmit_fifo_size; port->low_latency = (uport->flags & UPF_LOW_LATENCY) ? 1 : 0; check_and_exit: retval = 0; if (uport->type == PORT_UNKNOWN) goto exit; if (tty_port_initialized(port)) { if (((old_flags ^ uport->flags) & UPF_SPD_MASK) || old_custom_divisor != uport->custom_divisor) { /* * If they're setting up a custom divisor or speed, * instead of clearing it, then bitch about it. */ if (uport->flags & UPF_SPD_MASK) { dev_notice_ratelimited(uport->dev, "%s sets custom speed on %s. This is deprecated.\n", current->comm, tty_name(port->tty)); } uart_change_speed(tty, state, NULL); } } else { retval = uart_startup(tty, state, 1); if (retval == 0) tty_port_set_initialized(port, true); if (retval > 0) retval = 0; } exit: return retval; } static int uart_set_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; int retval; down_write(&tty->termios_rwsem); /* * This semaphore protects port->count. It is also * very useful to prevent opens. Also, take the * port configuration semaphore to make sure that a * module insertion/removal doesn't change anything * under us. */ mutex_lock(&port->mutex); retval = uart_set_info(tty, port, state, ss); mutex_unlock(&port->mutex); up_write(&tty->termios_rwsem); return retval; } /** * uart_get_lsr_info - get line status register info * @tty: tty associated with the UART * @state: UART being queried * @value: returned modem value */ static int uart_get_lsr_info(struct tty_struct *tty, struct uart_state *state, unsigned int __user *value) { struct uart_port *uport = uart_port_check(state); unsigned int result; result = uport->ops->tx_empty(uport); /* * If we're about to load something into the transmit * register, we'll pretend the transmitter isn't empty to * avoid a race condition (depending on when the transmit * interrupt happens). */ if (uport->x_char || ((uart_circ_chars_pending(&state->xmit) > 0) && !uart_tx_stopped(uport))) result &= ~TIOCSER_TEMT; return put_user(result, value); } static int uart_tiocmget(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; int result = -EIO; mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport) goto out; if (!tty_io_error(tty)) { result = uport->mctrl; spin_lock_irq(&uport->lock); result |= uport->ops->get_mctrl(uport); spin_unlock_irq(&uport->lock); } out: mutex_unlock(&port->mutex); return result; } static int uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; int ret = -EIO; mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport) goto out; if (!tty_io_error(tty)) { uart_update_mctrl(uport, set, clear); ret = 0; } out: mutex_unlock(&port->mutex); return ret; } static int uart_break_ctl(struct tty_struct *tty, int break_state) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; int ret = -EIO; mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport) goto out; if (uport->type != PORT_UNKNOWN && uport->ops->break_ctl) uport->ops->break_ctl(uport, break_state); ret = 0; out: mutex_unlock(&port->mutex); return ret; } static int uart_do_autoconfig(struct tty_struct *tty, struct uart_state *state) { struct tty_port *port = &state->port; struct uart_port *uport; int flags, ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Take the per-port semaphore. This prevents count from * changing, and hence any extra opens of the port while * we're auto-configuring. */ if (mutex_lock_interruptible(&port->mutex)) return -ERESTARTSYS; uport = uart_port_check(state); if (!uport) { ret = -EIO; goto out; } ret = -EBUSY; if (tty_port_users(port) == 1) { uart_shutdown(tty, state); /* * If we already have a port type configured, * we must release its resources. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); flags = UART_CONFIG_TYPE; if (uport->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; /* * This will claim the ports resources if * a port is found. */ uport->ops->config_port(uport, flags); ret = uart_startup(tty, state, 1); if (ret == 0) tty_port_set_initialized(port, true); if (ret > 0) ret = 0; } out: mutex_unlock(&port->mutex); return ret; } static void uart_enable_ms(struct uart_port *uport) { /* * Force modem status interrupts on */ if (uport->ops->enable_ms) uport->ops->enable_ms(uport); } /* * Wait for any of the 4 modem inputs (DCD,RI,DSR,CTS) to change * - mask passed in arg for lines of interest * (use |'ed TIOCM_RNG/DSR/CD/CTS for masking) * Caller should use TIOCGICOUNT to see which one it was * * FIXME: This wants extracting into a common all driver implementation * of TIOCMWAIT using tty_port. */ static int uart_wait_modem_status(struct uart_state *state, unsigned long arg) { struct uart_port *uport; struct tty_port *port = &state->port; DECLARE_WAITQUEUE(wait, current); struct uart_icount cprev, cnow; int ret; /* * note the counters on entry */ uport = uart_port_ref(state); if (!uport) return -EIO; spin_lock_irq(&uport->lock); memcpy(&cprev, &uport->icount, sizeof(struct uart_icount)); uart_enable_ms(uport); spin_unlock_irq(&uport->lock); add_wait_queue(&port->delta_msr_wait, &wait); for (;;) { spin_lock_irq(&uport->lock); memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); spin_unlock_irq(&uport->lock); set_current_state(TASK_INTERRUPTIBLE); if (((arg & TIOCM_RNG) && (cnow.rng != cprev.rng)) || ((arg & TIOCM_DSR) && (cnow.dsr != cprev.dsr)) || ((arg & TIOCM_CD) && (cnow.dcd != cprev.dcd)) || ((arg & TIOCM_CTS) && (cnow.cts != cprev.cts))) { ret = 0; break; } schedule(); /* see if a signal did it */ if (signal_pending(current)) { ret = -ERESTARTSYS; break; } cprev = cnow; } __set_current_state(TASK_RUNNING); remove_wait_queue(&port->delta_msr_wait, &wait); uart_port_deref(uport); return ret; } /* * Get counter of input serial line interrupts (DCD,RI,DSR,CTS) * Return: write counters to the user passed counter struct * NB: both 1->0 and 0->1 transitions are counted except for * RI where only 0->1 is counted. */ static int uart_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount) { struct uart_state *state = tty->driver_data; struct uart_icount cnow; struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return -EIO; spin_lock_irq(&uport->lock); memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); spin_unlock_irq(&uport->lock); uart_port_deref(uport); icount->cts = cnow.cts; icount->dsr = cnow.dsr; icount->rng = cnow.rng; icount->dcd = cnow.dcd; icount->rx = cnow.rx; icount->tx = cnow.tx; icount->frame = cnow.frame; icount->overrun = cnow.overrun; icount->parity = cnow.parity; icount->brk = cnow.brk; icount->buf_overrun = cnow.buf_overrun; return 0; } static int uart_get_rs485_config(struct uart_port *port, struct serial_rs485 __user *rs485) { unsigned long flags; struct serial_rs485 aux; spin_lock_irqsave(&port->lock, flags); aux = port->rs485; spin_unlock_irqrestore(&port->lock, flags); if (copy_to_user(rs485, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_rs485_config(struct uart_port *port, struct serial_rs485 __user *rs485_user) { struct serial_rs485 rs485; int ret; unsigned long flags; if (!port->rs485_config) return -ENOTTY; if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user))) return -EFAULT; /* pick sane settings if the user hasn't */ if (!(rs485.flags & SER_RS485_RTS_ON_SEND) == !(rs485.flags & SER_RS485_RTS_AFTER_SEND)) { dev_warn_ratelimited(port->dev, "%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n", port->name, port->line); rs485.flags |= SER_RS485_RTS_ON_SEND; rs485.flags &= ~SER_RS485_RTS_AFTER_SEND; } if (rs485.delay_rts_before_send > RS485_MAX_RTS_DELAY) { rs485.delay_rts_before_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%d): RTS delay before sending clamped to %u ms\n", port->name, port->line, rs485.delay_rts_before_send); } if (rs485.delay_rts_after_send > RS485_MAX_RTS_DELAY) { rs485.delay_rts_after_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%d): RTS delay after sending clamped to %u ms\n", port->name, port->line, rs485.delay_rts_after_send); } /* Return clean padding area to userspace */ memset(rs485.padding, 0, sizeof(rs485.padding)); spin_lock_irqsave(&port->lock, flags); ret = port->rs485_config(port, &rs485); if (!ret) { port->rs485 = rs485; /* Reset RTS and other mctrl lines when disabling RS485 */ if (!(rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); } spin_unlock_irqrestore(&port->lock, flags); if (ret) return ret; if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485))) return -EFAULT; return 0; } static int uart_get_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816) { unsigned long flags; struct serial_iso7816 aux; if (!port->iso7816_config) return -ENOTTY; spin_lock_irqsave(&port->lock, flags); aux = port->iso7816; spin_unlock_irqrestore(&port->lock, flags); if (copy_to_user(iso7816, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816_user) { struct serial_iso7816 iso7816; int i, ret; unsigned long flags; if (!port->iso7816_config) return -ENOTTY; if (copy_from_user(&iso7816, iso7816_user, sizeof(*iso7816_user))) return -EFAULT; /* * There are 5 words reserved for future use. Check that userspace * doesn't put stuff in there to prevent breakages in the future. */ for (i = 0; i < 5; i++) if (iso7816.reserved[i]) return -EINVAL; spin_lock_irqsave(&port->lock, flags); ret = port->iso7816_config(port, &iso7816); spin_unlock_irqrestore(&port->lock, flags); if (ret) return ret; if (copy_to_user(iso7816_user, &port->iso7816, sizeof(port->iso7816))) return -EFAULT; return 0; } /* * Called via sys_ioctl. We can use spin_lock_irq() here. */ static int uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; void __user *uarg = (void __user *)arg; int ret = -ENOIOCTLCMD; /* * These ioctls don't rely on the hardware to be present. */ switch (cmd) { case TIOCSERCONFIG: down_write(&tty->termios_rwsem); ret = uart_do_autoconfig(tty, state); up_write(&tty->termios_rwsem); break; } if (ret != -ENOIOCTLCMD) goto out; if (tty_io_error(tty)) { ret = -EIO; goto out; } /* * The following should only be used when hardware is present. */ switch (cmd) { case TIOCMIWAIT: ret = uart_wait_modem_status(state, arg); break; } if (ret != -ENOIOCTLCMD) goto out; mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) { ret = -EIO; goto out_up; } /* * All these rely on hardware being present and need to be * protected against the tty being hung up. */ switch (cmd) { case TIOCSERGETLSR: /* Get line status register */ ret = uart_get_lsr_info(tty, state, uarg); break; case TIOCGRS485: ret = uart_get_rs485_config(uport, uarg); break; case TIOCSRS485: ret = uart_set_rs485_config(uport, uarg); break; case TIOCSISO7816: ret = uart_set_iso7816_config(state->uart_port, uarg); break; case TIOCGISO7816: ret = uart_get_iso7816_config(state->uart_port, uarg); break; default: if (uport->ops->ioctl) ret = uport->ops->ioctl(uport, cmd, arg); break; } out_up: mutex_unlock(&port->mutex); out: return ret; } static void uart_set_ldisc(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *uport; struct tty_port *port = &state->port; if (!tty_port_initialized(port)) return; mutex_lock(&state->port.mutex); uport = uart_port_check(state); if (uport && uport->ops->set_ldisc) uport->ops->set_ldisc(uport, &tty->termios); mutex_unlock(&state->port.mutex); } static void uart_set_termios(struct tty_struct *tty, struct ktermios *old_termios) { struct uart_state *state = tty->driver_data; struct uart_port *uport; unsigned int cflag = tty->termios.c_cflag; unsigned int iflag_mask = IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK; bool sw_changed = false; mutex_lock(&state->port.mutex); uport = uart_port_check(state); if (!uport) goto out; /* * Drivers doing software flow control also need to know * about changes to these input settings. */ if (uport->flags & UPF_SOFT_FLOW) { iflag_mask |= IXANY|IXON|IXOFF; sw_changed = tty->termios.c_cc[VSTART] != old_termios->c_cc[VSTART] || tty->termios.c_cc[VSTOP] != old_termios->c_cc[VSTOP]; } /* * These are the bits that are used to setup various * flags in the low level driver. We can ignore the Bfoo * bits in c_cflag; c_[io]speed will always be set * appropriately by set_termios() in tty_ioctl.c */ if ((cflag ^ old_termios->c_cflag) == 0 && tty->termios.c_ospeed == old_termios->c_ospeed && tty->termios.c_ispeed == old_termios->c_ispeed && ((tty->termios.c_iflag ^ old_termios->c_iflag) & iflag_mask) == 0 && !sw_changed) { goto out; } uart_change_speed(tty, state, old_termios); /* reload cflag from termios; port driver may have overridden flags */ cflag = tty->termios.c_cflag; /* Handle transition to B0 status */ if ((old_termios->c_cflag & CBAUD) && !(cflag & CBAUD)) uart_clear_mctrl(uport, TIOCM_RTS | TIOCM_DTR); /* Handle transition away from B0 status */ else if (!(old_termios->c_cflag & CBAUD) && (cflag & CBAUD)) { unsigned int mask = TIOCM_DTR; if (!(cflag & CRTSCTS) || !tty_throttled(tty)) mask |= TIOCM_RTS; uart_set_mctrl(uport, mask); } out: mutex_unlock(&state->port.mutex); } /* * Calls to uart_close() are serialised via the tty_lock in * drivers/tty/tty_io.c:tty_release() * drivers/tty/tty_io.c:do_tty_hangup() */ static void uart_close(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; if (!state) { struct uart_driver *drv = tty->driver->driver_state; struct tty_port *port; state = drv->state + tty->index; port = &state->port; spin_lock_irq(&port->lock); --port->count; spin_unlock_irq(&port->lock); return; } pr_debug("uart_close(%d) called\n", tty->index); tty_port_close(tty->port, tty, filp); } static void uart_tty_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); char *buf; /* * At this point, we stop accepting input. To do this, we * disable the receive line status interrupts. */ if (WARN(!uport, "detached port still initialized!\n")) return; spin_lock_irq(&uport->lock); uport->ops->stop_rx(uport); spin_unlock_irq(&uport->lock); uart_port_shutdown(port); /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, 0); /* * Free the transmit buffer. */ spin_lock_irq(&uport->lock); buf = state->xmit.buf; state->xmit.buf = NULL; spin_unlock_irq(&uport->lock); if (buf) free_page((unsigned long)buf); uart_change_pm(state, UART_PM_STATE_OFF); } static void uart_wait_until_sent(struct tty_struct *tty, int timeout) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long char_time, expire; port = uart_port_ref(state); if (!port) return; if (port->type == PORT_UNKNOWN || port->fifosize == 0) { uart_port_deref(port); return; } /* * Set the check interval to be 1/5 of the estimated time to * send a single character, and make it at least 1. The check * interval should also be less than the timeout. * * Note: we have to use pretty tight timings here to satisfy * the NIST-PCTS. */ char_time = (port->timeout - HZ/50) / port->fifosize; char_time = char_time / 5; if (char_time == 0) char_time = 1; if (timeout && timeout < char_time) char_time = timeout; /* * If the transmitter hasn't cleared in twice the approximate * amount of time to send the entire FIFO, it probably won't * ever clear. This assumes the UART isn't doing flow * control, which is currently the case. Hence, if it ever * takes longer than port->timeout, this is probably due to a * UART bug of some kind. So, we clamp the timeout parameter at * 2*port->timeout. */ if (timeout == 0 || timeout > 2 * port->timeout) timeout = 2 * port->timeout; expire = jiffies + timeout; pr_debug("uart_wait_until_sent(%d), jiffies=%lu, expire=%lu...\n", port->line, jiffies, expire); /* * Check whether the transmitter is empty every 'char_time'. * 'timeout' / 'expire' give us the maximum amount of time * we wait. */ while (!port->ops->tx_empty(port)) { msleep_interruptible(jiffies_to_msecs(char_time)); if (signal_pending(current)) break; if (time_after(jiffies, expire)) break; } uart_port_deref(port); } /* * Calls to uart_hangup() are serialised by the tty_lock in * drivers/tty/tty_io.c:do_tty_hangup() * This runs from a workqueue and can sleep for a _short_ time only. */ static void uart_hangup(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; unsigned long flags; pr_debug("uart_hangup(%d)\n", tty->index); mutex_lock(&port->mutex); uport = uart_port_check(state); WARN(!uport, "hangup of detached port!\n"); if (tty_port_active(port)) { uart_flush_buffer(tty); uart_shutdown(tty, state); spin_lock_irqsave(&port->lock, flags); port->count = 0; spin_unlock_irqrestore(&port->lock, flags); tty_port_set_active(port, 0); tty_port_tty_set(port, NULL); if (uport && !uart_console(uport)) uart_change_pm(state, UART_PM_STATE_OFF); wake_up_interruptible(&port->open_wait); wake_up_interruptible(&port->delta_msr_wait); } mutex_unlock(&port->mutex); } /* uport == NULL if uart_port has already been removed */ static void uart_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * clear delta_msr_wait queue to avoid mem leaks: we may free * the irq here so the queue might never be woken up. Note * that we won't end up waiting on delta_msr_wait again since * any outstanding file descriptors should be pointing at * hung_up_tty_fops now. */ wake_up_interruptible(&port->delta_msr_wait); /* * Free the IRQ and disable the port. */ if (uport) uport->ops->shutdown(uport); /* * Ensure that the IRQ handler isn't running on another CPU. */ if (uport) synchronize_irq(uport->irq); } static int uart_carrier_raised(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int mctrl; uport = uart_port_ref(state); /* * Should never observe uport == NULL since checks for hangup should * abort the tty_port_block_til_ready() loop before checking for carrier * raised -- but report carrier raised if it does anyway so open will * continue and not sleep */ if (WARN_ON(!uport)) return 1; spin_lock_irq(&uport->lock); uart_enable_ms(uport); mctrl = uport->ops->get_mctrl(uport); spin_unlock_irq(&uport->lock); uart_port_deref(uport); if (mctrl & TIOCM_CAR) return 1; return 0; } static void uart_dtr_rts(struct tty_port *port, int raise) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return; uart_port_dtr_rts(uport, raise); uart_port_deref(uport); } static int uart_install(struct tty_driver *driver, struct tty_struct *tty) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + tty->index; tty->driver_data = state; return tty_standard_install(driver, tty); } /* * Calls to uart_open are serialised by the tty_lock in * drivers/tty/tty_io.c:tty_open() * Note that if this fails, then uart_close() _will_ be called. * * In time, we want to scrap the "opening nonpresent ports" * behaviour and implement an alternative way for setserial * to set base addresses/ports/types. This will allow us to * get rid of a certain amount of extra tests. */ static int uart_open(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; int retval; retval = tty_port_open(&state->port, tty, filp); if (retval > 0) retval = 0; return retval; } static int uart_port_activate(struct tty_port *port, struct tty_struct *tty) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int ret; uport = uart_port_check(state); if (!uport || uport->flags & UPF_DEAD) return -ENXIO; port->low_latency = (uport->flags & UPF_LOW_LATENCY) ? 1 : 0; /* * Start up the serial port. */ ret = uart_startup(tty, state, 0); if (ret > 0) tty_port_set_active(port, 1); return ret; } static const char *uart_type(struct uart_port *port) { const char *str = NULL; if (port->ops->type) str = port->ops->type(port); if (!str) str = "unknown"; return str; } #ifdef CONFIG_PROC_FS static void uart_line_info(struct seq_file *m, struct uart_driver *drv, int i) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; enum uart_pm_state pm_state; struct uart_port *uport; char stat_buf[32]; unsigned int status; int mmio; mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport) goto out; mmio = uport->iotype >= UPIO_MEM; seq_printf(m, "%d: uart:%s %s%08llX irq:%d", uport->line, uart_type(uport), mmio ? "mmio:0x" : "port:", mmio ? (unsigned long long)uport->mapbase : (unsigned long long)uport->iobase, uport->irq); if (uport->type == PORT_UNKNOWN) { seq_putc(m, '\n'); goto out; } if (capable(CAP_SYS_ADMIN)) { pm_state = state->pm_state; if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, UART_PM_STATE_ON); spin_lock_irq(&uport->lock); status = uport->ops->get_mctrl(uport); spin_unlock_irq(&uport->lock); if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, pm_state); seq_printf(m, " tx:%d rx:%d", uport->icount.tx, uport->icount.rx); if (uport->icount.frame) seq_printf(m, " fe:%d", uport->icount.frame); if (uport->icount.parity) seq_printf(m, " pe:%d", uport->icount.parity); if (uport->icount.brk) seq_printf(m, " brk:%d", uport->icount.brk); if (uport->icount.overrun) seq_printf(m, " oe:%d", uport->icount.overrun); if (uport->icount.buf_overrun) seq_printf(m, " bo:%d", uport->icount.buf_overrun); #define INFOBIT(bit, str) \ if (uport->mctrl & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) #define STATBIT(bit, str) \ if (status & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) stat_buf[0] = '\0'; stat_buf[1] = '\0'; INFOBIT(TIOCM_RTS, "|RTS"); STATBIT(TIOCM_CTS, "|CTS"); INFOBIT(TIOCM_DTR, "|DTR"); STATBIT(TIOCM_DSR, "|DSR"); STATBIT(TIOCM_CAR, "|CD"); STATBIT(TIOCM_RNG, "|RI"); if (stat_buf[0]) stat_buf[0] = ' '; seq_puts(m, stat_buf); } seq_putc(m, '\n'); #undef STATBIT #undef INFOBIT out: mutex_unlock(&port->mutex); } static int uart_proc_show(struct seq_file *m, void *v) { struct tty_driver *ttydrv = m->private; struct uart_driver *drv = ttydrv->driver_state; int i; seq_printf(m, "serinfo:1.0 driver%s%s revision:%s\n", "", "", ""); for (i = 0; i < drv->nr; i++) uart_line_info(m, drv, i); return 0; } #endif static void uart_port_spin_lock_init(struct uart_port *port) { spin_lock_init(&port->lock); lockdep_set_class(&port->lock, &port_lock_key); } #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL) /** * uart_console_write - write a console message to a serial port * @port: the port to write the message * @s: array of characters * @count: number of characters in string to write * @putchar: function to write character to port */ void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, int)) { unsigned int i; for (i = 0; i < count; i++, s++) { if (*s == '\n') putchar(port, '\r'); putchar(port, *s); } } EXPORT_SYMBOL_GPL(uart_console_write); /* * Check whether an invalid uart number has been specified, and * if so, search for the first available port that does have * console support. */ struct uart_port * __init uart_get_console(struct uart_port *ports, int nr, struct console *co) { int idx = co->index; if (idx < 0 || idx >= nr || (ports[idx].iobase == 0 && ports[idx].membase == NULL)) for (idx = 0; idx < nr; idx++) if (ports[idx].iobase != 0 || ports[idx].membase != NULL) break; co->index = idx; return ports + idx; } /** * uart_parse_earlycon - Parse earlycon options * @p: ptr to 2nd field (ie., just beyond '<name>,') * @iotype: ptr for decoded iotype (out) * @addr: ptr for decoded mapbase/iobase (out) * @options: ptr for <options> field; NULL if not present (out) * * Decodes earlycon kernel command line parameters of the form * earlycon=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * console=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * The optional form * * earlycon=<name>,0x<addr>,<options> * console=<name>,0x<addr>,<options> * * is also accepted; the returned @iotype will be UPIO_MEM. * * Returns 0 on success or -EINVAL on failure */ int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options) { if (strncmp(p, "mmio,", 5) == 0) { *iotype = UPIO_MEM; p += 5; } else if (strncmp(p, "mmio16,", 7) == 0) { *iotype = UPIO_MEM16; p += 7; } else if (strncmp(p, "mmio32,", 7) == 0) { *iotype = UPIO_MEM32; p += 7; } else if (strncmp(p, "mmio32be,", 9) == 0) { *iotype = UPIO_MEM32BE; p += 9; } else if (strncmp(p, "mmio32native,", 13) == 0) { *iotype = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) ? UPIO_MEM32BE : UPIO_MEM32; p += 13; } else if (strncmp(p, "io,", 3) == 0) { *iotype = UPIO_PORT; p += 3; } else if (strncmp(p, "0x", 2) == 0) { *iotype = UPIO_MEM; } else { return -EINVAL; } /* * Before you replace it with kstrtoull(), think about options separator * (',') it will not tolerate */ *addr = simple_strtoull(p, NULL, 0); p = strchr(p, ','); if (p) p++; *options = p; return 0; } EXPORT_SYMBOL_GPL(uart_parse_earlycon); /** * uart_parse_options - Parse serial port baud/parity/bits/flow control. * @options: pointer to option string * @baud: pointer to an 'int' variable for the baud rate. * @parity: pointer to an 'int' variable for the parity. * @bits: pointer to an 'int' variable for the number of data bits. * @flow: pointer to an 'int' variable for the flow control character. * * uart_parse_options decodes a string containing the serial console * options. The format of the string is <baud><parity><bits><flow>, * eg: 115200n8r */ void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow) { const char *s = options; *baud = simple_strtoul(s, NULL, 10); while (*s >= '0' && *s <= '9') s++; if (*s) *parity = *s++; if (*s) *bits = *s++ - '0'; if (*s) *flow = *s; } EXPORT_SYMBOL_GPL(uart_parse_options); /** * uart_set_options - setup the serial console parameters * @port: pointer to the serial ports uart_port structure * @co: console pointer * @baud: baud rate * @parity: parity character - 'n' (none), 'o' (odd), 'e' (even) * @bits: number of data bits * @flow: flow control character - 'r' (rts) */ int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow) { struct ktermios termios; static struct ktermios dummy; /* * Ensure that the serial-console lock is initialised early. * * Note that the console-enabled check is needed because of kgdboc, * which can end up calling uart_set_options() for an already enabled * console via tty_find_polling_driver() and uart_poll_init(). */ if (!uart_console_enabled(port) && !port->console_reinit) uart_port_spin_lock_init(port); memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag |= CREAD | HUPCL | CLOCAL; tty_termios_encode_baud_rate(&termios, baud, baud); if (bits == 7) termios.c_cflag |= CS7; else termios.c_cflag |= CS8; switch (parity) { case 'o': case 'O': termios.c_cflag |= PARODD; fallthrough; case 'e': case 'E': termios.c_cflag |= PARENB; break; } if (flow == 'r') termios.c_cflag |= CRTSCTS; /* * some uarts on other side don't support no flow control. * So we set * DTR in host uart to make them happy */ port->mctrl |= TIOCM_DTR; port->ops->set_termios(port, &termios, &dummy); /* * Allow the setting of the UART parameters with a NULL console * too: */ if (co) { co->cflag = termios.c_cflag; co->ispeed = termios.c_ispeed; co->ospeed = termios.c_ospeed; } return 0; } EXPORT_SYMBOL_GPL(uart_set_options); #endif /* CONFIG_SERIAL_CORE_CONSOLE */ /** * uart_change_pm - set power state of the port * * @state: port descriptor * @pm_state: new state * * Locking: port->mutex has to be held */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state) { struct uart_port *port = uart_port_check(state); if (state->pm_state != pm_state) { if (port && port->ops->pm) port->ops->pm(port, pm_state, state->pm_state); state->pm_state = pm_state; } } struct uart_match { struct uart_port *port; struct uart_driver *driver; }; static int serial_match_port(struct device *dev, void *data) { struct uart_match *match = data; struct tty_driver *tty_drv = match->driver->tty_driver; dev_t devt = MKDEV(tty_drv->major, tty_drv->minor_start) + match->port->line; return dev->devt == devt; /* Actually, only one tty per port */ } int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; mutex_lock(&port->mutex); tty_dev = device_find_child(uport->dev, &match, serial_match_port); if (tty_dev && device_may_wakeup(tty_dev)) { enable_irq_wake(uport->irq); put_device(tty_dev); mutex_unlock(&port->mutex); return 0; } put_device(tty_dev); /* Nothing to do if the console is not suspending */ if (!console_suspend_enabled && uart_console(uport)) goto unlock; uport->suspended = 1; if (tty_port_initialized(port)) { const struct uart_ops *ops = uport->ops; int tries; tty_port_set_suspended(port, 1); tty_port_set_initialized(port, 0); spin_lock_irq(&uport->lock); ops->stop_tx(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); ops->stop_rx(uport); spin_unlock_irq(&uport->lock); /* * Wait for the transmitter to empty. */ for (tries = 3; !ops->tx_empty(uport) && tries; tries--) msleep(10); if (!tries) dev_err(uport->dev, "%s: Unable to drain transmitter\n", uport->name); ops->shutdown(uport); } /* * Disable the console device before suspending. */ if (uart_console(uport)) console_stop(uport->cons); uart_change_pm(state, UART_PM_STATE_OFF); unlock: mutex_unlock(&port->mutex); return 0; } int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; struct ktermios termios; mutex_lock(&port->mutex); tty_dev = device_find_child(uport->dev, &match, serial_match_port); if (!uport->suspended && device_may_wakeup(tty_dev)) { if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq)))) disable_irq_wake(uport->irq); put_device(tty_dev); mutex_unlock(&port->mutex); return 0; } put_device(tty_dev); uport->suspended = 0; /* * Re-enable the console device after suspending. */ if (uart_console(uport)) { /* * First try to use the console cflag setting. */ memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag = uport->cons->cflag; termios.c_ispeed = uport->cons->ispeed; termios.c_ospeed = uport->cons->ospeed; /* * If that's unset, use the tty termios setting. */ if (port->tty && termios.c_cflag == 0) termios = port->tty->termios; if (console_suspend_enabled) uart_change_pm(state, UART_PM_STATE_ON); uport->ops->set_termios(uport, &termios, NULL); if (console_suspend_enabled) console_start(uport->cons); } if (tty_port_suspended(port)) { const struct uart_ops *ops = uport->ops; int ret; uart_change_pm(state, UART_PM_STATE_ON); spin_lock_irq(&uport->lock); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); spin_unlock_irq(&uport->lock); if (console_suspend_enabled || !uart_console(uport)) { /* Protected by port mutex for now */ struct tty_struct *tty = port->tty; ret = ops->startup(uport); if (ret == 0) { if (tty) uart_change_speed(tty, state, NULL); spin_lock_irq(&uport->lock); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, uport->mctrl); else uport->rs485_config(uport, &uport->rs485); ops->start_tx(uport); spin_unlock_irq(&uport->lock); tty_port_set_initialized(port, 1); } else { /* * Failed to resume - maybe hardware went away? * Clear the "initialized" flag so we won't try * to call the low level drivers shutdown method. */ uart_shutdown(tty, state); } } tty_port_set_suspended(port, 0); } mutex_unlock(&port->mutex); return 0; } static inline void uart_report_port(struct uart_driver *drv, struct uart_port *port) { char address[64]; switch (port->iotype) { case UPIO_PORT: snprintf(address, sizeof(address), "I/O 0x%lx", port->iobase); break; case UPIO_HUB6: snprintf(address, sizeof(address), "I/O 0x%lx offset 0x%x", port->iobase, port->hub6); break; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: snprintf(address, sizeof(address), "MMIO 0x%llx", (unsigned long long)port->mapbase); break; default: strlcpy(address, "*unknown*", sizeof(address)); break; } pr_info("%s%s%s at %s (irq = %d, base_baud = %d) is a %s\n", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, address, port->irq, port->uartclk / 16, uart_type(port)); } static void uart_configure_port(struct uart_driver *drv, struct uart_state *state, struct uart_port *port) { unsigned int flags; /* * If there isn't a port here, don't do anything further. */ if (!port->iobase && !port->mapbase && !port->membase) return; /* * Now do the auto configuration stuff. Note that config_port * is expected to claim the resources and map the port for us. */ flags = 0; if (port->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; if (port->flags & UPF_BOOT_AUTOCONF) { if (!(port->flags & UPF_FIXED_TYPE)) { port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); port->ops->config_port(port, flags); if (uart_console(port)) console_unlock(); } if (port->type != PORT_UNKNOWN) { unsigned long flags; uart_report_port(drv, port); /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); /* * Ensure that the modem control lines are de-activated. * keep the DTR setting that is set in uart_set_options() * We probably don't need a spinlock around this, but */ spin_lock_irqsave(&port->lock, flags); port->mctrl &= TIOCM_DTR; if (!(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); else port->rs485_config(port, &port->rs485); spin_unlock_irqrestore(&port->lock, flags); if (uart_console(port)) console_unlock(); /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. * It may be that the port was not available. */ if (port->cons && !(port->cons->flags & CON_ENABLED)) register_console(port->cons); /* * Power down all ports by default, except the * console if we have one. */ if (!uart_console(port)) uart_change_pm(state, UART_PM_STATE_OFF); } } #ifdef CONFIG_CONSOLE_POLL static int uart_poll_init(struct tty_driver *driver, int line, char *options) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct tty_port *tport; struct uart_port *port; int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; int ret = 0; tport = &state->port; mutex_lock(&tport->mutex); port = uart_port_check(state); if (!port || !(port->ops->poll_get_char && port->ops->poll_put_char)) { ret = -1; goto out; } if (port->ops->poll_init) { /* * We don't set initialized as we only initialized the hw, * e.g. state->xmit is still uninitialized. */ if (!tty_port_initialized(tport)) ret = port->ops->poll_init(port); } if (!ret && options) { uart_parse_options(options, &baud, &parity, &bits, &flow); ret = uart_set_options(port, NULL, baud, parity, bits, flow); } out: mutex_unlock(&tport->mutex); return ret; } static int uart_poll_get_char(struct tty_driver *driver, int line) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; int ret = -1; port = uart_port_ref(state); if (port) { ret = port->ops->poll_get_char(port); uart_port_deref(port); } return ret; } static void uart_poll_put_char(struct tty_driver *driver, int line, char ch) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (ch == '\n') port->ops->poll_put_char(port, '\r'); port->ops->poll_put_char(port, ch); uart_port_deref(port); } #endif static const struct tty_operations uart_ops = { .install = uart_install, .open = uart_open, .close = uart_close, .write = uart_write, .put_char = uart_put_char, .flush_chars = uart_flush_chars, .write_room = uart_write_room, .chars_in_buffer= uart_chars_in_buffer, .flush_buffer = uart_flush_buffer, .ioctl = uart_ioctl, .throttle = uart_throttle, .unthrottle = uart_unthrottle, .send_xchar = uart_send_xchar, .set_termios = uart_set_termios, .set_ldisc = uart_set_ldisc, .stop = uart_stop, .start = uart_start, .hangup = uart_hangup, .break_ctl = uart_break_ctl, .wait_until_sent= uart_wait_until_sent, #ifdef CONFIG_PROC_FS .proc_show = uart_proc_show, #endif .tiocmget = uart_tiocmget, .tiocmset = uart_tiocmset, .set_serial = uart_set_info_user, .get_serial = uart_get_info_user, .get_icount = uart_get_icount, #ifdef CONFIG_CONSOLE_POLL .poll_init = uart_poll_init, .poll_get_char = uart_poll_get_char, .poll_put_char = uart_poll_put_char, #endif }; static const struct tty_port_operations uart_port_ops = { .carrier_raised = uart_carrier_raised, .dtr_rts = uart_dtr_rts, .activate = uart_port_activate, .shutdown = uart_tty_port_shutdown, }; /** * uart_register_driver - register a driver with the uart core layer * @drv: low level driver structure * * Register a uart driver with the core driver. We in turn register * with the tty layer, and initialise the core driver per-port state. * * We have a proc file in /proc/tty/driver which is named after the * normal driver. * * drv->port should be NULL, and the per-port structures should be * registered using uart_add_one_port after this call has succeeded. */ int uart_register_driver(struct uart_driver *drv) { struct tty_driver *normal; int i, retval = -ENOMEM; BUG_ON(drv->state); /* * Maybe we should be using a slab cache for this, especially if * we have a large number of ports to handle. */ drv->state = kcalloc(drv->nr, sizeof(struct uart_state), GFP_KERNEL); if (!drv->state) goto out; normal = alloc_tty_driver(drv->nr); if (!normal) goto out_kfree; drv->tty_driver = normal; normal->driver_name = drv->driver_name; normal->name = drv->dev_name; normal->major = drv->major; normal->minor_start = drv->minor; normal->type = TTY_DRIVER_TYPE_SERIAL; normal->subtype = SERIAL_TYPE_NORMAL; normal->init_termios = tty_std_termios; normal->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; normal->init_termios.c_ispeed = normal->init_termios.c_ospeed = 9600; normal->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV; normal->driver_state = drv; tty_set_operations(normal, &uart_ops); /* * Initialise the UART state(s). */ for (i = 0; i < drv->nr; i++) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; tty_port_init(port); port->ops = &uart_port_ops; } retval = tty_register_driver(normal); if (retval >= 0) return retval; for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); put_tty_driver(normal); out_kfree: kfree(drv->state); out: return retval; } /** * uart_unregister_driver - remove a driver from the uart core layer * @drv: low level driver structure * * Remove all references to a driver from the core driver. The low * level driver must have removed all its ports via the * uart_remove_one_port() if it registered them with uart_add_one_port(). * (ie, drv->port == NULL) */ void uart_unregister_driver(struct uart_driver *drv) { struct tty_driver *p = drv->tty_driver; unsigned int i; tty_unregister_driver(p); put_tty_driver(p); for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); kfree(drv->state); drv->state = NULL; drv->tty_driver = NULL; } struct tty_driver *uart_console_device(struct console *co, int *index) { struct uart_driver *p = co->data; *index = co->index; return p->tty_driver; } EXPORT_SYMBOL_GPL(uart_console_device); static ssize_t uartclk_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.baud_base * 16); } static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.type); } static ssize_t line_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.line); } static ssize_t port_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); unsigned long ioaddr; uart_get_info(port, &tmp); ioaddr = tmp.port; if (HIGH_BITS_OFFSET) ioaddr |= (unsigned long)tmp.port_high << HIGH_BITS_OFFSET; return sprintf(buf, "0x%lX\n", ioaddr); } static ssize_t irq_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.irq); } static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%X\n", tmp.flags); } static ssize_t xmit_fifo_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.xmit_fifo_size); } static ssize_t close_delay_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.close_delay); } static ssize_t closing_wait_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.closing_wait); } static ssize_t custom_divisor_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.custom_divisor); } static ssize_t io_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.io_type); } static ssize_t iomem_base_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%lX\n", (unsigned long)tmp.iomem_base); } static ssize_t iomem_reg_shift_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.iomem_reg_shift); } static ssize_t console_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool console = false; mutex_lock(&port->mutex); uport = uart_port_check(state); if (uport) console = uart_console_enabled(uport); mutex_unlock(&port->mutex); return sprintf(buf, "%c\n", console ? 'Y' : 'N'); } static ssize_t console_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool oldconsole, newconsole; int ret; ret = kstrtobool(buf, &newconsole); if (ret) return ret; mutex_lock(&port->mutex); uport = uart_port_check(state); if (uport) { oldconsole = uart_console_enabled(uport); if (oldconsole && !newconsole) { ret = unregister_console(uport->cons); } else if (!oldconsole && newconsole) { if (uart_console(uport)) { uport->console_reinit = 1; register_console(uport->cons); } else { ret = -ENOENT; } } } else { ret = -ENXIO; } mutex_unlock(&port->mutex); return ret < 0 ? ret : count; } static DEVICE_ATTR_RO(uartclk); static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(line); static DEVICE_ATTR_RO(port); static DEVICE_ATTR_RO(irq); static DEVICE_ATTR_RO(flags); static DEVICE_ATTR_RO(xmit_fifo_size); static DEVICE_ATTR_RO(close_delay); static DEVICE_ATTR_RO(closing_wait); static DEVICE_ATTR_RO(custom_divisor); static DEVICE_ATTR_RO(io_type); static DEVICE_ATTR_RO(iomem_base); static DEVICE_ATTR_RO(iomem_reg_shift); static DEVICE_ATTR_RW(console); static struct attribute *tty_dev_attrs[] = { &dev_attr_uartclk.attr, &dev_attr_type.attr, &dev_attr_line.attr, &dev_attr_port.attr, &dev_attr_irq.attr, &dev_attr_flags.attr, &dev_attr_xmit_fifo_size.attr, &dev_attr_close_delay.attr, &dev_attr_closing_wait.attr, &dev_attr_custom_divisor.attr, &dev_attr_io_type.attr, &dev_attr_iomem_base.attr, &dev_attr_iomem_reg_shift.attr, &dev_attr_console.attr, NULL }; static const struct attribute_group tty_dev_attr_group = { .attrs = tty_dev_attrs, }; /** * uart_add_one_port - attach a driver-defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure to use for this port. * * This allows the driver to register its own uart_port structure * with the core driver. The main purpose is to allow the low * level uart drivers to expand uart_port, rather than having yet * more levels of structures. */ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state; struct tty_port *port; int ret = 0; struct device *tty_dev; int num_groups; BUG_ON(in_interrupt()); if (uport->line >= drv->nr) return -EINVAL; state = drv->state + uport->line; port = &state->port; mutex_lock(&port_mutex); mutex_lock(&port->mutex); if (state->uart_port) { ret = -EINVAL; goto out; } /* Link the port to the driver state table and vice versa */ atomic_set(&state->refcount, 1); init_waitqueue_head(&state->remove_wait); state->uart_port = uport; uport->state = state; state->pm_state = UART_PM_STATE_UNDEFINED; uport->cons = drv->cons; uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name, drv->tty_driver->name_base + uport->line); if (!uport->name) { ret = -ENOMEM; goto out; } /* * If this port is in use as a console then the spinlock is already * initialised. */ if (!uart_console_enabled(uport)) uart_port_spin_lock_init(uport); if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); num_groups = 2; if (uport->attr_group) num_groups++; uport->tty_groups = kcalloc(num_groups, sizeof(*uport->tty_groups), GFP_KERNEL); if (!uport->tty_groups) { ret = -ENOMEM; goto out; } uport->tty_groups[0] = &tty_dev_attr_group; if (uport->attr_group) uport->tty_groups[1] = uport->attr_group; /* * Register the port whether it's detected or not. This allows * setserial to be used to alter this port's parameters. */ tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver, uport->line, uport->dev, port, uport->tty_groups); if (!IS_ERR(tty_dev)) { device_set_wakeup_capable(tty_dev, 1); } else { dev_err(uport->dev, "Cannot register tty device on line %d\n", uport->line); } /* * Ensure UPF_DEAD is not set. */ uport->flags &= ~UPF_DEAD; out: mutex_unlock(&port->mutex); mutex_unlock(&port_mutex); return ret; } /** * uart_remove_one_port - detach a driver defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure for this port * * This unhooks (and hangs up) the specified port structure from the * core driver. No further calls will be made to the low-level code * for this port. */ int uart_remove_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct uart_port *uart_port; struct tty_struct *tty; int ret = 0; BUG_ON(in_interrupt()); mutex_lock(&port_mutex); /* * Mark the port "dead" - this prevents any opens from * succeeding while we shut down the port. */ mutex_lock(&port->mutex); uart_port = uart_port_check(state); if (uart_port != uport) dev_alert(uport->dev, "Removing wrong port: %p != %p\n", uart_port, uport); if (!uart_port) { mutex_unlock(&port->mutex); ret = -EINVAL; goto out; } uport->flags |= UPF_DEAD; mutex_unlock(&port->mutex); /* * Remove the devices from the tty layer */ tty_port_unregister_device(port, drv->tty_driver, uport->line); tty = tty_port_tty_get(port); if (tty) { tty_vhangup(port->tty); tty_kref_put(tty); } /* * If the port is used as a console, unregister it */ if (uart_console(uport)) unregister_console(uport->cons); /* * Free the port IO and memory resources, if any. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); kfree(uport->tty_groups); kfree(uport->name); /* * Indicate that there isn't a port here anymore. */ uport->type = PORT_UNKNOWN; mutex_lock(&port->mutex); WARN_ON(atomic_dec_return(&state->refcount) < 0); wait_event(state->remove_wait, !atomic_read(&state->refcount)); state->uart_port = NULL; mutex_unlock(&port->mutex); out: mutex_unlock(&port_mutex); return ret; } /* * Are the two ports equivalent? */ int uart_match_port(struct uart_port *port1, struct uart_port *port2) { if (port1->iotype != port2->iotype) return 0; switch (port1->iotype) { case UPIO_PORT: return (port1->iobase == port2->iobase); case UPIO_HUB6: return (port1->iobase == port2->iobase) && (port1->hub6 == port2->hub6); case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: return (port1->mapbase == port2->mapbase); } return 0; } EXPORT_SYMBOL(uart_match_port); /** * uart_handle_dcd_change - handle a change of carrier detect state * @uport: uart_port structure for the open port * @status: new carrier detect status, nonzero if active * * Caller must hold uport->lock */ void uart_handle_dcd_change(struct uart_port *uport, unsigned int status) { struct tty_port *port = &uport->state->port; struct tty_struct *tty = port->tty; struct tty_ldisc *ld; lockdep_assert_held_once(&uport->lock); if (tty) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) ld->ops->dcd_change(tty, status); tty_ldisc_deref(ld); } } uport->icount.dcd++; if (uart_dcd_enabled(uport)) { if (status) wake_up_interruptible(&port->open_wait); else if (tty) tty_hangup(tty); } } EXPORT_SYMBOL_GPL(uart_handle_dcd_change); /** * uart_handle_cts_change - handle a change of clear-to-send state * @uport: uart_port structure for the open port * @status: new clear to send status, nonzero if active * * Caller must hold uport->lock */ void uart_handle_cts_change(struct uart_port *uport, unsigned int status) { lockdep_assert_held_once(&uport->lock); uport->icount.cts++; if (uart_softcts_mode(uport)) { if (uport->hw_stopped) { if (status) { uport->hw_stopped = 0; uport->ops->start_tx(uport); uart_write_wakeup(uport); } } else { if (!status) { uport->hw_stopped = 1; uport->ops->stop_tx(uport); } } } } EXPORT_SYMBOL_GPL(uart_handle_cts_change); /** * uart_insert_char - push a char to the uart layer * * User is responsible to call tty_flip_buffer_push when they are done with * insertion. * * @port: corresponding port * @status: state of the serial port RX buffer (LSR for 8250) * @overrun: mask of overrun bits in @status * @ch: character to push * @flag: flag for the character (see TTY_NORMAL and friends) */ void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag) { struct tty_port *tport = &port->state->port; if ((status & port->ignore_status_mask & ~overrun) == 0) if (tty_insert_flip_char(tport, ch, flag) == 0) ++port->icount.buf_overrun; /* * Overrun is special. Since it's reported immediately, * it doesn't affect the current character. */ if (status & ~port->ignore_status_mask & overrun) if (tty_insert_flip_char(tport, 0, TTY_OVERRUN) == 0) ++port->icount.buf_overrun; } EXPORT_SYMBOL_GPL(uart_insert_char); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL static const char sysrq_toggle_seq[] = CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE; static void uart_sysrq_on(struct work_struct *w) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); sysrq_toggle_support(1); pr_info("SysRq is enabled by magic sequence '%*pE' on serial\n", sysrq_toggle_seq_len, sysrq_toggle_seq); } static DECLARE_WORK(sysrq_enable_work, uart_sysrq_on); /** * uart_try_toggle_sysrq - Enables SysRq from serial line * @port: uart_port structure where char(s) after BREAK met * @ch: new character in the sequence after received BREAK * * Enables magic SysRq when the required sequence is met on port * (see CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE). * * Returns false if @ch is out of enabling sequence and should be * handled some other way, true if @ch was consumed. */ bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); if (!sysrq_toggle_seq_len) return false; BUILD_BUG_ON(ARRAY_SIZE(sysrq_toggle_seq) >= U8_MAX); if (sysrq_toggle_seq[port->sysrq_seq] != ch) { port->sysrq_seq = 0; return false; } if (++port->sysrq_seq < sysrq_toggle_seq_len) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return true; } schedule_work(&sysrq_enable_work); port->sysrq = 0; return true; } EXPORT_SYMBOL_GPL(uart_try_toggle_sysrq); #endif EXPORT_SYMBOL(uart_write_wakeup); EXPORT_SYMBOL(uart_register_driver); EXPORT_SYMBOL(uart_unregister_driver); EXPORT_SYMBOL(uart_suspend_port); EXPORT_SYMBOL(uart_resume_port); EXPORT_SYMBOL(uart_add_one_port); EXPORT_SYMBOL(uart_remove_one_port); /** * uart_get_rs485_mode() - retrieve rs485 properties for given uart * @port: uart device's target port * * This function implements the device tree binding described in * Documentation/devicetree/bindings/serial/rs485.txt. */ int uart_get_rs485_mode(struct uart_port *port) { struct serial_rs485 *rs485conf = &port->rs485; struct device *dev = port->dev; u32 rs485_delay[2]; int ret; ret = device_property_read_u32_array(dev, "rs485-rts-delay", rs485_delay, 2); if (!ret) { rs485conf->delay_rts_before_send = rs485_delay[0]; rs485conf->delay_rts_after_send = rs485_delay[1]; } else { rs485conf->delay_rts_before_send = 0; rs485conf->delay_rts_after_send = 0; } /* * Clear full-duplex and enabled flags, set RTS polarity to active high * to get to a defined state with the following properties: */ rs485conf->flags &= ~(SER_RS485_RX_DURING_TX | SER_RS485_ENABLED | SER_RS485_TERMINATE_BUS | SER_RS485_RTS_AFTER_SEND); rs485conf->flags |= SER_RS485_RTS_ON_SEND; if (device_property_read_bool(dev, "rs485-rx-during-tx")) rs485conf->flags |= SER_RS485_RX_DURING_TX; if (device_property_read_bool(dev, "linux,rs485-enabled-at-boot-time")) rs485conf->flags |= SER_RS485_ENABLED; if (device_property_read_bool(dev, "rs485-rts-active-low")) { rs485conf->flags &= ~SER_RS485_RTS_ON_SEND; rs485conf->flags |= SER_RS485_RTS_AFTER_SEND; } /* * Disabling termination by default is the safe choice: Else if many * bus participants enable it, no communication is possible at all. * Works fine for short cables and users may enable for longer cables. */ port->rs485_term_gpio = devm_gpiod_get_optional(dev, "rs485-term", GPIOD_OUT_LOW); if (IS_ERR(port->rs485_term_gpio)) { ret = PTR_ERR(port->rs485_term_gpio); port->rs485_term_gpio = NULL; return dev_err_probe(dev, ret, "Cannot get rs485-term-gpios\n"); } return 0; } EXPORT_SYMBOL_GPL(uart_get_rs485_mode); MODULE_DESCRIPTION("Serial driver core"); MODULE_LICENSE("GPL"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SMP_H #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ #include <linux/cpumask.h> #include <asm/percpu.h> #include <asm/thread_info.h> #include <asm/cpumask.h> extern int smp_num_siblings; extern unsigned int num_processors; DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); /* cpus sharing the last level cache: */ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); } DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid); #endif struct task_struct; struct smp_ops { void (*smp_prepare_boot_cpu)(void); void (*smp_prepare_cpus)(unsigned max_cpus); void (*smp_cpus_done)(unsigned max_cpus); void (*stop_other_cpus)(int wait); void (*crash_stop_other_cpus)(void); void (*smp_send_reschedule)(int cpu); int (*cpu_up)(unsigned cpu, struct task_struct *tidle); int (*cpu_disable)(void); void (*cpu_die)(unsigned int cpu); void (*play_dead)(void); void (*send_call_func_ipi)(const struct cpumask *mask); void (*send_call_func_single_ipi)(int cpu); }; /* Globals due to paravirt */ extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP extern struct smp_ops smp_ops; static inline void smp_send_stop(void) { smp_ops.stop_other_cpus(0); } static inline void stop_other_cpus(void) { smp_ops.stop_other_cpus(1); } static inline void smp_prepare_boot_cpu(void) { smp_ops.smp_prepare_boot_cpu(); } static inline void smp_prepare_cpus(unsigned int max_cpus) { smp_ops.smp_prepare_cpus(max_cpus); } static inline void smp_cpus_done(unsigned int max_cpus) { smp_ops.smp_cpus_done(max_cpus); } static inline int __cpu_up(unsigned int cpu, struct task_struct *tidle) { return smp_ops.cpu_up(cpu, tidle); } static inline int __cpu_disable(void) { return smp_ops.cpu_disable(); } static inline void __cpu_die(unsigned int cpu) { smp_ops.cpu_die(cpu); } static inline void play_dead(void) { smp_ops.play_dead(); } static inline void smp_send_reschedule(int cpu) { smp_ops.smp_send_reschedule(cpu); } static inline void arch_send_call_function_single_ipi(int cpu) { smp_ops.send_call_func_single_ipi(cpu); } static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { smp_ops.send_call_func_ipi(mask); } void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); void hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); void cond_wakeup_cpu0(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); asmlinkage __visible void smp_reboot_interrupt(void); __visible void smp_reschedule_interrupt(struct pt_regs *regs); __visible void smp_call_function_interrupt(struct pt_regs *regs); __visible void smp_call_function_single_interrupt(struct pt_regs *r); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu) /* * This function is needed by all SMP systems. It must _always_ be valid * from the initial startup. We map APIC_BASE very early in page_setup(), * so this is correct in the x86 case. */ #define raw_smp_processor_id() this_cpu_read(cpu_number) #define __smp_processor_id() __this_cpu_read(cpu_number) #ifdef CONFIG_X86_32 extern int safe_smp_processor_id(void); #else # define safe_smp_processor_id() smp_processor_id() #endif #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) { wbinvd(); return 0; } #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; #ifdef CONFIG_X86_LOCAL_APIC extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ #define hard_smp_processor_id() 0 #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_DEBUG_NMI_SELFTEST extern void nmi_selftest(void); #else #define nmi_selftest() do { } while (0) #endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMP_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_H #define BLK_MQ_H #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/srcu.h> struct blk_mq_tags; struct blk_flush_queue; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device */ struct blk_mq_hw_ctx { struct { /** @lock: Protects the dispatch list. */ spinlock_t lock; /** * @dispatch: Used for requests that are ready to be * dispatched to the hardware but for some reason (e.g. lack of * resources) could not be sent to the hardware. As soon as the * driver can send new requests, requests at this list will * be sent first for a fairer dispatch. */ struct list_head dispatch; /** * @state: BLK_MQ_S_* flags. Defines the state of the hw * queue (active, scheduled to restart, stopped). */ unsigned long state; } ____cacheline_aligned_in_smp; /** * @run_work: Used for scheduling a hardware queue run at a later time. */ struct delayed_work run_work; /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; /** * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU * selection from @cpumask. */ int next_cpu; /** * @next_cpu_batch: Counter of how many works left in the batch before * changing to the next CPU. */ int next_cpu_batch; /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ unsigned long flags; /** * @sched_data: Pointer owned by the IO scheduler attached to a request * queue. It's up to the IO scheduler how to use this pointer. */ void *sched_data; /** * @queue: Pointer to the request queue that owns this hardware context. */ struct request_queue *queue; /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; /** * @driver_data: Pointer to data owned by the block driver that created * this hctx */ void *driver_data; /** * @ctx_map: Bitmap for each software queue. If bit is on, there is a * pending request in that software queue. */ struct sbitmap ctx_map; /** * @dispatch_from: Software queue to be used when no scheduler was * selected. */ struct blk_mq_ctx *dispatch_from; /** * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to * decide if the hw_queue is busy using Exponential Weighted Moving * Average algorithm. */ unsigned int dispatch_busy; /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; /** * @dispatch_wait: Waitqueue to put requests when there is no tag * available at the moment, to wait for another try in the future. */ wait_queue_entry_t dispatch_wait; /** * @wait_index: Index of next available dispatch_wait queue to insert * requests. */ atomic_t wait_index; /** * @tags: Tags owned by the block driver. A tag at this set is only * assigned when a request is dispatched from a hardware queue. */ struct blk_mq_tags *tags; /** * @sched_tags: Tags owned by I/O scheduler. If there is an I/O * scheduler associated with a request queue, a tag is assigned when * that request is allocated. Else, this member is not used. */ struct blk_mq_tags *sched_tags; /** @queued: Number of queued requests. */ unsigned long queued; /** @run: Number of dispatched requests. */ unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 /** @dispatched: Number of dispatch requests by queue. */ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; /** * @nr_active: Number of active requests. Only used when a tag set is * shared across request queues. */ atomic_t nr_active; /** * @elevator_queued: Number of queued requests on hctx. */ atomic_t elevator_queued; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; /** @poll_considered: Count times blk_poll() was called. */ unsigned long poll_considered; /** @poll_invoked: Count how many requests blk_poll() polled. */ unsigned long poll_invoked; /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named * as cpu<cpu_number>. */ struct dentry *debugfs_dir; /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif /** * @hctx_list: if this hctx is not in use, this is an entry in * q->unused_hctx_list. */ struct list_head hctx_list; /** * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also * blk_mq_hw_ctx_size(). */ struct srcu_struct srcu[]; }; /** * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). * @nr_queues: Number of hardware queues to map CPU IDs onto. * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe * driver to map each hardware queue type (enum hctx_type) onto a distinct * set of hardware queues. */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; /** * enum hctx_type - Type of hardware queue * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. * @HCTX_TYPE_READ: Just for READ I/O. * @HCTX_TYPE_POLL: Polled I/O of any kind. * @HCTX_MAX_TYPES: Number of types of hctx. */ enum hctx_type { HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; /** * struct blk_mq_tag_set - tag set that can be shared between request queues * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the * same size, and it's perfectly legal to share maps between * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. * @ops: Pointers to functions that implement block driver behavior. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag * allocations. * @cmd_size: Number of additional bytes to allocate per request. The block * driver owns these additional bytes. * @numa_node: NUMA node the storage adapter has been connected to. * @timeout: Request processing timeout in jiffies. * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. * @active_queues_shared_sbitmap: * number of active request queues per tag set. * @__bitmap_tags: A shared tags sbitmap, used over all hctx's * @__breserved_tags: * A shared reserved tags sbitmap, used over all hctx's * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. */ struct blk_mq_tag_set { struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; const struct blk_mq_ops *ops; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; unsigned int cmd_size; int numa_node; unsigned int timeout; unsigned int flags; void *driver_data; atomic_t active_queues_shared_sbitmap; struct sbitmap_queue __bitmap_tags; struct sbitmap_queue __breserved_tags; struct blk_mq_tags **tags; struct mutex tag_list_lock; struct list_head tag_list; }; /** * struct blk_mq_queue_data - Data about a request inserted in a queue * * @rq: Request pointer. * @last: If it is the last request in the queue. */ struct blk_mq_queue_data { struct request *rq; bool last; }; typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); /** * struct blk_mq_ops - Callback functions that implements block driver * behaviour. */ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit * requests to hardware, it must define this function. In case of errors * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ void (*commit_rqs)(struct blk_mq_hw_ctx *); /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ bool (*get_budget)(struct request_queue *); /** * @put_budget: Release the reserved budget. */ void (*put_budget)(struct request_queue *); /** * @timeout: Called on request timeout. */ enum blk_eh_timer_return (*timeout)(struct request *, bool); /** * @poll: Called to poll for completion of a specific tag. */ int (*poll)(struct blk_mq_hw_ctx *); /** * @complete: Mark the request as complete. */ void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. */ int (*init_request)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); /** * @exit_request: Ditto for exit/teardown. */ void (*exit_request)(struct blk_mq_tag_set *set, struct request *, unsigned int); /** * @initialize_rq_fn: Called from inside blk_get_request(). */ void (*initialize_rq_fn)(struct request *rq); /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ int (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); #endif }; enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, /* hw queue is inactive after all its CPUs become offline */ BLK_MQ_S_INACTIVE = 3, BLK_MQ_MAX_DEPTH = 10240, BLK_MQ_CPU_WORK_BATCH = 8, }; #define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) #define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \ ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q, bool elevator_init); struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags); void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); bool blk_mq_queue_inflight(struct request_queue *q); enum { /* return when out of requests */ BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), /* set RQF_PM */ BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); enum { BLK_MQ_UNIQUE_TAG_BITS = 16, BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1, }; u32 blk_mq_unique_tag(struct request *rq); static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag) { return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS; } static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) { return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } /** * blk_mq_rq_state() - read the current MQ_RQ_* state of a request * @rq: target request. */ static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) { return READ_ONCE(rq->state); } static inline int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; } static inline int blk_mq_request_completed(struct request *rq) { return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); int blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); bool __blk_should_fake_timeout(struct request_queue *q); static inline bool blk_should_fake_timeout(struct request_queue *q) { if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) return __blk_should_fake_timeout(q); return false; } /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted * * Return: request * * Driver command data is immediately after the request. So subtract request * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } /** * blk_mq_rq_to_pdu - cast a request to a PDU * @rq: the request to be casted * * Return: pointer to the PDU * * Driver command data is immediately after the request. So add request to get * the PDU. */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; } #define queue_for_each_hw_ctx(q, hctx, i) \ for ((i) = 0; (i) < (q)->nr_hw_queues && \ ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq) { if (rq->tag != -1) return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT); return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) | BLK_QC_T_INTERNAL; } static inline void blk_mq_cleanup_rq(struct request *rq) { if (rq->q->mq_ops->cleanup_rq) rq->q->mq_ops->cleanup_rq(rq); } blk_qc_t blk_mq_submit_bio(struct bio *bio); #endif |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() do { } while (0) #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } #ifndef arch_spin_lock_flags #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #endif static inline void do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock) { __acquire(lock); arch_spin_lock_flags(&lock->raw_lock, *flags); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) \ __cond_lock(lock, _raw_spin_trylock_bh(lock)) #define raw_spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define raw_spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) /* Include rwlock functions */ #include <linux/rwlock.h> /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } #define spin_trylock_irqsave(lock, flags) \ ({ \ raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t, raw_spin_lock(_T->lock), raw_spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t, raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING), raw_spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, raw_spin_lock_irq(_T->lock), raw_spin_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, raw_spin_lock_irqsave(_T->lock, _T->flags), raw_spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1(spinlock, spinlock_t, spin_lock(_T->lock), spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, spin_lock_irq(_T->lock), spin_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, spin_lock_irqsave(_T->lock, _T->flags), spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) #undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC64_64_H #define _ASM_X86_ATOMIC64_64_H #include <linux/types.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> /* The 64-bit atomic type */ #define ATOMIC64_INIT(i) { (i) } /** * arch_atomic64_read - read atomic64 variable * @v: pointer of type atomic64_t * * Atomically reads the value of @v. * Doesn't imply a read memory barrier. */ static inline s64 arch_atomic64_read(const atomic64_t *v) { return __READ_ONCE((v)->counter); } /** * arch_atomic64_set - set atomic64 variable * @v: pointer to type atomic64_t * @i: required value * * Atomically sets the value of @v to @i. */ static inline void arch_atomic64_set(atomic64_t *v, s64 i) { __WRITE_ONCE(v->counter, i); } /** * arch_atomic64_add - add integer to atomic64 variable * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v. */ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) : "er" (i), "m" (v->counter) : "memory"); } /** * arch_atomic64_sub - subtract the atomic64 variable * @i: integer value to subtract * @v: pointer to type atomic64_t * * Atomically subtracts @i from @v. */ static inline void arch_atomic64_sub(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "subq %1,%0" : "=m" (v->counter) : "er" (i), "m" (v->counter) : "memory"); } /** * arch_atomic64_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer to type atomic64_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i); } #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test /** * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter) : "memory"); } #define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable * @v: pointer to type atomic64_t * * Atomically decrements @v by 1. */ static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter) : "memory"); } #define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_dec_and_test - decrement and test * @v: pointer to type atomic64_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e); } #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test /** * arch_atomic64_inc_and_test - increment and test * @v: pointer to type atomic64_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e); } #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test /** * arch_atomic64_add_negative - add and test if negative * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i); } #define arch_atomic64_add_negative arch_atomic64_add_negative /** * arch_atomic64_add_return - add and return * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v and returns @i + @v */ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { return i + xadd(&v->counter, i); } #define arch_atomic64_add_return arch_atomic64_add_return static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) { return arch_atomic64_add_return(-i, v); } #define arch_atomic64_sub_return arch_atomic64_sub_return static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { return xadd(&v->counter, i); } #define arch_atomic64_fetch_add arch_atomic64_fetch_add static inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v) { return xadd(&v->counter, -i); } #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { return arch_cmpxchg(&v->counter, old, new); } #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { return try_cmpxchg(&v->counter, old, new); } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) { return arch_xchg(&v->counter, new); } #define arch_atomic64_xchg arch_atomic64_xchg static inline void arch_atomic64_and(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "andq %1,%0" : "+m" (v->counter) : "er" (i) : "memory"); } static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i)); return val; } #define arch_atomic64_fetch_and arch_atomic64_fetch_and static inline void arch_atomic64_or(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "orq %1,%0" : "+m" (v->counter) : "er" (i) : "memory"); } static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i)); return val; } #define arch_atomic64_fetch_or arch_atomic64_fetch_or static inline void arch_atomic64_xor(s64 i, atomic64_t *v) { asm volatile(LOCK_PREFIX "xorq %1,%0" : "+m" (v->counter) : "er" (i) : "memory"); } static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i)); return val; } #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor #endif /* _ASM_X86_ATOMIC64_64_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM printk #if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PRINTK_H #include <linux/tracepoint.h> TRACE_EVENT(console, TP_PROTO(const char *text, size_t len), TP_ARGS(text, len), TP_STRUCT__entry( __dynamic_array(char, msg, len + 1) ), TP_fast_assign( /* * Each trace entry is printed in a new line. * If the msg finishes with '\n', cut it off * to avoid blank lines in the trace. */ if ((len > 0) && (text[len-1] == '\n')) len -= 1; memcpy(__get_str(msg), text, len); __get_str(msg)[len] = 0; ), TP_printk("%s", __get_str(msg)) ); #endif /* _TRACE_PRINTK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/shmem_fs.h> #include <linux/cleancache.h> #include <linux/rmap.h> #include "internal.h" /* * Regular page slots are stabilized by the page lock even without the tree * itself locked. These unlocked entries need verification under the tree * lock. */ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { XA_STATE(xas, &mapping->i_pages, index); xas_set_update(&xas, workingset_update_node); if (xas_load(&xas) != entry) return; xas_store(&xas, NULL); mapping->nrexceptional--; } static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { xa_lock_irq(&mapping->i_pages); __clear_shadow_entry(mapping, index, entry); xa_unlock_irq(&mapping->i_pages); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the pagevec may be altered by this function by removing * exceptional entries similar to what pagevec_remove_exceptionals does. */ static void truncate_exceptional_pvec_entries(struct address_space *mapping, struct pagevec *pvec, pgoff_t *indices, pgoff_t end) { int i, j; bool dax, lock; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < pagevec_count(pvec); j++) if (xa_is_value(pvec->pages[j])) break; if (j == pagevec_count(pvec)) return; dax = dax_mapping(mapping); lock = !dax && indices[j] < end; if (lock) xa_lock_irq(&mapping->i_pages); for (i = j; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; pgoff_t index = indices[i]; if (!xa_is_value(page)) { pvec->pages[j++] = page; continue; } if (index >= end) continue; if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; } __clear_shadow_entry(mapping, index, page); } if (lock) xa_unlock_irq(&mapping->i_pages); pvec->nr = j; } /* * Invalidate exceptional entry if easily possible. This handles exceptional * entries for invalidate_inode_pages(). */ static int invalidate_exceptional_entry(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return 1; clear_shadow_entry(mapping, index, entry); return 1; } /* * Invalidate exceptional entry if clean. This handles exceptional entries for * invalidate_inode_pages2() so for DAX it evicts only clean entries. */ static int invalidate_exceptional_entry2(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself */ if (shmem_mapping(mapping)) return 1; if (dax_mapping(mapping)) return dax_invalidate_mapping_entry_sync(mapping, index); clear_shadow_entry(mapping, index, entry); return 1; } /** * do_invalidatepage - invalidate part or all of a page * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * do_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * do_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { void (*invalidatepage)(struct page *, unsigned int, unsigned int); invalidatepage = page->mapping->a_ops->invalidatepage; #ifdef CONFIG_BLOCK if (!invalidatepage) invalidatepage = block_invalidatepage; #endif if (invalidatepage) (*invalidatepage)(page, offset, length); } /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_page(struct page *page) { if (page_mapped(page)) unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, thp_size(page)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ cancel_dirty_page(page); ClearPageMappedToDisk(page); } /* * This is for invalidate_mapping_pages(). That function can be called at * any time, and is not supposed to throw away dirty pages. But pages can * be marked dirty at any time too, so use remove_mapping which safely * discards clean, unused pages. * * Returns non-zero if the page was successfully invalidated. */ static int invalidate_complete_page(struct address_space *mapping, struct page *page) { int ret; if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, 0)) return 0; ret = remove_mapping(mapping, page); return ret; } int truncate_inode_page(struct address_space *mapping, struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); if (page->mapping != mapping) return -EIO; truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_page(struct address_space *mapping, struct page *page) { if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_page(mapping, page); } EXPORT_SYMBOL(generic_error_remove_page); /* * Safely invalidate one page from its pagecache mapping. * It only drops clean, unused pages. The page must be locked. * * Returns 1 if the page is successfully invalidated, otherwise 0. */ int invalidate_inode_page(struct page *page) { struct address_space *mapping = page_mapping(page); if (!mapping) return 0; if (PageDirty(page) || PageWriteback(page)) return 0; if (page_mapped(page)) return 0; return invalidate_complete_page(mapping, page); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidatepage() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) goto out; /* Offsets within partial pages */ partial_start = lstart & (PAGE_SIZE - 1); partial_end = (lend + 1) & (PAGE_SIZE - 1); /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; pagevec_init(&pvec); index = start; while (index < end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { /* * Pagevec array has exceptional entries and we may also fail * to lock some pages. So we store pages that can be deleted * in a new pagevec. */ struct pagevec locked_pvec; pagevec_init(&locked_pvec); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index >= end) break; if (xa_is_value(page)) continue; if (!trylock_page(page)) continue; WARN_ON(page_to_index(page) != index); if (PageWriteback(page)) { unlock_page(page); continue; } if (page->mapping != mapping) { unlock_page(page); continue; } pagevec_add(&locked_pvec, page); } for (i = 0; i < pagevec_count(&locked_pvec); i++) truncate_cleanup_page(locked_pvec.pages[i]); delete_from_page_cache_batch(mapping, &locked_pvec); for (i = 0; i < pagevec_count(&locked_pvec); i++) unlock_page(locked_pvec.pages[i]); truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); pagevec_release(&pvec); cond_resched(); index++; } if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { unsigned int top = PAGE_SIZE; if (start > end) { /* Truncation within a single page */ top = partial_end; partial_end = 0; } wait_on_page_writeback(page); zero_user_segment(page, partial_start, top); cleancache_invalidate_page(mapping, page); if (page_has_private(page)) do_invalidatepage(page, partial_start, top - partial_start); unlock_page(page); put_page(page); } } if (partial_end) { struct page *page = find_lock_page(mapping, end); if (page) { wait_on_page_writeback(page); zero_user_segment(page, 0, partial_end); cleancache_invalidate_page(mapping, page); if (page_has_private(page)) do_invalidatepage(page, 0, partial_end); unlock_page(page); put_page(page); } } /* * If the truncation happened within a single page no pages * will be released, just zeroed, so we can bail out now. */ if (start >= end) goto out; index = start; for ( ; ; ) { cond_resched(); if (!pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } if (index == start && indices[0] >= end) { /* All gone out of hole to be punched, we're done */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index >= end) { /* Restart punch to make sure all gone */ index = start - 1; break; } if (xa_is_value(page)) continue; lock_page(page); WARN_ON(page_to_index(page) != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); pagevec_release(&pvec); index++; } out: cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_mutex. * * Note: When this function returns, there can be a page in the process of * deletion (inside __delete_from_page_cache()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_mutex. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { unsigned long nrexceptional; unsigned long nrpages; /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); /* * When reclaim installs eviction entries, it increases * nrexceptional first, then decreases nrpages. Make sure we see * this in the right order or we might miss an entry. */ nrpages = mapping->nrpages; smp_rmb(); nrexceptional = mapping->nrexceptional; if (nrpages || nrexceptional) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } /* * Cleancache needs notification even if there are no pages or shadow * entries. */ truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); static unsigned long __invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; pagevec_init(&pvec); while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index > end) break; if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, page); continue; } if (!trylock_page(page)) continue; WARN_ON(page_to_index(page) != index); /* Middle of THP: skip */ if (PageTransTail(page)) { unlock_page(page); continue; } else if (PageTransHuge(page)) { index += HPAGE_PMD_NR - 1; i += HPAGE_PMD_NR - 1; /* * 'end' is in the middle of THP. Don't * invalidate the page as the part outside of * 'end' could be still useful. */ if (index > end) { unlock_page(page); continue; } /* Take a pin outside pagevec */ get_page(page); /* * Drop extra pins before trying to invalidate * the huge page. */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); } ret = invalidate_inode_page(page); unlock_page(page); /* * Invalidation is a hint that the page is no longer * of interest and try to speed up its reclaim. */ if (!ret) { deactivate_file_page(page); /* It is likely on the pagevec of a remote CPU */ if (nr_pagevec) (*nr_pagevec)++; } if (PageTransHuge(page)) put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } return count; } /** * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function only removes the unlocked pages, if you want to * remove all the pages of one inode, you must call truncate_inode_pages. * * invalidate_mapping_pages() will not block on IO activity. It will not * invalidate pages which are dirty, locked, under writeback or mapped into * pagetables. * * Return: the number of the pages that were invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { return __invalidate_mapping_pages(mapping, start, end, NULL); } EXPORT_SYMBOL(invalidate_mapping_pages); /** * This helper is similar with the above one, except that it accounts for pages * that are likely on a pagevec and count them in @nr_pagevec, which will used by * the caller. */ void invalidate_mapping_pagevec(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { __invalidate_mapping_pages(mapping, start, end, nr_pagevec); } /* * This is like invalidate_complete_page(), except it ignores the page's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the lru_cache_add() pagevecs. */ static int invalidate_complete_page2(struct address_space *mapping, struct page *page) { unsigned long flags; if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; xa_lock_irqsave(&mapping->i_pages, flags); if (PageDirty(page)) goto failed; BUG_ON(page_has_private(page)); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); put_page(page); /* pagecache ref */ return 1; failed: xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } static int do_launder_page(struct address_space *mapping, struct page *page) { if (!PageDirty(page)) return 0; if (page->mapping != mapping || mapping->a_ops->launder_page == NULL) return 0; return mapping->a_ops->launder_page(page); } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) goto out; pagevec_init(&pvec); index = start; while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index > end) break; if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, index, page)) ret = -EBUSY; continue; } if (!did_range_unmap && page_mapped(page)) { /* * If page is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, index, (1 + end - index), false); did_range_unmap = 1; } lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { unlock_page(page); continue; } wait_on_page_writeback(page); if (page_mapped(page)) unmap_mapping_page(page); BUG_ON(page_mapped(page)); ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page)) ret2 = -EBUSY; } if (ret2 < 0) ret = ret2; unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } out: cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_mutex but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or by * write starting after current i_size. We mark the page straddling current * i_size RO so that page_mkwrite() is called on the nearest write access to * the page. This way filesystem can be sure that page_mkwrite() is called on * the page before user writes to the page via mmap after the i_size has been * changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the page will already see the new i_size. * The function must be called while we still hold i_mutex - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; WARN_ON(to > inode->i_size); if (from >= to || bsize == PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; index = from >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); /* Page not cached? Nothing to do */ if (!page) return; /* * See clear_page_dirty_for_io() for details why set_page_dirty() * is needed. */ if (page_mkclean(page)) set_page_dirty(page); unlock_page(page); put_page(page); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/rcupdate.h> struct workqueue_struct; struct work_struct; typedef void (*work_func_t)(struct work_struct *work); void delayed_work_timer_fn(struct timer_list *t); /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif /* * The last color is no color used for works which don't * participate in workqueue flushing. */ WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, WORK_NO_COLOR = WORK_NR_COLORS, /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. * This makes pwqs aligned to 256 bytes and allows 15 workqueue * flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, /* * When a work item is off queue, its high bits point to the last * pool it was on. Cap at 31 bits and use the highest number to * indicate that no pool is associated. */ WORK_OFFQ_FLAG_BITS = 1, WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 24, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct work_struct { atomic_long_t data; struct list_head entry; work_func_t func; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs */ cpumask_var_t cpumask; /** * @no_numa: disable NUMA affinity * * Unlike other fields, ``no_numa`` isn't a property of a worker_pool. It * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus * doesn't participate in pool hash calculations or equality comparisons. */ bool no_numa; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK(_work, _func, _onstack) \ do { \ static struct lock_class_key __key; \ \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK(_work, _func, _onstack) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __init_timer(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __init_timer_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum { WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * excute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; /* unbound wq's aren't per-cpu, scale max_active according to #cpus */ #define WQ_UNBOUND_MAX_ACTIVE \ max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) /* * System-wide workqueues which are always present. * * system_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * * system_unbound_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * remaining args: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed * information on WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args...: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_workqueue_state(void); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_wq, work); } /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * * Think twice before calling this function! It's very easy to get into * trouble if you don't take great care. Either of the following situations * will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. * * Your code is running in the context of a work routine. * * They will be detected by lockdep when they occur, but the first might not * occur very often. It depends on what work items are on the workqueue and * what locks they need, which you have no control over. * * In most situations flushing the entire workqueue is overkill; you merely * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. */ static inline void flush_scheduled_work(void) { flush_workqueue(system_wq); } /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu(int cpu, long (*fn)(void *), void *arg); long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) { if (!filp->f_mapping || !filp->f_mapping->a_ops || !filp->f_mapping->a_ops->direct_IO) return -EINVAL; } if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); spin_unlock(&filp->f_lock); out: return error; } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; struct pid *pid = NULL; int who = arg, ret = 0; type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&filp->f_owner.lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(enum rw_hint hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; enum rw_hint hint; u64 h; switch (cmd) { case F_GET_FILE_RW_HINT: h = file_write_hint(file); if (copy_to_user(argp, &h, sizeof(*argp))) return -EFAULT; return 0; case F_SET_FILE_RW_HINT: if (copy_from_user(&h, argp, sizeof(h))) return -EFAULT; hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; spin_lock(&file->f_lock); file->f_write_hint = hint; spin_unlock(&file->f_lock); return 0; case F_GET_RW_HINT: h = inode->i_write_hint; if (copy_to_user(argp, &h, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: if (copy_from_user(&h, argp, sizeof(h))) return -EFAULT; hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; inode_lock(inode); inode->i_write_hint = hint; inode_unlock(inode); return 0; default: return -EINVAL; } } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(arg, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(arg, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, arg & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: #endif fallthrough; case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, arg, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(arg)) { break; } err = 0; filp->f_owner.signum = arg; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, arg); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, arg); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, arg); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, arg); break; case F_GET_RW_HINT: case F_SET_RW_HINT: case F_GET_FILE_RW_HINT: case F_SET_FILE_RW_HINT: err = fcntl_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); struct flock64 flock; long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(f.file, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; long err = -EBADF; if (!f.file) return err; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out_put; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out_put: fdput(f); return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __read_mostly; static void fasync_free_rcu(struct rcu_head *head) { kmem_cache_free(fasync_cache, container_of(head, struct fasync_struct, fa_rcu)); } /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; call_rcu(&fa->fa_rcu, fasync_free_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL); return 0; } module_init(fcntl_init) |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/cpumask.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) #define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) #define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } #endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * * RCU read-side critical sections are forbidden in the inner idle loop, * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU * will happily ignore any such read-side critical sections. However, * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument * (in this example, calling the do_something_with_RCU() function), * and then tell RCU to go back to ignoring this CPU. It is permissible * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is * on the order of a million or so, even on 32-bit systems). It is * not legal to block within RCU_NONIDLE(), nor is it permissible to * transfer control either into or out of RCU_NONIDLE()'s statement. */ #define RCU_NONIDLE(a) \ do { \ rcu_irq_enter_irqson(); \ do { a; } while (0); \ rcu_irq_exit_irqson(); \ } while (0) /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU # define rcu_tasks_trace_qs(t) \ do { \ if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ smp_store_release(&(t)->trc_reader_checked, true); \ smp_mb(); /* Readers partitioned by store. */ \ } \ } while (0) # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs((t)); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as * is the case in the context of the RCU callback that is freeing up * the data, or after a synchronize_rcu() returns. This can be useful * when tearing down multi-linked structures after a grace period * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In most situations, rcu_read_unlock() is immune from deadlock. * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() * is responsible for deboosting, which it does via rt_mutex_unlock(). * Unfortunately, this function acquires the scheduler's runqueue and * priority-inheritance spinlocks. This means that deadlock could result * if the caller of rcu_read_unlock() already holds one of these locks or * any lock that is ever acquired while holding them. * * That said, RCU readers are never priority boosted unless they were * preempted. Therefore, one way to avoid deadlock is to make sure * that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with one of * rt_mutex_unlock()'s locks held. Such preemption can be avoided in * a number of ways, for example, by invoking preempt_disable() before * critical section's outermost rcu_read_lock(). * * Given that the set of locks acquired by rt_mutex_unlock() might change * at any time, a somewhat more future-proofed approach is to make sure * that that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with irqs disabled. * This approach relies on the fact that rt_mutex_unlock() currently only * acquires irq-disabled locks. * * The second of these two approaches is best in most situations, * however, the first approach can also be useful, at least to those * developers willing to keep abreast of the set of locks acquired by * rt_mutex_unlock(). * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent of rcu_read_lock(), but disables preemption. * Read-side critical sections can also be introduced by anything else * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ #define __kvfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in __kvfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * Note that the allowable offset might decrease in the future, for example, * to allow something like kmem_cache_free_rcu(). * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) /** * kvfree_rcu() - kvfree an object after a grace period. * * This macro consists of one or two arguments and it is * based on whether an object is head-less or not. If it * has a head then a semantic stays the same as it used * to be before: * * kvfree_rcu(ptr, rhf); * * where @ptr is a pointer to kvfree(), @rhf is the name * of the rcu_head structure within the type of @ptr. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kvfree_rcu(ptr); * * where @ptr is a pointer to kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kfree_rcu_mightsleep(ptr) kvfree_rcu_mightsleep(ptr) #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME #define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ /* * generic net pointers */ #ifndef __NET_GENERIC_H__ #define __NET_GENERIC_H__ #include <linux/bug.h> #include <linux/rcupdate.h> /* * Generic net pointers are to be used by modules to put some private * stuff on the struct net without explicit struct net modification * * The rules are simple: * 1. set pernet_operations->id. After register_pernet_device you * will have the id of your private pointer. * 2. set pernet_operations->size to have the code allocate and free * a private structure pointed to from struct net. * 3. do not change this pointer while the net is alive; * 4. do not try to have any private reference on the net_generic object. * * After accomplishing all of the above, the private pointer can be * accessed with the net_generic() call. */ struct net_generic { union { struct { unsigned int len; struct rcu_head rcu; } s; void *ptr[0]; }; }; static inline void *net_generic(const struct net *net, unsigned int id) { struct net_generic *ng; void *ptr; rcu_read_lock(); ng = rcu_dereference(net->gen); ptr = ng->ptr[id]; rcu_read_unlock(); return ptr; } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_H #define _LINUX_WAIT_H /* * Linux wait queue related types and methods */ #include <linux/list.h> #include <linux/stddef.h> #include <linux/spinlock.h> #include <asm/current.h> #include <uapi/linux/wait.h> typedef struct wait_queue_entry wait_queue_entry_t; typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 #define WQ_FLAG_DONE 0x10 /* * A single wait-queue entry structure: */ struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; struct list_head entry; }; struct wait_queue_head { spinlock_t lock; struct list_head head; }; typedef struct wait_queue_head wait_queue_head_t; struct task_struct; /* * Macros for declaration and initialisaton of the datatypes */ #define __WAITQUEUE_INITIALIZER(name, tsk) { \ .private = tsk, \ .func = default_wake_function, \ .entry = { NULL, NULL } } #define DECLARE_WAITQUEUE(name, tsk) \ struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = { &(name).head, &(name).head } } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); #define init_waitqueue_head(wq_head) \ do { \ static struct lock_class_key __key; \ \ __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { wq_entry->flags = 0; wq_entry->private = p; wq_entry->func = default_wake_function; } static inline void init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { wq_entry->flags = 0; wq_entry->private = NULL; wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like:: * * CPU0 - waker CPU1 - waiter * * for (;;) { * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (waitqueue_active(wq_head)) if (@cond) * wake_up(wq_head); break; * schedule(); * } * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll * observe an empty wait list while the waiter might not observe @cond. * * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ static inline int waitqueue_active(struct wait_queue_head *wq_head) { return !list_empty(&wq_head->head); } /** * wq_has_single_sleeper - check if there is only one sleeper * @wq_head: wait queue head * * Returns true of wq_head has only one sleeper on the list. * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) { return list_is_singular(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier should be paired with one on the * waiting side. */ smp_mb(); return waitqueue_active(wq_head); } extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add(&wq_entry->entry, &wq_head->head); } /* * Used for wake-one threads: */ static inline void __add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq_head, wq_entry); } static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void __add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_del(&wq_entry->entry); } void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, unsigned int mode, void *key, wait_queue_entry_t *bookmark); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) #define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE) /* * Wakeup macros to be used to report events to the targets. */ #define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m)) #define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m)) #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, poll_to_key(m)) #define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) /** * wake_up_pollfree - signal that a polled waitqueue is going away * @wq_head: the wait queue head * * In the very rare cases where a ->poll() implementation uses a waitqueue whose * lifetime is tied to a task rather than to the 'struct file' being polled, * this function must be called before the waitqueue is freed so that * non-blocking polls (e.g. epoll) are notified that the queue is going away. * * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. */ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) { /* * For performance reasons, we don't always take the queue lock here. * Therefore, we might race with someone removing the last entry from * the queue, and proceed while they still hold the queue lock. * However, rcu_read_lock() is required to be held in such cases, so we * can safely proceed with an RCU-delayed free. */ if (waitqueue_active(wq_head)) __wake_up_pollfree(wq_head); } #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ if (__cond && !__ret) \ __ret = 1; \ __cond || !__ret; \ }) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret * variable when used from the wait_event_*() macros. * * This is so that both can use the ___wait_cond_timeout() construct * to wrap the condition. * * The type inconsistency of the wait_event_*() __ret variable is also * on purpose; we use long where we can return timeout values and int * otherwise. */ #define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_entry __wq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ }) #define __wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_event(wq_head, condition); \ } while (0) #define __io_wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ #define io_wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __io_wait_event(wq_head, condition); \ } while (0) #define __wait_event_freezable(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ freezable_schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_freezable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable(wq_head, condition); \ __ret; \ }) #define __wait_event_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = freezable_schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ #define wait_event_freezable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ #define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_interruptible(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible(wq_head, condition); \ __ret; \ }) #define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ #define wait_event_interruptible_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_interruptible_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ ({ \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \ } \ \ __ret = ___wait_event(wq_head, condition, state, 0, 0, \ if (!__t.task) { \ __ret = -ETIME; \ break; \ } \ schedule()); \ \ hrtimer_cancel(&__t.timer); \ destroy_hrtimer_on_stack(&__t.timer); \ __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ #define wait_event_hrtimeout(wq_head, condition, timeout) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ #define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ ({ \ long __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq, condition, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define __wait_event_interruptible_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) #define wait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_killable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) #define wait_event_killable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_freezable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ freezable_schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable_exclusive(wq, condition); \ __ret; \ }) /** * wait_event_idle - wait for a condition without contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \ } while (0) /** * wait_event_idle_exclusive - wait for a condition with contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle_exclusive(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \ } while (0) #define __wait_event_idle_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 1, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\ __ret; \ }) extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); #define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ __ret = fn(&(wq), &__wait); \ if (__ret) \ break; \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ __ret; \ }) /** * wait_event_interruptible_locked - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** * wait_event_killable - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_killable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable(wq_head, condition); \ __ret; \ }) #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a kill signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a kill signal. * * Only kill signals interrupt this process. */ #define wait_event_killable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_killable_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_lock_irq_cmd - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ #define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** * wait_event_lock_irq - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ #define wait_event_lock_irq(wq_head, condition, lock) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) #define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock, cmd); \ __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock,); \ __ret; \ }) #define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ #define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_FUNC(name, function) \ struct wait_queue_entry name = { \ .private = current, \ .func = function, \ .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) #define init_wait(wait) \ do { \ (wait)->private = current; \ (wait)->func = autoremove_wake_function; \ INIT_LIST_HEAD(&(wait)->entry); \ (wait)->flags = 0; \ } while (0) bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg); #endif /* _LINUX_WAIT_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> /* * There are two chunk types: root and memcg-aware. * Chunks of each type have separate slots list. * * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is * used to store memcg membership data of a percpu object. Obj_cgroups are * ref-counted pointers to a memory cgroup with an ability to switch dynamically * to the parent memory cgroup. This allows to reclaim a deleted memory cgroup * without reclaiming of all outstanding objects, which hold a reference at it. */ enum pcpu_chunk_type { PCPU_CHUNK_ROOT, #ifdef CONFIG_MEMCG_KMEM PCPU_CHUNK_MEMCG, #endif PCPU_NR_CHUNK_TYPES, PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES }; /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; void *base_addr; /* base address of this chunk */ unsigned long *alloc_map; /* allocation map */ unsigned long *bound_map; /* boundary map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef CONFIG_MEMCG_KMEM struct obj_cgroup **obj_cgroups; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_nr_empty_pop_pages[]; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } #ifdef CONFIG_MEMCG_KMEM static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) { if (chunk->obj_cgroups) return PCPU_CHUNK_MEMCG; return PCPU_CHUNK_ROOT; } static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) { return chunk_type == PCPU_CHUNK_MEMCG; } #else static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) { return PCPU_CHUNK_ROOT; } static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) { return false; } #endif static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type) { return &pcpu_chunk_lists[pcpu_nr_slots * pcpu_is_memcg_chunk(chunk_type)]; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocaiton size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NETLINK Kernel-user communication protocol. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Patrick McHardy <kaber@trash.net> * * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith * added netlink_proto_exit * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> * use nlk_sk, as sk->protinfo is on a diet 8) * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> * - inc module use count of module that owns * the kernel socket in case userspace opens * socket of same protocol * - remove all module support, since netlink is * mandatory if CONFIG_NET=y these days */ #include <linux/module.h> #include <linux/capability.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/un.h> #include <linux/fcntl.h> #include <linux/termios.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/security.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/bitops.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/audit.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> #include <linux/genetlink.h> #include <linux/net_namespace.h> #include <linux/nospec.h> #include <linux/btf_ids.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/scm.h> #include <net/netlink.h> #include "af_netlink.h" struct listeners { struct rcu_head rcu; unsigned long masks[]; }; /* state bits */ #define NETLINK_S_CONGESTED 0x0 static inline int netlink_is_kernel(struct sock *sk) { return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET; } struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { "nlk_cb_mutex-ROUTE", "nlk_cb_mutex-1", "nlk_cb_mutex-USERSOCK", "nlk_cb_mutex-FIREWALL", "nlk_cb_mutex-SOCK_DIAG", "nlk_cb_mutex-NFLOG", "nlk_cb_mutex-XFRM", "nlk_cb_mutex-SELINUX", "nlk_cb_mutex-ISCSI", "nlk_cb_mutex-AUDIT", "nlk_cb_mutex-FIB_LOOKUP", "nlk_cb_mutex-CONNECTOR", "nlk_cb_mutex-NETFILTER", "nlk_cb_mutex-IP6_FW", "nlk_cb_mutex-DNRTMSG", "nlk_cb_mutex-KOBJECT_UEVENT", "nlk_cb_mutex-GENERIC", "nlk_cb_mutex-17", "nlk_cb_mutex-SCSITRANSPORT", "nlk_cb_mutex-ECRYPTFS", "nlk_cb_mutex-RDMA", "nlk_cb_mutex-CRYPTO", "nlk_cb_mutex-SMC", "nlk_cb_mutex-23", "nlk_cb_mutex-24", "nlk_cb_mutex-25", "nlk_cb_mutex-26", "nlk_cb_mutex-27", "nlk_cb_mutex-28", "nlk_cb_mutex-29", "nlk_cb_mutex-30", "nlk_cb_mutex-31", "nlk_cb_mutex-MAX_LINKS" }; static int netlink_dump(struct sock *sk, bool lock_taken); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion * and removal are protected with per bucket lock while using RCU list * modification primitives and may run in parallel to RCU protected lookups. * Destruction of the Netlink socket may only occur *after* nl_table_lock has * been acquired * either during or after the socket has been removed from * the list and after an RCU grace period. */ DEFINE_RWLOCK(nl_table_lock); EXPORT_SYMBOL_GPL(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); static BLOCKING_NOTIFIER_HEAD(netlink_chain); static const struct rhashtable_params netlink_rhashtable_params; static inline u32 netlink_group_mask(u32 group) { if (group > 32) return 0; return group ? 1 << (group - 1) : 0; } static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); if (new == NULL) return NULL; NETLINK_CB(new).portid = NETLINK_CB(skb).portid; NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; NETLINK_CB(new).creds = NETLINK_CB(skb).creds; skb_put_data(new, skb->data, len); return new; } static unsigned int netlink_tap_net_id; struct netlink_tap_net { struct list_head netlink_tap_all; struct mutex netlink_tap_lock; }; int netlink_add_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); if (unlikely(nt->dev->type != ARPHRD_NETLINK)) return -EINVAL; mutex_lock(&nn->netlink_tap_lock); list_add_rcu(&nt->list, &nn->netlink_tap_all); mutex_unlock(&nn->netlink_tap_lock); __module_get(nt->module); return 0; } EXPORT_SYMBOL_GPL(netlink_add_tap); static int __netlink_remove_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); bool found = false; struct netlink_tap *tmp; mutex_lock(&nn->netlink_tap_lock); list_for_each_entry(tmp, &nn->netlink_tap_all, list) { if (nt == tmp) { list_del_rcu(&nt->list); found = true; goto out; } } pr_warn("__netlink_remove_tap: %p not found\n", nt); out: mutex_unlock(&nn->netlink_tap_lock); if (found) module_put(nt->module); return found ? 0 : -ENODEV; } int netlink_remove_tap(struct netlink_tap *nt) { int ret; ret = __netlink_remove_tap(nt); synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(netlink_remove_tap); static __net_init int netlink_tap_init_net(struct net *net) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); INIT_LIST_HEAD(&nn->netlink_tap_all); mutex_init(&nn->netlink_tap_lock); return 0; } static struct pernet_operations netlink_tap_net_ops = { .init = netlink_tap_init_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), }; static bool netlink_filter_tap(const struct sk_buff *skb) { struct sock *sk = skb->sk; /* We take the more conservative approach and * whitelist socket protocols that may pass. */ switch (sk->sk_protocol) { case NETLINK_ROUTE: case NETLINK_USERSOCK: case NETLINK_SOCK_DIAG: case NETLINK_NFLOG: case NETLINK_XFRM: case NETLINK_FIB_LOOKUP: case NETLINK_NETFILTER: case NETLINK_GENERIC: return true; } return false; } static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; struct sock *sk = skb->sk; int ret = -ENOMEM; if (!net_eq(dev_net(dev), sock_net(sk))) return 0; dev_hold(dev); if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); } dev_put(dev); return ret; } static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn) { int ret; struct netlink_tap *tmp; if (!netlink_filter_tap(skb)) return; list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) { ret = __netlink_deliver_tap_skb(skb, tmp->dev); if (unlikely(ret)) break; } } static void netlink_deliver_tap(struct net *net, struct sk_buff *skb) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); rcu_read_lock(); if (unlikely(!list_empty(&nn->netlink_tap_all))) __netlink_deliver_tap(skb, nn); rcu_read_unlock(); } static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, struct sk_buff *skb) { if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) netlink_deliver_tap(sock_net(dst), skb); } static void netlink_overrun(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; sk->sk_error_report(sk); } } atomic_inc(&sk->sk_drops); } static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); } static void netlink_skb_destructor(struct sk_buff *skb) { if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) vfree_atomic(skb->head); skb->head = NULL; } if (skb->sk != NULL) sock_rfree(skb); } static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; sk_mem_charge(sk, skb->truesize); } static void netlink_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves * this, _but_ remember, it adds useless work on UP machines. */ void netlink_table_grab(void) __acquires(nl_table_lock) { might_sleep(); write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&nl_table_wait, &wait); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&nl_table_users) == 0) break; write_unlock_irq(&nl_table_lock); schedule(); write_lock_irq(&nl_table_lock); } __set_current_state(TASK_RUNNING); remove_wait_queue(&nl_table_wait, &wait); } } void netlink_table_ungrab(void) __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); wake_up(&nl_table_wait); } static inline void netlink_lock_table(void) { unsigned long flags; /* read_lock() synchronizes us to netlink_table_grab */ read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); read_unlock_irqrestore(&nl_table_lock, flags); } static inline void netlink_unlock_table(void) { if (atomic_dec_and_test(&nl_table_users)) wake_up(&nl_table_wait); } struct netlink_compare_arg { possible_net_t pnet; u32 portid; }; /* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ #define netlink_compare_arg_len \ (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) static inline int netlink_compare(struct rhashtable_compare_arg *arg, const void *ptr) { const struct netlink_compare_arg *x = arg->key; const struct netlink_sock *nlk = ptr; return nlk->portid != x->portid || !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); } static void netlink_compare_arg_init(struct netlink_compare_arg *arg, struct net *net, u32 portid) { memset(arg, 0, sizeof(*arg)); write_pnet(&arg->pnet, net); arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, net, portid); return rhashtable_lookup_fast(&table->hash, &arg, netlink_rhashtable_params); } static int __netlink_insert(struct netlink_table *table, struct sock *sk) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); return rhashtable_lookup_insert_key(&table->hash, &arg, &nlk_sk(sk)->node, netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { struct netlink_table *table = &nl_table[protocol]; struct sock *sk; rcu_read_lock(); sk = __netlink_lookup(table, portid, net); if (sk) sock_hold(sk); rcu_read_unlock(); return sk; } static const struct proto_ops netlink_ops; static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; unsigned long mask; unsigned int i; struct listeners *listeners; listeners = nl_deref_protected(tbl->listeners); if (!listeners) return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ } static int netlink_insert(struct sock *sk, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; int err; lock_sock(sk); err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; if (nlk_sk(sk)->bound) goto err; /* portid can be read locklessly from netlink_getname(). */ WRITE_ONCE(nlk_sk(sk)->portid, portid); sock_hold(sk); err = __netlink_insert(table, sk); if (err) { /* In case the hashtable backend returns with -EBUSY * from here, it must not escape to the caller. */ if (unlikely(err == -EBUSY)) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; sock_put(sk); goto err; } /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); /* Paired with lockless reads from netlink_bind(), * netlink_connect() and netlink_sendmsg(). */ WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); return err; } static void netlink_remove(struct sock *sk) { struct netlink_table *table; table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) { WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { __sk_del_bind_node(sk); netlink_update_listeners(sk); } if (sk->sk_protocol == NETLINK_GENERIC) atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } static struct proto netlink_proto = { .name = "NETLINK", .owner = THIS_MODULE, .obj_size = sizeof(struct netlink_sock), }; static int __netlink_create(struct net *net, struct socket *sock, struct mutex *cb_mutex, int protocol, int kern) { struct sock *sk; struct netlink_sock *nlk; sock->ops = &netlink_ops; sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); nlk = nlk_sk(sk); if (cb_mutex) { nlk->cb_mutex = cb_mutex; } else { nlk->cb_mutex = &nlk->cb_def_mutex; mutex_init(nlk->cb_mutex); lockdep_set_class_and_name(nlk->cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); } init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; return 0; } static int netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct module *module = NULL; struct mutex *cb_mutex; struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); int err = 0; sock->state = SS_UNCONNECTED; if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES if (!nl_table[protocol].registered) { netlink_unlock_table(); request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); netlink_lock_table(); } #endif if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; else err = -EPROTONOSUPPORT; cb_mutex = nl_table[protocol].cb_mutex; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; netlink_unlock_table(); if (err < 0) goto out; err = __netlink_create(net, sock, cb_mutex, protocol, kern); if (err < 0) goto out_module; local_bh_disable(); sock_prot_inuse_add(net, &netlink_proto, 1); local_bh_enable(); nlk = nlk_sk(sock->sk); nlk->module = module; nlk->netlink_bind = bind; nlk->netlink_unbind = unbind; out: return err; out_module: module_put(module); goto out; } static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; kfree(nlk->groups); nlk->groups = NULL; if (!refcount_dec_and_test(&sk->sk_refcnt)) return; sk_free(sk); } static int netlink_release(struct socket *sock) { struct sock *sk = sock->sk; struct netlink_sock *nlk; if (!sk) return 0; netlink_remove(sk); sock_orphan(sk); nlk = nlk_sk(sk); /* * OK. Socket is unlinked, any packets that arrive now * will be purged. */ /* must not acquire netlink_table_lock in any way again before unbind * and notifying genetlink is done as otherwise it might deadlock */ if (nlk->netlink_unbind) { int i; for (i = 0; i < nlk->ngroups; i++) if (test_bit(i, nlk->groups)) nlk->netlink_unbind(sock_net(sk), i + 1); } if (sk->sk_protocol == NETLINK_GENERIC && atomic_dec_return(&genl_sk_destructing_cnt) == 0) wake_up(&genl_sk_destructing_waitq); sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); skb_queue_purge(&sk->sk_write_queue); if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, .portid = nlk->portid, }; blocking_notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); } /* Terminate any outstanding dump */ if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); } module_put(nlk->module); if (netlink_is_kernel(sk)) { netlink_table_grab(); BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { struct listeners *old; old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].unbind = NULL; nl_table[sk->sk_protocol].flags = 0; nl_table[sk->sk_protocol].registered = 0; } netlink_table_ungrab(); } local_bh_disable(); sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); local_bh_enable(); call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_table *table = &nl_table[sk->sk_protocol]; s32 portid = task_tgid_vnr(current); int err; s32 rover = -4096; bool ok; retry: cond_resched(); rcu_read_lock(); ok = !__netlink_lookup(table, portid, net); rcu_read_unlock(); if (!ok) { /* Bind collision, search negative portid values. */ if (rover == -4096) /* rover will be in range [S32_MIN, -4097] */ rover = S32_MIN + prandom_u32_max(-4096 - S32_MIN); else if (rover >= -4096) rover = -4097; portid = rover--; goto retry; } err = netlink_insert(sk, portid); if (err == -EADDRINUSE) goto retry; /* If 2 threads race to autobind, that is fine. */ if (err == -EBUSY) err = 0; return err; } /** * __netlink_ns_capable - General netlink message capability test * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { return ((nsp->flags & NETLINK_SKB_DST) || file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable); /** * netlink_ns_capable - General netlink message capability test * @skb: socket buffer holding a netlink command from userspace * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) { return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); } EXPORT_SYMBOL(netlink_ns_capable); /** * netlink_capable - Netlink global message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, &init_user_ns, cap); } EXPORT_SYMBOL(netlink_capable); /** * netlink_net_capable - Netlink network namespace message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); } EXPORT_SYMBOL(netlink_net_capable); static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); } static void netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) { struct netlink_sock *nlk = nlk_sk(sk); if (nlk->subscriptions && !subscriptions) __sk_del_bind_node(sk); else if (!nlk->subscriptions && subscriptions) sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); nlk->subscriptions = subscriptions; } static int netlink_realloc_groups(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int groups; unsigned long *new_groups; int err = 0; netlink_table_grab(); groups = nl_table[sk->sk_protocol].groups; if (!nl_table[sk->sk_protocol].registered) { err = -ENOENT; goto out_unlock; } if (nlk->ngroups >= groups) goto out_unlock; new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); if (new_groups == NULL) { err = -ENOMEM; goto out_unlock; } memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); nlk->groups = new_groups; nlk->ngroups = groups; out_unlock: netlink_table_ungrab(); return err; } static void netlink_undo_bind(int group, long unsigned int groups, struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); int undo; if (!nlk->netlink_unbind) return; for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) nlk->netlink_unbind(sock_net(sk), undo + 1); } static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; if (nladdr->nl_family != AF_NETLINK) return -EINVAL; groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; } if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; /* Paired with WRITE_ONCE() in netlink_insert() */ bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); if (nladdr->nl_pid != nlk->portid) return -EINVAL; } if (nlk->netlink_bind && groups) { int group; /* nl_groups is a u32, so cap the maximum groups we can bind */ for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); if (!err) continue; netlink_undo_bind(group, groups, sk); return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) goto unlock; netlink_unlock_table(); netlink_table_grab(); netlink_update_subscriptions(sk, nlk->subscriptions + hweight32(groups) - hweight32(nlk->groups[0])); nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; netlink_update_listeners(sk); netlink_table_ungrab(); return 0; unlock: netlink_unlock_table(); return err; } static int netlink_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { int err = 0; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; if (alen < sizeof(addr->sa_family)) return -EINVAL; if (addr->sa_family == AF_UNSPEC) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, 0); WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) return -EINVAL; if (alen < sizeof(struct sockaddr_nl)) return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; /* No need for barriers here as we return to user-space without * using any of the bound attributes. * Paired with WRITE_ONCE() in netlink_insert(). */ if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; } static int netlink_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; if (peer) { /* Paired with WRITE_ONCE() in netlink_connect() */ nladdr->nl_pid = READ_ONCE(nlk->dst_portid); nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* try to hand this ioctl down to the NIC drivers. */ return -ENOIOCTLCMD; } static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; struct netlink_sock *nlk; sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); if (!sock) return ERR_PTR(-ECONNREFUSED); /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); /* dst_portid and sk_state can be changed in netlink_connect() */ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } return sock; } struct sock *netlink_getsockbyfilp(struct file *filp) { struct inode *inode = file_inode(filp); struct sock *sock; if (!S_ISSOCK(inode->i_mode)) return ERR_PTR(-ENOTSOCK); sock = SOCKET_I(inode)->sk; if (sock->sk_family != AF_NETLINK) return ERR_PTR(-EINVAL); sock_hold(sock); return sock; } static struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { struct sk_buff *skb; void *data; if (size <= NLMSG_GOODSIZE || broadcast) return alloc_skb(size, GFP_KERNEL); size = SKB_DATA_ALIGN(size) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); data = vmalloc(size); if (data == NULL) return NULL; skb = __build_skb(data, size); if (skb == NULL) vfree(data); else skb->destructor = netlink_skb_destructor; return skb; } /* * Attach a skb to a netlink socket. * The caller must hold a reference to the destination socket. On error, the * reference is dropped. The skb is not send to the destination, just all * all error checks are performed and memory in the queue is reserved. * Return values: * < 0: error. skb freed, reference to sock dropped. * 0: continue * 1: repeat lookup - reference dropped while waiting for socket memory. */ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { DECLARE_WAITQUEUE(wait, current); struct netlink_sock *nlk; unsigned int rmem; nlk = nlk_sk(sk); rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); if ((rmem == skb->truesize || rmem <= READ_ONCE(sk->sk_rcvbuf)) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); return 0; } atomic_sub(skb->truesize, &sk->sk_rmem_alloc); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); kfree_skb(skb); return -EAGAIN; } __set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&nlk->wait, &wait); rmem = atomic_read(&sk->sk_rmem_alloc); if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) || test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); sock_put(sk); if (signal_pending(current)) { kfree_skb(skb); return sock_intr_errno(*timeo); } return 1; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; netlink_deliver_tap(sock_net(sk), skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } int netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = __netlink_sendskb(sk, skb); sock_put(sk); return len; } void netlink_detachskb(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); sock_put(sk); } static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) { int delta; WARN_ON(skb->sk != NULL); delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, allocation); if (!nskb) return skb; consume_skb(skb); skb = nskb; } pskb_expand_head(skb, 0, -delta, (allocation & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); return skb; } static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, struct sock *ssk) { int ret; struct netlink_sock *nlk = nlk_sk(sk); ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; atomic_add(skb->truesize, &sk->sk_rmem_alloc); netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); nlk->netlink_rcv(skb); consume_skb(skb); } else { kfree_skb(skb); } sock_put(sk); return ret; } int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 portid, int nonblock) { struct sock *sk; int err; long timeo; skb = netlink_trim(skb, gfp_any()); timeo = sock_sndtimeo(ssk, nonblock); retry: sk = netlink_getsockbyportid(ssk, portid); if (IS_ERR(sk)) { kfree_skb(skb); return PTR_ERR(sk); } if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb, ssk); if (sk_filter(sk, skb)) { err = skb->len; kfree_skb(skb); sock_put(sk); return err; } err = netlink_attachskb(sk, skb, &timeo, ssk); if (err == 1) goto retry; if (err) return err; return netlink_sendskb(sk, skb); } EXPORT_SYMBOL(netlink_unicast); int netlink_has_listeners(struct sock *sk, unsigned int group) { int res = 0; struct listeners *listeners; BUG_ON(!netlink_is_kernel(sk)); rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { const struct netlink_sock *nlk = nlk_sk(NETLINK_CB(skb).sk); return nlk->flags & NETLINK_F_STRICT_CHK; } EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int rmem, rcvbuf; rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); rcvbuf = READ_ONCE(sk->sk_rcvbuf); if ((rmem == skb->truesize || rmem <= rcvbuf) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); return rmem > (rcvbuf >> 1); } atomic_sub(skb->truesize, &sk->sk_rmem_alloc); return -1; } struct netlink_broadcast_data { struct sock *exclude_sk; struct net *net; u32 portid; u32 group; int failure; int delivery_failure; int congested; int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); void *tx_data; }; static void do_one_broadcast(struct sock *sk, struct netlink_broadcast_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int val; if (p->exclude_sk == sk) return; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) return; if (!net_eq(sock_net(sk), p->net)) { if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID)) return; if (!peernet_has_id(sock_net(sk), p->net)) return; if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, CAP_NET_BROADCAST)) return; } if (p->failure) { netlink_overrun(sk); return; } sock_hold(sk); if (p->skb2 == NULL) { if (skb_shared(p->skb)) { p->skb2 = skb_clone(p->skb, p->allocation); } else { p->skb2 = skb_get(p->skb); /* * skb ownership may have been set when * delivered to a previous socket. */ skb_orphan(p->skb2); } } if (p->skb2 == NULL) { netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) p->delivery_failure = 1; goto out; } if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) NETLINK_CB(p->skb2).nsid_is_set = true; val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; p->skb2 = NULL; } out: sock_put(sk); } int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation, int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), void *filter_data) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct sock *sk; skb = netlink_trim(skb, allocation); info.exclude_sk = ssk; info.net = net; info.portid = portid; info.group = group; info.failure = 0; info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; info.skb = skb; info.skb2 = NULL; info.tx_filter = filter; info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ netlink_lock_table(); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); netlink_unlock_table(); if (info.delivery_failure) { kfree_skb(info.skb2); return -ENOBUFS; } consume_skb(info.skb2); if (info.delivered) { if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } return -ESRCH; } EXPORT_SYMBOL(netlink_broadcast_filtered); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation) { return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, NULL, NULL); } EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; u32 portid; u32 group; int code; }; static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int ret = 0; if (sk == p->exclude_sk) goto out; if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) { ret = 1; goto out; } sk->sk_err = p->code; sk->sk_error_report(sk); out: return ret; } /** * netlink_set_err - report error to broadcast listeners * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_NO_ENOBUFS socket option. */ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; unsigned long flags; struct sock *sk; int ret = 0; info.exclude_sk = ssk; info.portid = portid; info.group = group; /* sk->sk_err wants a positive error value */ info.code = -code; read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); /* must be called with netlink table grabbed */ static void netlink_update_socket_mc(struct netlink_sock *nlk, unsigned int group, int is_new) { int old, new = !!is_new, subscriptions; old = test_bit(group - 1, nlk->groups); subscriptions = nlk->subscriptions - old + new; if (new) __set_bit(group - 1, nlk->groups); else __clear_bit(group - 1, nlk->groups); netlink_update_subscriptions(&nlk->sk, subscriptions); netlink_update_listeners(&nlk->sk); } static int netlink_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; int err; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (optlen >= sizeof(int) && copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case NETLINK_PKTINFO: if (val) nlk->flags |= NETLINK_F_RECV_PKTINFO; else nlk->flags &= ~NETLINK_F_RECV_PKTINFO; err = 0; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; if (!val || val - 1 >= nlk->ngroups) return -EINVAL; if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { err = nlk->netlink_bind(sock_net(sk), val); if (err) return err; } netlink_table_grab(); netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); err = 0; break; } case NETLINK_BROADCAST_ERROR: if (val) nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR; else nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR; err = 0; break; case NETLINK_NO_ENOBUFS: if (val) { nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS; clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); } else { nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS; } err = 0; break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; if (val) nlk->flags |= NETLINK_F_LISTEN_ALL_NSID; else nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID; err = 0; break; case NETLINK_CAP_ACK: if (val) nlk->flags |= NETLINK_F_CAP_ACK; else nlk->flags &= ~NETLINK_F_CAP_ACK; err = 0; break; case NETLINK_EXT_ACK: if (val) nlk->flags |= NETLINK_F_EXT_ACK; else nlk->flags &= ~NETLINK_F_EXT_ACK; err = 0; break; case NETLINK_GET_STRICT_CHK: if (val) nlk->flags |= NETLINK_F_STRICT_CHK; else nlk->flags &= ~NETLINK_F_STRICT_CHK; err = 0; break; default: err = -ENOPROTOOPT; } return err; } static int netlink_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int flag; int len, val; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case NETLINK_PKTINFO: flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { int pos, idx, shift, err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; idx = pos / sizeof(unsigned long); shift = (pos % sizeof(unsigned long)) * 8; if (put_user((u32)(nlk->groups[idx] >> shift), (u32 __user *)(optval + pos))) { err = -EFAULT; break; } } if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; } case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: flag = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: flag = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = nlk->flags & flag ? 1 : 0; if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct nl_pktinfo info; info.group = NETLINK_CB(skb).dst_group; put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { if (!NETLINK_CB(skb).nsid_is_set) return; put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), &NETLINK_CB(skb).nsid); } static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); u32 dst_portid; u32 dst_group; struct sk_buff *skb; int err; struct scm_cookie scm; u32 netlink_skb_flags = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (len == 0) { pr_warn_once("Zero length message leads to an empty skb\n"); return -ENODATA; } err = scm_send(sock, msg, &scm, true); if (err < 0) return err; if (msg->msg_namelen) { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_nl)) goto out; if (addr->nl_family != AF_NETLINK) goto out; dst_portid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { /* Paired with WRITE_ONCE() in netlink_connect() */ dst_portid = READ_ONCE(nlk->dst_portid); dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; } else { /* Ensure nlk is hashed and visible. */ smp_rmb(); } err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = netlink_alloc_large_skb(len, dst_group); if (skb == NULL) goto out; NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = scm.creds; NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_from_msg(skb_put(skb, len), msg, len)) { kfree_skb(skb); goto out; } err = security_netlink_send(sk, skb); if (err) { kfree_skb(skb); goto out; } if (dst_group) { refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); out: scm_destroy(&scm); return err; } static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); int noblock = flags & MSG_DONTWAIT; size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; if (flags & MSG_OOB) return -EOPNOTSUPP; copied = 0; skb = skb_recv_datagram(sk, flags, noblock, &err); if (skb == NULL) goto out; data_skb = skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES if (unlikely(skb_shinfo(skb)->frag_list)) { /* * If this skb has a frag_list, then here that means that we * will have to use the frag_list skb's data for compat tasks * and the regular skb's data for normal (non-compat) tasks. * * If we need to send the compat skb, assign it to the * 'data_skb' variable so that it will be used below for data * copying. We keep 'skb' for everything else, including * freeing both later. */ if (flags & MSG_CMSG_COMPAT) data_skb = skb_shinfo(skb)->frag_list; } #endif /* Record the max length of recvmsg() calls for future allocations */ max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); max_recvmsg_len = min_t(size_t, max_recvmsg_len, SKB_WITH_OVERHEAD(32768)); WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); addr->nl_family = AF_NETLINK; addr->nl_pad = 0; addr->nl_pid = NETLINK_CB(skb).portid; addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); msg->msg_namelen = sizeof(*addr); } if (nlk->flags & NETLINK_F_RECV_PKTINFO) netlink_cmsg_recv_pktinfo(msg, skb); if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); scm.creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = data_skb->len; skb_free_datagram(sk, skb); if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk, false); if (ret) { sk->sk_err = -ret; sk->sk_error_report(sk); } } scm_recv(sock, msg, &scm, flags); out: netlink_rcv_wake(sk); return err ? : copied; } static void netlink_data_ready(struct sock *sk) { BUG(); } /* * We export these functions to other modules. They provide a * complete set of kernel non-blocking support for message * queueing. */ struct sock * __netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; unsigned int groups; BUG_ON(!nl_table); if (unit < 0 || unit >= MAX_LINKS) return NULL; if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; if (!cfg || cfg->groups < 32) groups = 32; else groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; if (cfg && cfg->input) nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, 0)) goto out_sock_release; nlk = nlk_sk(sk); nlk->flags |= NETLINK_F_KERNEL_SOCKET; netlink_table_grab(); if (!nl_table[unit].registered) { nl_table[unit].groups = groups; rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].cb_mutex = cb_mutex; nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; nl_table[unit].unbind = cfg->unbind; nl_table[unit].flags = cfg->flags; if (cfg->compare) nl_table[unit].compare = cfg->compare; } nl_table[unit].registered = 1; } else { kfree(listeners); nl_table[unit].registered++; } netlink_table_ungrab(); return sk; out_sock_release: kfree(listeners); netlink_kernel_release(sk); return NULL; out_sock_release_nosk: sock_release(sock); return NULL; } EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) { if (sk == NULL || sk->sk_socket == NULL) return; sock_release(sk->sk_socket); } EXPORT_SYMBOL(netlink_kernel_release); int __netlink_change_ngroups(struct sock *sk, unsigned int groups) { struct listeners *new, *old; struct netlink_table *tbl = &nl_table[sk->sk_protocol]; if (groups < 32) groups = 32; if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); kfree_rcu(old, rcu); } tbl->groups = groups; return 0; } /** * netlink_change_ngroups - change number of multicast groups * * This changes the number of multicast groups that are available * on a certain netlink family. Note that it is not possible to * change the number of groups to below 32. Also note that it does * not implicitly call netlink_clear_multicast_users() when the * number of groups is reduced. * * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). * @groups: The new number of groups. */ int netlink_change_ngroups(struct sock *sk, unsigned int groups) { int err; netlink_table_grab(); err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); return err; } void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; struct hlist_node *tmp; sk_for_each_bound_safe(sk, tmp, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); nlh = skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; nlh->nlmsg_pid = portid; nlh->nlmsg_seq = seq; if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); return nlh; } EXPORT_SYMBOL(__nlmsg_put); /* * It looks a bit ugly. * It would be better to create kernel thread. */ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, struct netlink_callback *cb, struct netlink_ext_ack *extack) { struct nlmsghdr *nlh; nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), NLM_F_MULTI | cb->answer_flags); if (WARN_ON(!nlh)) return -ENOBUFS; nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)) nlmsg_end(skb, nlh); } return 0; } static int netlink_dump(struct sock *sk, bool lock_taken) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; unsigned int rmem, rcvbuf; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; int alloc_size; if (!lock_taken) mutex_lock(nlk->cb_mutex); if (!nlk->cb_running) { err = -EINVAL; goto errout_skb; } /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 16K bytes allocation * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); if (alloc_min_size < max_recvmsg_len) { alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; skb = alloc_skb(alloc_size, GFP_KERNEL); } if (!skb) goto errout_skb; rcvbuf = READ_ONCE(sk->sk_rcvbuf); rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); if (rmem != skb->truesize && rmem >= rcvbuf) { atomic_sub(skb->truesize, &sk->sk_rmem_alloc); goto errout_skb; } /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as * could fit within the allocated skb. skb is typically allocated * with larger space than required (could be as much as near 2x the * requested size with align to next power of 2 approach). Allowing * dump to use the excess space makes it difficult for a user to have a * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); /* Make sure malicious BPF programs can not read unitialized memory * from skb->head -> skb->data */ skb_reset_network_header(skb); skb_reset_mac_header(skb); netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { cb->extack = &extack; nlk->dump_done_errno = cb->dump(skb, cb); cb->extack = NULL; } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(nlk->cb_mutex); if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); return 0; } if (netlink_dump_done(nlk, skb, cb, &extack)) goto errout_skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES /* frag_list skb's data is used for compat tasks * and the regular skb's data for normal (non-compat) tasks. * See netlink_recvmsg(). */ if (unlikely(skb_shinfo(skb)->frag_list)) { if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) goto errout_skb; } #endif if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(nlk->cb_mutex); module_put(module); consume_skb(skb); return 0; errout_skb: mutex_unlock(nlk->cb_mutex); kfree_skb(skb); return err; } int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { struct netlink_sock *nlk, *nlk2; struct netlink_callback *cb; struct sock *sk; int ret; refcount_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { ret = -ECONNREFUSED; goto error_free; } nlk = nlk_sk(sk); mutex_lock(nlk->cb_mutex); /* A dump is in progress... */ if (nlk->cb_running) { ret = -EBUSY; goto error_unlock; } /* add reference of module which cb->dump belongs to */ if (!try_module_get(control->module)) { ret = -EPROTONOSUPPORT; goto error_unlock; } cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; nlk2 = nlk_sk(NETLINK_CB(skb).sk); cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK); if (control->start) { ret = control->start(cb); if (ret) goto error_put; } WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; ret = netlink_dump(sk, true); sock_put(sk); if (ret) return ret; /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ return -EINTR; error_put: module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(nlk->cb_mutex); error_free: kfree_skb(skb); return ret; } EXPORT_SYMBOL(__netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct sk_buff *skb; struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); size_t tlvlen = 0; struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); unsigned int flags = 0; bool nlk_has_extack = nlk->flags & NETLINK_F_EXT_ACK; /* Error messages get the original request appened, unless the user * requests to cap the error message, and get extra error data if * requested. */ if (nlk_has_extack && extack && extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); if (err && !(nlk->flags & NETLINK_F_CAP_ACK)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; if (err && nlk_has_extack && extack && extack->bad_attr) tlvlen += nla_total_size(sizeof(u32)); if (nlk_has_extack && extack && extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); if (err && nlk_has_extack && extack && extack->policy) tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); if (tlvlen) flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); return; } rep = __nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, payload, flags); errmsg = nlmsg_data(rep); errmsg->error = err; memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh)); if (nlk_has_extack && extack) { if (extack->_msg) { WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); } if (err && extack->bad_attr && !WARN_ON((u8 *)extack->bad_attr < in_skb->data || (u8 *)extack->bad_attr >= in_skb->data + in_skb->len)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - (u8 *)nlh)); if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, extack->cookie_len, extack->cookie)); if (extack->policy) netlink_policy_dump_write_attr(skb, extack->policy, NLMSGERR_ATTR_POLICY); } nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); } EXPORT_SYMBOL(netlink_ack); int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; while (skb->len >= nlmsg_total_size(0)) { int msglen; memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return 0; /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) goto ack; /* Skip control messages */ if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) netlink_ack(skb, nlh, err, &extack); skip: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } return 0; } EXPORT_SYMBOL(netlink_rcv_skb); /** * nlmsg_notify - send a notification netlink message * @sk: netlink socket to use * @skb: notification message * @portid: destination netlink portid for reports or 0 * @group: destination multicast group or 0 * @report: 1 to report back, 0 to disable * @flags: allocation flags */ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags) { int err = 0; if (group) { int exclude_portid = 0; if (report) { refcount_inc(&skb->users); exclude_portid = portid; } /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); if (err == -ESRCH) err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); if (!err) err = err2; } return err; } EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { struct seq_net_private p; struct rhashtable_iter hti; int link; }; static void netlink_walk_start(struct nl_seq_iter *iter) { rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti); rhashtable_walk_start(&iter->hti); } static void netlink_walk_stop(struct nl_seq_iter *iter) { rhashtable_walk_stop(&iter->hti); rhashtable_walk_exit(&iter->hti); } static void *__netlink_seq_next(struct seq_file *seq) { struct nl_seq_iter *iter = seq->private; struct netlink_sock *nlk; do { for (;;) { nlk = rhashtable_walk_next(&iter->hti); if (IS_ERR(nlk)) { if (PTR_ERR(nlk) == -EAGAIN) continue; return nlk; } if (nlk) break; netlink_walk_stop(iter); if (++iter->link >= MAX_LINKS) return NULL; netlink_walk_start(iter); } } while (sock_net(&nlk->sk) != seq_file_net(seq)); return nlk; } static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) __acquires(RCU) { struct nl_seq_iter *iter = seq->private; void *obj = SEQ_START_TOKEN; loff_t pos; iter->link = 0; netlink_walk_start(iter); for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) obj = __netlink_seq_next(seq); return obj; } static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return __netlink_seq_next(seq); } static void netlink_native_seq_stop(struct seq_file *seq, void *v) { struct nl_seq_iter *iter = seq->private; if (iter->link >= MAX_LINKS) return; netlink_walk_stop(iter); } static int netlink_native_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk Eth Pid Groups " "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8lu\n", s, s->sk_protocol, nlk->portid, nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) ); } return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__netlink { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct netlink_sock *, sk); }; DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk) static int netlink_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__netlink ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk = nlk_sk((struct sock *)v); return bpf_iter_run_prog(prog, &ctx); } static int netlink_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return netlink_native_seq_show(seq, v); if (v != SEQ_START_TOKEN) return netlink_prog_seq_show(prog, &meta, v); return 0; } static void netlink_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)netlink_prog_seq_show(prog, &meta, v); } netlink_native_seq_stop(seq, v); } #else static int netlink_seq_show(struct seq_file *seq, void *v) { return netlink_native_seq_show(seq, v); } static void netlink_seq_stop(struct seq_file *seq, void *v) { netlink_native_seq_stop(seq, v); } #endif static const struct seq_operations netlink_seq_ops = { .start = netlink_seq_start, .next = netlink_seq_next, .stop = netlink_seq_stop, .show = netlink_seq_show, }; #endif int netlink_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_register_notifier); int netlink_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_unregister_notifier); static const struct proto_ops netlink_ops = { .family = PF_NETLINK, .owner = THIS_MODULE, .release = netlink_release, .bind = netlink_bind, .connect = netlink_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, .poll = datagram_poll, .ioctl = netlink_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = netlink_setsockopt, .getsockopt = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ }; static int __net_init netlink_net_init(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops, sizeof(struct nl_seq_iter))) return -ENOMEM; #endif return 0; } static void __net_exit netlink_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("netlink", net->proc_net); #endif } static void __init netlink_add_usersock_entry(void) { struct listeners *listeners; int groups = 32; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); netlink_table_grab(); nl_table[NETLINK_USERSOCK].groups = groups; rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); nl_table[NETLINK_USERSOCK].module = THIS_MODULE; nl_table[NETLINK_USERSOCK].registered = 1; nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; netlink_table_ungrab(); } static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) { const struct netlink_sock *nlk = data; struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); } static const struct rhashtable_params netlink_rhashtable_params = { .head_offset = offsetof(struct netlink_sock, node), .key_len = netlink_compare_arg_len, .obj_hashfn = netlink_hash, .obj_cmpfn = netlink_compare, .automatic_shrinking = true, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) BTF_ID_LIST(btf_netlink_sock_id) BTF_ID(struct, netlink_sock) static const struct bpf_iter_seq_info netlink_seq_info = { .seq_ops = &netlink_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct nl_seq_iter), }; static struct bpf_iter_reg netlink_reg_info = { .target = "netlink", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__netlink, sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &netlink_seq_info, }; static int __init bpf_iter_register(void) { netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id; return bpf_iter_reg_target(&netlink_reg_info); } #endif static int __init netlink_proto_init(void) { int i; int err = proto_register(&netlink_proto, 0); if (err != 0) goto out; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) err = bpf_iter_register(); if (err) goto out; #endif BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) goto panic; for (i = 0; i < MAX_LINKS; i++) { if (rhashtable_init(&nl_table[i].hash, &netlink_rhashtable_params) < 0) { while (--i > 0) rhashtable_destroy(&nl_table[i].hash); kfree(nl_table); goto panic; } } netlink_add_usersock_entry(); sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); register_pernet_subsys(&netlink_tap_net_ops); /* The netlink device handler may be needed early. */ rtnetlink_init(); out: return err; panic: panic("netlink_init: Cannot allocate nl_table\n"); } core_initcall(netlink_proto_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #endif /* _LINUX_TOPOLOGY_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk> * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blktrace_api.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/debugfs.h> #include <linux/export.h> #include <linux/time.h> #include <linux/uaccess.h> #include <linux/list.h> #include <linux/blk-cgroup.h> #include "../../block/blk.h" #include <trace/events/block.h> #include "trace_output.h" #ifdef CONFIG_BLK_DEV_IO_TRACE static unsigned int blktrace_seq __read_mostly = 1; static struct trace_array *blk_tr; static bool blk_tracer_enabled __read_mostly; static LIST_HEAD(running_trace_list); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock); /* Select an alternative, minimalistic output than the original one */ #define TRACE_BLK_OPT_CLASSIC 0x1 #define TRACE_BLK_OPT_CGROUP 0x2 #define TRACE_BLK_OPT_CGNAME 0x4 static struct tracer_opt blk_tracer_opts[] = { /* Default disable the minimalistic output */ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, #ifdef CONFIG_BLK_CGROUP { TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) }, { TRACER_OPT(blk_cgname, TRACE_BLK_OPT_CGNAME) }, #endif { } }; static struct tracer_flags blk_tracer_flags = { .val = 0, .opts = blk_tracer_opts, }; /* Global reference count of probes */ static DEFINE_MUTEX(blk_probe_mutex); static int blk_probes_ref; static void blk_register_tracepoints(void); static void blk_unregister_tracepoints(void); /* * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, const void *data, size_t len, u64 cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; int pc = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { buffer = blk_tr->array_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len + cgid_len, 0, pc); if (!event) return; t = ring_buffer_event_data(event); goto record_it; } if (!bt->rchan) return; t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len); if (t) { t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->time = ktime_to_ns(ktime_get()); record_it: t->device = bt->dev; t->action = action | (cgid ? __BLK_TN_CGROUP : 0); t->pid = pid; t->cpu = cpu; t->pdu_len = len + cgid_len; if (cgid_len) memcpy((void *)t + sizeof(*t), &cgid, cgid_len); memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); } } /* * Send out a notify for this process, if we haven't done so since a trace * started */ static void trace_note_tsk(struct task_struct *tsk) { unsigned long flags; struct blk_trace *bt; tsk->btrace_seq = blktrace_seq; spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm), 0); } spin_unlock_irqrestore(&running_trace_lock, flags); } static void trace_note_time(struct blk_trace *bt) { struct timespec64 now; unsigned long flags; u32 words[2]; /* need to check user space to see if this breaks in y2038 or y2106 */ ktime_get_real_ts64(&now); words[0] = (u32)now.tv_sec; words[1] = now.tv_nsec; local_irq_save(flags); trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0); local_irq_restore(flags); } void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, const char *fmt, ...) { int n; va_list args; unsigned long flags; char *buf; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer_enabled)) return; /* * If the BLK_TC_NOTIFY action mask isn't set, don't send any note * message to the trace. */ if (!(bt->act_mask & BLK_TC_NOTIFY)) return; local_irq_save(flags); buf = this_cpu_ptr(bt->msg_data); va_start(args, fmt); n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, blkcg ? cgroup_id(blkcg->css.cgroup) : 1); #else trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0); #endif local_irq_restore(flags); } EXPORT_SYMBOL_GPL(__trace_note_message); static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, pid_t pid) { if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0) return 1; if (sector && (sector < bt->start_lba || sector > bt->end_lba)) return 1; if (bt->pid && pid != bt->pid) return 1; return 0; } /* * Data direction bit lookup */ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; #define BLK_TC_RAHEAD BLK_TC_AHEAD #define BLK_TC_PREFLUSH BLK_TC_FLUSH /* The ilog2() calls fall out because they're constant */ #define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \ (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name)) /* * The worker for the various blk_add_trace*() types. Fills out a * blk_io_trace structure and places it in a per-cpu subbuffer. */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int op, int op_flags, u32 what, int error, int pdu_len, void *pdu_data, u64 cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; struct blk_io_trace *t; unsigned long flags = 0; unsigned long *sequence; pid_t pid; int cpu, pc = 0; bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; what |= ddir_act[op_is_write(op) ? WRITE : READ]; what |= MASK_TC_BIT(op_flags, SYNC); what |= MASK_TC_BIT(op_flags, RAHEAD); what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); if (cgid) what |= __BLK_TA_CGROUP; pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) return; cpu = raw_smp_processor_id(); if (blk_tracer) { tracing_record_cmdline(current); buffer = blk_tr->array_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len + cgid_len, 0, pc); if (!event) return; t = ring_buffer_event_data(event); goto record_it; } if (unlikely(tsk->btrace_seq != blktrace_seq)) trace_note_tsk(tsk); /* * A word about the locking here - we disable interrupts to reserve * some space in the relay per-cpu buffer, to prevent an irq * from coming in and stepping on our toes. */ local_irq_save(flags); t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len); if (t) { sequence = per_cpu_ptr(bt->sequence, cpu); t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->sequence = ++(*sequence); t->time = ktime_to_ns(ktime_get()); record_it: /* * These two are not needed in ftrace as they are in the * generic trace_entry, filled by tracing_generic_entry_update, * but for the trace_event->bin() synthesizer benefit we do it * here too. */ t->cpu = cpu; t->pid = pid; t->sector = sector; t->bytes = bytes; t->action = what; t->device = bt->dev; t->error = error; t->pdu_len = pdu_len + cgid_len; if (cgid_len) memcpy((void *)t + sizeof(*t), &cgid, cgid_len); if (pdu_len) memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); if (blk_tracer) { trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); return; } } local_irq_restore(flags); } static void blk_trace_free(struct blk_trace *bt) { debugfs_remove(bt->msg_file); debugfs_remove(bt->dropped_file); relay_close(bt->rchan); debugfs_remove(bt->dir); free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); } static void get_probe_ref(void) { mutex_lock(&blk_probe_mutex); if (++blk_probes_ref == 1) blk_register_tracepoints(); mutex_unlock(&blk_probe_mutex); } static void put_probe_ref(void) { mutex_lock(&blk_probe_mutex); if (!--blk_probes_ref) blk_unregister_tracepoints(); mutex_unlock(&blk_probe_mutex); } static void blk_trace_cleanup(struct blk_trace *bt) { synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } static int __blk_trace_remove(struct request_queue *q) { struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, lockdep_is_held(&q->debugfs_mutex)); if (!bt) return -EINVAL; if (bt->trace_state != Blktrace_running) blk_trace_cleanup(bt); return 0; } int blk_trace_remove(struct request_queue *q) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_remove(q); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_remove); static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct blk_trace *bt = filp->private_data; char buf[16]; snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped)); return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); } static const struct file_operations blk_dropped_fops = { .owner = THIS_MODULE, .open = simple_open, .read = blk_dropped_read, .llseek = default_llseek, }; static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, size_t count, loff_t *ppos) { char *msg; struct blk_trace *bt; if (count >= BLK_TN_MAX_MSG) return -EINVAL; msg = memdup_user_nul(buffer, count); if (IS_ERR(msg)) return PTR_ERR(msg); bt = filp->private_data; __trace_note_message(bt, NULL, "%s", msg); kfree(msg); return count; } static const struct file_operations blk_msg_fops = { .owner = THIS_MODULE, .open = simple_open, .write = blk_msg_write, .llseek = noop_llseek, }; /* * Keep track of how many times we encountered a full subbuffer, to aid * the user space app in telling how many lost events there were. */ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding) { struct blk_trace *bt; if (!relay_buf_full(buf)) return 1; bt = buf->chan->private_data; atomic_inc(&bt->dropped); return 0; } static int blk_remove_buf_file_callback(struct dentry *dentry) { debugfs_remove(dentry); return 0; } static struct dentry *blk_create_buf_file_callback(const char *filename, struct dentry *parent, umode_t mode, struct rchan_buf *buf, int *is_global) { return debugfs_create_file(filename, mode, parent, buf, &relay_file_operations); } static struct rchan_callbacks blk_relay_callbacks = { .subbuf_start = blk_subbuf_start_callback, .create_buf_file = blk_create_buf_file_callback, .remove_buf_file = blk_remove_buf_file_callback, }; static void blk_trace_setup_lba(struct blk_trace *bt, struct block_device *bdev) { struct hd_struct *part = NULL; if (bdev) part = bdev->bd_part; if (part) { bt->start_lba = part->start_sect; bt->end_lba = part->start_sect + part->nr_sects; } else { bt->start_lba = 0; bt->end_lba = -1ULL; } } /* * Setup everything required to start tracing */ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts) { struct blk_trace *bt = NULL; struct dentry *dir = NULL; int ret; lockdep_assert_held(&q->debugfs_mutex); if (!buts->buf_size || !buts->buf_nr) return -EINVAL; strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; /* * some device names have larger paths - convert the slashes * to underscores for this to work as expected */ strreplace(buts->name, '/', '_'); /* * bdev can be NULL, as with scsi-generic, this is a helpful as * we can be. */ if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { pr_warn("Concurrent blktraces are not allowed on %s\n", buts->name); return -EBUSY; } bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; ret = -ENOMEM; bt->sequence = alloc_percpu(unsigned long); if (!bt->sequence) goto err; bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto err; /* * When tracing the whole disk reuse the existing debugfs directory * created by the block layer on init. For partitions block devices, * and scsi-generic block devices we create a temporary new debugfs * directory that will be removed once the trace ends. */ if (bdev && !bdev_is_partition(bdev)) dir = q->debugfs_dir; else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); /* * As blktrace relies on debugfs for its interface the debugfs directory * is required, contrary to the usual mantra of not checking for debugfs * files or directories. */ if (IS_ERR_OR_NULL(dir)) { pr_warn("debugfs_dir not present for %s so skipping\n", buts->name); ret = -ENOENT; goto err; } bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); ret = -EIO; bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops); bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); bt->rchan = relay_open("trace", dir, buts->buf_size, buts->buf_nr, &blk_relay_callbacks, bt); if (!bt->rchan) goto err; bt->act_mask = buts->act_mask; if (!bt->act_mask) bt->act_mask = (u16) -1; blk_trace_setup_lba(bt, bdev); /* overwrite with user settings */ if (buts->start_lba) bt->start_lba = buts->start_lba; if (buts->end_lba) bt->end_lba = buts->end_lba; bt->pid = buts->pid; bt->trace_state = Blktrace_setup; rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); ret = 0; err: if (ret) blk_trace_free(bt); return ret; } static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; int ret; ret = copy_from_user(&buts, arg, sizeof(buts)); if (ret) return -EFAULT; ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; if (copy_to_user(arg, &buts, sizeof(buts))) { __blk_trace_remove(q); return -EFAULT; } return 0; } int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_setup(q, name, dev, bdev, arg); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_setup); #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) static int compat_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; struct compat_blk_user_trace_setup cbuts; int ret; if (copy_from_user(&cbuts, arg, sizeof(cbuts))) return -EFAULT; buts = (struct blk_user_trace_setup) { .act_mask = cbuts.act_mask, .buf_size = cbuts.buf_size, .buf_nr = cbuts.buf_nr, .start_lba = cbuts.start_lba, .end_lba = cbuts.end_lba, .pid = cbuts.pid, }; ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { __blk_trace_remove(q); return -EFAULT; } return 0; } #endif static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; struct blk_trace *bt; bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; /* * For starting a trace, we can transition from a setup or stopped * trace. For stopping a trace, the state must be running */ ret = -EINVAL; if (start) { if (bt->trace_state == Blktrace_setup || bt->trace_state == Blktrace_stopped) { blktrace_seq++; smp_mb(); bt->trace_state = Blktrace_running; spin_lock_irq(&running_trace_lock); list_add(&bt->running_list, &running_trace_list); spin_unlock_irq(&running_trace_lock); trace_note_time(bt); ret = 0; } } else { if (bt->trace_state == Blktrace_running) { bt->trace_state = Blktrace_stopped; spin_lock_irq(&running_trace_lock); list_del_init(&bt->running_list); spin_unlock_irq(&running_trace_lock); relay_flush(bt->rchan); ret = 0; } } return ret; } int blk_trace_startstop(struct request_queue *q, int start) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_startstop(q, start); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_startstop); /* * When reading or writing the blktrace sysfs files, the references to the * opened sysfs or device files should prevent the underlying block device * from being removed. So no further delete protection is really needed. */ /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device * @cmd: the ioctl cmd * @arg: the argument data, if any * **/ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) { struct request_queue *q; int ret, start = 0; char b[BDEVNAME_SIZE]; q = bdev_get_queue(bdev); if (!q) return -ENXIO; mutex_lock(&q->debugfs_mutex); switch (cmd) { case BLKTRACESETUP: bdevname(bdev, b); ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: bdevname(bdev, b); ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #endif case BLKTRACESTART: start = 1; fallthrough; case BLKTRACESTOP: ret = __blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: ret = __blk_trace_remove(q); break; default: ret = -ENOTTY; break; } mutex_unlock(&q->debugfs_mutex); return ret; } /** * blk_trace_shutdown: - stop and cleanup trace structures * @q: the request queue associated with the device * **/ void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->debugfs_mutex); if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } mutex_unlock(&q->debugfs_mutex); } #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { struct blk_trace *bt; /* We don't use the 'bt' value here except as an optimization... */ bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; if (!bio->bi_blkg) return 0; return cgroup_id(bio_blkcg(bio)->css.cgroup); } #else static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { return 0; } #endif static u64 blk_trace_request_get_cgid(struct request *rq) { if (!rq->bio) return 0; /* Use the first bio */ return blk_trace_bio_get_cgid(rq->q, rq->bio); } /* * blktrace probes */ /** * blk_add_trace_rq - Add a trace for a request oriented action * @rq: the source request * @error: return status to log * @nr_bytes: number of completed bytes * @what: the action * @cgid: the cgroup info * * Description: * Records an action against a request. Will log the bio offset + size. * **/ static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); else what |= BLK_TC_ACT(BLK_TC_FS); __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_issue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_merge(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_requeue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, int error, unsigned int nr_bytes) { blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, blk_trace_request_get_cgid(rq)); } /** * blk_add_trace_bio - Add a trace for a bio oriented action * @q: queue the io is for * @bio: the source bio * @what: the action * @error: error, if any * * Description: * Records an action against a bio. Will log the bio offset + size. * **/ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); } static void blk_add_trace_bio_complete(void *ignore, struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, blk_status_to_errno(bio->bi_status)); } static void blk_add_trace_bio_backmerge(void *ignore, struct request_queue *q, struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); } static void blk_add_trace_bio_frontmerge(void *ignore, struct request_queue *q, struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); } static void blk_add_trace_bio_queue(void *ignore, struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0); } static void blk_add_trace_getrq(void *ignore, struct request_queue *q, struct bio *bio, int rw) { if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); else { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, 0); rcu_read_unlock(); } } static void blk_add_trace_sleeprq(void *ignore, struct request_queue *q, struct bio *bio, int rw) { if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); else { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, 0); rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; if (explicit) what = BLK_TA_UNPLUG_IO; else what = BLK_TA_UNPLUG_TIMER; __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_SPLIT, blk_status_to_errno(bio->bi_status), sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } rcu_read_unlock(); } /** * blk_add_trace_bio_remap - Add a trace for a bio-remap operation * @ignore: trace callback data parameter (not used) * @q: queue the io is for * @bio: the source bio * @dev: target device * @from: source sector * * Description: * Device mapper or raid target sometimes need to split a bio because * it spans a stripe (or similar). Add a trace for that action. * **/ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, blk_status_to_errno(bio->bi_status), sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } /** * blk_add_trace_rq_remap - Add a trace for a request-remap operation * @ignore: trace callback data parameter (not used) * @q: queue the io is for * @rq: the source request * @dev: target device * @from: source sector * * Description: * Device mapper remaps request to other devices. * Add a trace for that action. * **/ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), req_op(rq), rq->cmd_flags, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } /** * blk_add_driver_data - Add binary message with driver-specific data * @rq: io request * @data: driver-specific data * @len: length of driver-specific data * * Description: * Some drivers might want to write driver-specific data per request. * **/ void blk_add_driver_data(struct request *rq, void *data, size_t len) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); static void blk_register_tracepoints(void) { int ret; ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); WARN_ON(ret); ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); WARN_ON(ret); ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); WARN_ON(ret); ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); WARN_ON(ret); ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); WARN_ON(ret); ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); WARN_ON(ret); ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); WARN_ON(ret); ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); WARN_ON(ret); ret = register_trace_block_getrq(blk_add_trace_getrq, NULL); WARN_ON(ret); ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); WARN_ON(ret); ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); WARN_ON(ret); ret = register_trace_block_split(blk_add_trace_split, NULL); WARN_ON(ret); ret = register_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); WARN_ON(ret); ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); WARN_ON(ret); } static void blk_unregister_tracepoints(void) { unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); unregister_trace_block_split(blk_add_trace_split, NULL); unregister_trace_block_unplug(blk_add_trace_unplug, NULL); unregister_trace_block_plug(blk_add_trace_plug, NULL); unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); unregister_trace_block_getrq(blk_add_trace_getrq, NULL); unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); tracepoint_synchronize_unregister(); } /* * struct blk_io_tracer formatting routines */ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) { int i = 0; int tc = t->action >> BLK_TC_SHIFT; if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { rwbs[i++] = 'N'; goto out; } if (tc & BLK_TC_FLUSH) rwbs[i++] = 'F'; if (tc & BLK_TC_DISCARD) rwbs[i++] = 'D'; else if (tc & BLK_TC_WRITE) rwbs[i++] = 'W'; else if (t->bytes) rwbs[i++] = 'R'; else rwbs[i++] = 'N'; if (tc & BLK_TC_FUA) rwbs[i++] = 'F'; if (tc & BLK_TC_AHEAD) rwbs[i++] = 'A'; if (tc & BLK_TC_SYNC) rwbs[i++] = 'S'; if (tc & BLK_TC_META) rwbs[i++] = 'M'; out: rwbs[i] = '\0'; } static inline const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) { return (const struct blk_io_trace *)ent; } static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0); } static inline u64 t_cgid(const struct trace_entry *ent) { return *(u64 *)(te_blk_io_trace(ent) + 1); } static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) { return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0); } static inline u32 t_action(const struct trace_entry *ent) { return te_blk_io_trace(ent)->action; } static inline u32 t_bytes(const struct trace_entry *ent) { return te_blk_io_trace(ent)->bytes; } static inline u32 t_sec(const struct trace_entry *ent) { return te_blk_io_trace(ent)->bytes >> 9; } static inline unsigned long long t_sector(const struct trace_entry *ent) { return te_blk_io_trace(ent)->sector; } static inline __u16 t_error(const struct trace_entry *ent) { return te_blk_io_trace(ent)->error; } static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { const __be64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, bool has_cg); static void blk_log_action_classic(struct trace_iterator *iter, const char *act, bool has_cg) { char rwbs[RWBS_LEN]; unsigned long long ts = iter->ts; unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC); unsigned secs = (unsigned long)ts; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); trace_seq_printf(&iter->seq, "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ", MAJOR(t->device), MINOR(t->device), iter->cpu, secs, nsec_rem, iter->ent->pid, act, rwbs); } static void blk_log_action(struct trace_iterator *iter, const char *act, bool has_cg) { char rwbs[RWBS_LEN]; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); if (has_cg) { u64 id = t_cgid(iter->ent); if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { char blkcg_name_buf[NAME_MAX + 1] = "<...>"; cgroup_path_from_kernfs_id(id, blkcg_name_buf, sizeof(blkcg_name_buf)); trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ", MAJOR(t->device), MINOR(t->device), blkcg_name_buf, act, rwbs); } else { /* * The cgid portion used to be "INO,GEN". Userland * builds a FILEID_INO32_GEN fid out of them and * opens the cgroup using open_by_handle_at(2). * While 32bit ino setups are still the same, 64bit * ones now use the 64bit ino as the whole ID and * no longer use generation. * * Regarldess of the content, always output * "LOW32,HIGH32" so that FILEID_INO32_GEN fid can * be mapped back to @id on both 64 and 32bit ino * setups. See __kernfs_fh_to_dentry(). */ trace_seq_printf(&iter->seq, "%3d,%-3d %llx,%-llx %2s %3s ", MAJOR(t->device), MINOR(t->device), id & U32_MAX, id >> 32, act, rwbs); } } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); } static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { const unsigned char *pdu_buf; int pdu_len; int i, end; pdu_buf = pdu_start(ent, has_cg); pdu_len = pdu_real_len(ent, has_cg); if (!pdu_len) return; /* find the last zero that needs to be printed */ for (end = pdu_len - 1; end >= 0; end--) if (pdu_buf[end]) break; end++; trace_seq_putc(s, '('); for (i = 0; i < pdu_len; i++) { trace_seq_printf(s, "%s%02x", i == 0 ? "" : " ", pdu_buf[i]); /* * stop when the rest is just zeroes and indicate so * with a ".." appended */ if (i == end && end != pdu_len - 1) { trace_seq_puts(s, " ..) "); return; } } trace_seq_puts(s, ") "); } static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { trace_seq_printf(s, "%u ", t_bytes(ent)); blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%s]\n", cmd); } else { if (t_sec(ent)) trace_seq_printf(s, "%llu + %u [%s]\n", t_sector(ent), t_sec(ent), cmd); else trace_seq_printf(s, "[%s]\n", cmd); } } static void blk_log_with_error(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%d]\n", t_error(ent)); } else { if (t_sec(ent)) trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent), t_sec(ent), t_error(ent)); else trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent)); } } static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), MAJOR(be32_to_cpu(__r->device_from)), MINOR(be32_to_cpu(__r->device_from)), be64_to_cpu(__r->sector_from)); } static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "[%s]\n", cmd); } static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent, has_cg)); } static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), get_pdu_int(ent, has_cg), cmd); } static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { trace_seq_putmem(s, pdu_start(ent, has_cg), pdu_real_len(ent, has_cg)); trace_seq_putc(s, '\n'); } /* * struct tracer operations */ static void blk_tracer_print_header(struct seq_file *m) { if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return; seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n" "# | | | | | |\n"); } static void blk_tracer_start(struct trace_array *tr) { blk_tracer_enabled = true; } static int blk_tracer_init(struct trace_array *tr) { blk_tr = tr; blk_tracer_start(tr); return 0; } static void blk_tracer_stop(struct trace_array *tr) { blk_tracer_enabled = false; } static void blk_tracer_reset(struct trace_array *tr) { blk_tracer_stop(tr); } static const struct { const char *act[2]; void (*print)(struct trace_seq *s, const struct trace_entry *ent, bool has_cg); } what2act[] = { [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic }, [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic }, [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic }, [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error }, [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic }, [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error }, [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug }, [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug }, [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug }, [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic }, [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split }, [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic }, [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap }, }; static enum print_line_t print_one_line(struct trace_iterator *iter, bool classic) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; const struct blk_io_trace *t; u16 what; bool long_act; blk_log_action_t *log_action; bool has_cg; t = te_blk_io_trace(iter->ent); what = (t->action & ((1 << BLK_TC_SHIFT) - 1)) & ~__BLK_TA_CGROUP; long_act = !!(tr->trace_flags & TRACE_ITER_VERBOSE); log_action = classic ? &blk_log_action_classic : &blk_log_action; has_cg = t->action & __BLK_TA_CGROUP; if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { log_action(iter, long_act ? "message" : "m", has_cg); blk_log_msg(s, iter->ent, has_cg); return trace_handle_return(s); } if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) trace_seq_printf(s, "Unknown action %x\n", what); else { log_action(iter, what2act[what].act[long_act], has_cg); what2act[what].print(s, iter->ent, has_cg); } return trace_handle_return(s); } static enum print_line_t blk_trace_event_print(struct trace_iterator *iter, int flags, struct trace_event *event) { return print_one_line(iter, false); } static void blk_trace_synthesize_old_trace(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct blk_io_trace *t = (struct blk_io_trace *)iter->ent; const int offset = offsetof(struct blk_io_trace, sector); struct blk_io_trace old = { .magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION, .time = iter->ts, }; trace_seq_putmem(s, &old, offset); trace_seq_putmem(s, &t->sector, sizeof(old) - offset + t->pdu_len); } static enum print_line_t blk_trace_event_print_binary(struct trace_iterator *iter, int flags, struct trace_event *event) { blk_trace_synthesize_old_trace(iter); return trace_handle_return(&iter->seq); } static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) { if ((iter->ent->type != TRACE_BLK) || !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return TRACE_TYPE_UNHANDLED; return print_one_line(iter, true); } static int blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* don't output context-info for blk_classic output */ if (bit == TRACE_BLK_OPT_CLASSIC) { if (set) tr->trace_flags &= ~TRACE_ITER_CONTEXT_INFO; else tr->trace_flags |= TRACE_ITER_CONTEXT_INFO; } return 0; } static struct tracer blk_tracer __read_mostly = { .name = "blk", .init = blk_tracer_init, .reset = blk_tracer_reset, .start = blk_tracer_start, .stop = blk_tracer_stop, .print_header = blk_tracer_print_header, .print_line = blk_tracer_print_line, .flags = &blk_tracer_flags, .set_flag = blk_tracer_set_flag, }; static struct trace_event_functions trace_blk_event_funcs = { .trace = blk_trace_event_print, .binary = blk_trace_event_print_binary, }; static struct trace_event trace_blk_event = { .type = TRACE_BLK, .funcs = &trace_blk_event_funcs, }; static int __init init_blk_tracer(void) { if (!register_trace_event(&trace_blk_event)) { pr_warn("Warning: could not register block events\n"); return 1; } if (register_tracer(&blk_tracer) != 0) { pr_warn("Warning: could not register the block tracer\n"); unregister_trace_event(&trace_blk_event); return 1; } return 0; } device_initcall(init_blk_tracer); static int blk_trace_remove_queue(struct request_queue *q) { struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; if (bt->trace_state == Blktrace_running) { bt->trace_state = Blktrace_stopped; spin_lock_irq(&running_trace_lock); list_del_init(&bt->running_list); spin_unlock_irq(&running_trace_lock); relay_flush(bt->rchan); } put_probe_ref(); synchronize_rcu(); blk_trace_free(bt); return 0; } /* * Setup everything required to start tracing */ static int blk_trace_setup_queue(struct request_queue *q, struct block_device *bdev) { struct blk_trace *bt = NULL; int ret = -ENOMEM; bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto free_bt; bt->dev = bdev->bd_dev; bt->act_mask = (u16)-1; blk_trace_setup_lba(bt, bdev); rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); return 0; free_bt: blk_trace_free(bt); return ret; } /* * sysfs interface to enable and configure tracing */ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf); static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); #define BLK_TRACE_DEVICE_ATTR(_name) \ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \ sysfs_blk_trace_attr_show, \ sysfs_blk_trace_attr_store) static BLK_TRACE_DEVICE_ATTR(enable); static BLK_TRACE_DEVICE_ATTR(act_mask); static BLK_TRACE_DEVICE_ATTR(pid); static BLK_TRACE_DEVICE_ATTR(start_lba); static BLK_TRACE_DEVICE_ATTR(end_lba); static struct attribute *blk_trace_attrs[] = { &dev_attr_enable.attr, &dev_attr_act_mask.attr, &dev_attr_pid.attr, &dev_attr_start_lba.attr, &dev_attr_end_lba.attr, NULL }; struct attribute_group blk_trace_attr_group = { .name = "trace", .attrs = blk_trace_attrs, }; static const struct { int mask; const char *str; } mask_maps[] = { { BLK_TC_READ, "read" }, { BLK_TC_WRITE, "write" }, { BLK_TC_FLUSH, "flush" }, { BLK_TC_SYNC, "sync" }, { BLK_TC_QUEUE, "queue" }, { BLK_TC_REQUEUE, "requeue" }, { BLK_TC_ISSUE, "issue" }, { BLK_TC_COMPLETE, "complete" }, { BLK_TC_FS, "fs" }, { BLK_TC_PC, "pc" }, { BLK_TC_NOTIFY, "notify" }, { BLK_TC_AHEAD, "ahead" }, { BLK_TC_META, "meta" }, { BLK_TC_DISCARD, "discard" }, { BLK_TC_DRV_DATA, "drv_data" }, { BLK_TC_FUA, "fua" }, }; static int blk_trace_str2mask(const char *str) { int i; int mask = 0; char *buf, *s, *token; buf = kstrdup(str, GFP_KERNEL); if (buf == NULL) return -ENOMEM; s = strstrip(buf); while (1) { token = strsep(&s, ","); if (token == NULL) break; if (*token == '\0') continue; for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { if (strcasecmp(token, mask_maps[i].str) == 0) { mask |= mask_maps[i].mask; break; } } if (i == ARRAY_SIZE(mask_maps)) { mask = -EINVAL; break; } } kfree(buf); return mask; } static ssize_t blk_trace_mask2str(char *buf, int mask) { int i; char *p = buf; for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { if (mask & mask_maps[i].mask) { p += sprintf(p, "%s%s", (p == buf) ? "" : ",", mask_maps[i].str); } } *p++ = '\n'; return p - buf; } static struct request_queue *blk_trace_get_queue(struct block_device *bdev) { if (bdev->bd_disk == NULL) return NULL; return bdev_get_queue(bdev); } static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf) { struct block_device *bdev = bdget_part(dev_to_part(dev)); struct request_queue *q; struct blk_trace *bt; ssize_t ret = -ENXIO; if (bdev == NULL) goto out; q = blk_trace_get_queue(bdev); if (q == NULL) goto out_bdput; mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); out_bdput: bdput(bdev); out: return ret; } static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct block_device *bdev; struct request_queue *q; struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; if (count == 0) goto out; if (attr == &dev_attr_act_mask) { if (kstrtoull(buf, 0, &value)) { /* Assume it is a list of trace category names */ ret = blk_trace_str2mask(buf); if (ret < 0) goto out; value = ret; } } else if (kstrtoull(buf, 0, &value)) goto out; ret = -ENXIO; bdev = bdget_part(dev_to_part(dev)); if (bdev == NULL) goto out; q = blk_trace_get_queue(bdev); if (q == NULL) goto out_bdput; mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } if (value) ret = blk_trace_setup_queue(q, bdev); else ret = blk_trace_remove_queue(q); goto out_unlock_bdev; } ret = 0; if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); } if (ret == 0) { if (attr == &dev_attr_act_mask) bt->act_mask = value; else if (attr == &dev_attr_pid) bt->pid = value; else if (attr == &dev_attr_start_lba) bt->start_lba = value; else if (attr == &dev_attr_end_lba) bt->end_lba = value; } out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); out_bdput: bdput(bdev); out: return ret ? ret : count; } int blk_trace_init_sysfs(struct device *dev) { return sysfs_create_group(&dev->kobj, &blk_trace_attr_group); } void blk_trace_remove_sysfs(struct device *dev) { sysfs_remove_group(&dev->kobj, &blk_trace_attr_group); } #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_EVENT_TRACING void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes) { int i = 0; if (op & REQ_PREFLUSH) rwbs[i++] = 'F'; switch (op & REQ_OP_MASK) { case REQ_OP_WRITE: case REQ_OP_WRITE_SAME: rwbs[i++] = 'W'; break; case REQ_OP_DISCARD: rwbs[i++] = 'D'; break; case REQ_OP_SECURE_ERASE: rwbs[i++] = 'D'; rwbs[i++] = 'E'; break; case REQ_OP_FLUSH: rwbs[i++] = 'F'; break; case REQ_OP_READ: rwbs[i++] = 'R'; break; default: rwbs[i++] = 'N'; } if (op & REQ_FUA) rwbs[i++] = 'F'; if (op & REQ_RAHEAD) rwbs[i++] = 'A'; if (op & REQ_SYNC) rwbs[i++] = 'S'; if (op & REQ_META) rwbs[i++] = 'M'; rwbs[i] = '\0'; } EXPORT_SYMBOL_GPL(blk_fill_rwbs); #endif /* CONFIG_EVENT_TRACING */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); static inline void copy_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __compiletime_object_size(addr); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H #include <asm/page_64_types.h> #ifndef __ASSEMBLY__ #include <asm/alternative.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; static inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); return x; } #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); extern unsigned long __phys_addr_symbol(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #define __phys_addr_symbol(x) \ ((unsigned long)(x) - __START_KERNEL_map + phys_base) #endif #define __phys_reloc_hide(x) (x) #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) ((pfn) < max_pfn) #endif void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); static inline void clear_page(void *page) { alternative_call_2(clear_page_orig, clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, "=D" (page), "0" (page) : "cc", "memory", "rax", "rcx"); } void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION # define __HAVE_ARCH_GATE_AREA 1 #endif #endif /* _ASM_X86_PAGE_64_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/vmscan.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for try_to_release_page(), buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; /* Can active pages be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped pages be reclaimed? */ unsigned int may_unmap:1; /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file pages on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate pages for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_page(_page, _base, _field) \ do { \ if ((_page)->lru.prev != _base) { \ struct page *prev; \ \ prev = lru_to_page(&(_page->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) #endif /* * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG /* * We allow subsystems to populate their shrinker-related * LRU lists before register_shrinker_prepared() is called * for the shrinker, since we don't want to impose * restrictions on their internal registration order. * In this case shrink_slab_memcg() may find corresponding * bit is set in the shrinkers map. * * This value is used by the function to detect registering * shrinkers and to skip do_shrink_slab() calls for them. */ #define SHRINKER_REGISTERING ((struct shrinker *)~0UL) static DEFINE_IDR(shrinker_idr); static int shrinker_nr_max; static int prealloc_memcg_shrinker(struct shrinker *shrinker) { int id, ret = -ENOMEM; down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { if (memcg_expand_shrinker_maps(id)) { idr_remove(&shrinker_idr, id); goto unlock; } shrinker_nr_max = id + 1; } shrinker->id = id; ret = 0; unlock: up_write(&shrinker_rwsem); return ret; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { int id = shrinker->id; BUG_ON(id < 0); down_write(&shrinker_rwsem); idr_remove(&shrinker_idr, id); up_write(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_page_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { return 0; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { } static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } #endif /* * This misses isolated pages which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated pages will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (get_nr_swap_pages() > 0) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); /* * If there are no reclaimable file-backed or anonymous pages, * ensure zones with sufficient free pages are not skipped. * This prevents zones like DMA32 from being ignored in reclaim * scenarios where they can still help alleviate memory pressure. */ if (nr == 0) nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) */ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } /* * Add a shrinker callback to be called from the vm. */ int prealloc_shrinker(struct shrinker *shrinker) { unsigned int size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); if (!shrinker->nr_deferred) return -ENOMEM; if (shrinker->flags & SHRINKER_MEMCG_AWARE) { if (prealloc_memcg_shrinker(shrinker)) goto free_deferred; } return 0; free_deferred: kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; return -ENOMEM; } void free_prealloced_shrinker(struct shrinker *shrinker) { if (!shrinker->nr_deferred) return; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); #ifdef CONFIG_MEMCG if (shrinker->flags & SHRINKER_MEMCG_AWARE) idr_replace(&shrinker_idr, shrinker, shrinker->id); #endif up_write(&shrinker_rwsem); } int register_shrinker(struct shrinker *shrinker) { int err = prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } EXPORT_SYMBOL(register_shrinker); /* * Remove one */ void unregister_shrinker(struct shrinker *shrinker) { if (!shrinker->nr_deferred) return; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, struct shrinker *shrinker, int priority) { unsigned long freed = 0; unsigned long long delta; long total_scan; long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; /* * copy the current shrinker scan count into a local variable * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); total_scan = nr; if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); total_scan = freeable; next_deferred = nr; } else next_deferred = total_scan; /* * We need to avoid excessive windup on filesystem shrinkers * due to large numbers of GFP_NOFS allocations causing the * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ if (delta < freeable / 4) total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ if (total_scan > freeable * 2) total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); total_scan -= shrinkctl->nr_scanned; scanned += shrinkctl->nr_scanned; cond_resched(); } if (next_deferred >= scanned) next_deferred -= scanned; else next_deferred = 0; /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. If we exhausted the * scan, there is no need to do an update. */ if (next_deferred > 0) new_nr = atomic_long_add_return(next_deferred, &shrinker->nr_deferred[nid]); else new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); return freed; } #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct memcg_shrinker_map *map; unsigned long ret, freed = 0; int i; if (!mem_cgroup_online(memcg)) return 0; if (!down_read_trylock(&shrinker_rwsem)) return 0; map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, true); if (unlikely(!map)) goto unlock; for_each_set_bit(i, map->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { if (!shrinker) clear_bit(i, map->map); continue; } /* Call non-slab shrinkers even though kmem is disabled */ if (!memcg_kmem_enabled() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(i, map->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in * the memcg shrinker map, a new object might have been * added. To make sure, we have the bit set in this * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in * memcg_set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() * <MB> <MB> * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; else memcg_set_shrinker_bit(memcg, nid, i); } freed += ret; if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } unlock: up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } #endif /* CONFIG_MEMCG */ /** * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target * @memcg: memory cgroup whose slab caches to target * @priority: the reclaim priority * * Call the shrink functions to age shrinkable caches. * * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * * @memcg specifies the memory cgroup to target. Unaware shrinkers * are called only if it is the root cgroup. * * @priority is sc->priority, we take the number of objects and >> by priority * in order to get the scan target. * * Returns the number of reclaimed slab objects. */ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { unsigned long ret, freed = 0; struct shrinker *shrinker; /* * The root memcg might be allocated even though memcg is disabled * via "cgroup_disable=memory" boot parameter. This could make * mem_cgroup_is_root() return false, then just run memcg slab * shrink, but skip global shrink. This may result in premature * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) goto out; list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; /* * Bail out if someone want to register a new shrinker to * prevent the registration from being stalled for long periods * by parallel ongoing shrinking. */ if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } up_read(&shrinker_rwsem); out: cond_resched(); return freed; } void drop_slab_node(int nid) { unsigned long freed; do { struct mem_cgroup *memcg = NULL; if (fatal_signal_pending(current)) return; freed = 0; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); } while (freed > 10); } void drop_slab(void) { int nid; for_each_online_node(nid) drop_slab_node(nid); } static inline int is_page_cache_freeable(struct page *page) { /* * A freeable page cache page is referenced only by the caller * that isolated the page, the page cache and optional buffer * heads at page->private. */ int page_cache_pins = thp_nr_pages(page); return page_count(page) - page_has_private(page) == 1 + page_cache_pins; } static int may_write_to_inode(struct inode *inode) { if (current->flags & PF_SWAPWRITE) return 1; if (!inode_write_congested(inode)) return 1; if (inode_to_bdi(inode) == current->backing_dev_info) return 1; return 0; } /* * We detected a synchronous write error writing a page out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the page and once * that page is locked, the mapping is pinned. * * We're allowed to run sleeping lock_page() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct page *page, int error) { lock_page(page); if (page_mapping(page) == mapping) mapping_set_error(mapping, error); unlock_page(page); } /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ PAGE_KEEP, /* move page to the active list, page is locked */ PAGE_ACTIVATE, /* page has been sent to the disk successfully, page is unlocked */ PAGE_SUCCESS, /* page is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_page_list() for each dirty page. * Calls ->writepage(). */ static pageout_t pageout(struct page *page, struct address_space *mapping) { /* * If the page is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * * If the page is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(page)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned pages can have * page->mapping == NULL while being dirty with clean buffers. */ if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); pr_info("%s: orphaned page\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (!may_write_to_inode(mapping->host)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, }; SetPageReclaim(page); res = mapping->a_ops->writepage(page, &wbc); if (res < 0) handle_write_error(mapping, page, res); if (res == AOP_WRITEPAGE_ACTIVATE) { ClearPageReclaim(page); return PAGE_ACTIVATE; } if (!PageWriteback(page)) { /* synchronous write or broken a_ops? */ ClearPageReclaim(page); } trace_mm_vmscan_writepage(page); inc_node_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct page *page, bool reclaimed, struct mem_cgroup *target_memcg) { unsigned long flags; int refcount; void *shadow = NULL; BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); xa_lock_irqsave(&mapping->i_pages, flags); /* * The non racy check for a busy page. * * Must be careful with the order of the tests. When someone has * a ref to the page, it may be possible that they dirty it then * drop the reference. So if PageDirty is tested before page_count * here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !PageDirty(page) [good] * SetPageDirty(page); * put_page(page); * !page_count(page) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the page->flags * load is not satisfied before that of page->_refcount. * * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + compound_nr(page); if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ if (unlikely(PageDirty(page))) { page_ref_unfreeze(page, refcount); goto cannot_free; } if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(page, target_memcg); __delete_from_swap_cache(page, swap, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache pages found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && page_is_file_lru(page) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(page, target_memcg); __delete_from_page_cache(page, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); if (freepage != NULL) freepage(page); } return 1; cannot_free: xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } /* * Attempt to detach a locked page from its ->mapping. If it is dirty or if * someone else has a ref on the page, abort and return 0. If it was * successfully detached, return 1. Assumes the caller has a single ref on * this page. */ int remove_mapping(struct address_space *mapping, struct page *page) { if (__remove_mapping(mapping, page, false, NULL)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ page_ref_unfreeze(page, 1); return 1; } return 0; } /** * putback_lru_page - put previously isolated page onto appropriate LRU list * @page: page to be put back to appropriate lru list * * Add previously isolated @page to appropriate LRU list. * Page may still be unevictable for other reasons. * * lru_lock must not be held, interrupts must be enabled. */ void putback_lru_page(struct page *page) { lru_cache_add(page); put_page(page); /* drop ref from isolate */ } enum page_references { PAGEREF_RECLAIM, PAGEREF_RECLAIM_CLEAN, PAGEREF_KEEP, PAGEREF_ACTIVATE, }; static enum page_references page_check_references(struct page *page, struct scan_control *sc) { int referenced_ptes, referenced_page; unsigned long vm_flags; referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, &vm_flags); referenced_page = TestClearPageReferenced(page); /* * Mlock lost the isolation race with us. Let try_to_unmap() * move the page to the unevictable list. */ if (vm_flags & VM_LOCKED) return PAGEREF_RECLAIM; if (referenced_ptes) { /* * All mapped pages start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file page is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated pages as well * so that recently deactivated but used pages are * quickly recovered. */ SetPageReferenced(page); if (referenced_page || referenced_ptes > 1) return PAGEREF_ACTIVATE; /* * Activate file-backed executable pages after first usage. */ if ((vm_flags & VM_EXEC) && !PageSwapBacked(page)) return PAGEREF_ACTIVATE; return PAGEREF_KEEP; } /* Reclaim if clean, defer dirty pages to writeback */ if (referenced_page && !PageSwapBacked(page)) return PAGEREF_RECLAIM_CLEAN; return PAGEREF_RECLAIM; } /* Check if a page is dirty or under writeback */ static void page_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous pages are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them */ if (!page_is_file_lru(page) || (PageAnon(page) && !PageSwapBacked(page))) { *dirty = false; *writeback = false; return; } /* By default assume that the page flags are accurate */ *dirty = PageDirty(page); *writeback = PageWriteback(page); /* Verify dirty/writeback state if the filesystem supports it */ if (!page_has_private(page)) return; mapping = page_mapping(page); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(page, dirty, writeback); } /* * shrink_page_list() returns the number of reclaimed pages */ static unsigned int shrink_page_list(struct list_head *page_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; memset(stat, 0, sizeof(*stat)); cond_resched(); while (!list_empty(page_list)) { struct address_space *mapping; struct page *page; enum page_references references = PAGEREF_RECLAIM; bool dirty, writeback, may_enter_fs; unsigned int nr_pages; cond_resched(); page = lru_to_page(page_list); list_del(&page->lru); if (!trylock_page(page)) goto keep; VM_BUG_ON_PAGE(PageActive(page), page); nr_pages = compound_nr(page); /* Account the number of base pages even though THP */ sc->nr_scanned += nr_pages; if (unlikely(!page_evictable(page))) goto activate_locked; if (!sc->may_unmap && page_mapped(page)) goto keep_locked; may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); /* * The number of dirty pages determines if a node is marked * reclaim_congested which affects wait_iff_congested. kswapd * will stall and start writing pages if the tail of the LRU * is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty++; if (dirty && !writeback) stat->nr_unqueued_dirty++; /* * Treat this page as congested if the underlying BDI is or if * pages are cycling through the LRU so quickly that the * pages marked for immediate reclaim are making it to the * end of the LRU a second time. */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && inode_write_congested(mapping->host)) || (writeback && PageReclaim(page))) stat->nr_congested++; /* * If a page at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number of pages * under writeback and this page is both under writeback and * PageReclaim then it indicates that pages are being queued * for IO but are being recycled through the LRU before the * IO can complete. Waiting on the page itself risks an * indefinite stall if it is impossible to writeback the * page due to IO error or disconnected storage so instead * note that the LRU is being scanned too quickly and the * caller can stall after page list has been processed. * * 2) Global or new memcg reclaim encounters a page that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the page for immediate * reclaim and continue scanning. * * Require may_enter_fs because we would wait on fs, which * may not have submitted IO yet. And the loop driver might * enter reclaim, and deadlock if it waits on a page for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a page that is already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the pages to get them out of * the way while we continue scanning for clean pages on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (PageWriteback(page)) { /* Case 1 above */ if (current_is_kswapd() && PageReclaim(page) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate++; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !PageReclaim(page) || !may_enter_fs) { /* * This is slightly racy - end_page_writeback() * might have just cleared PageReclaim, then * setting PageReclaim here end up interpreted * as PageReadahead - but that does not matter * enough to care. What we do want is for this * page to have PageReclaim set next time memcg * reclaim reaches the tests above, so it will * then wait_on_page_writeback() to avoid OOM; * and it's also appropriate in global reclaim. */ SetPageReclaim(page); stat->nr_writeback++; goto activate_locked; /* Case 3 above */ } else { unlock_page(page); wait_on_page_writeback(page); /* then go back and try same page again */ list_add_tail(&page->lru, page_list); continue; } } if (!ignore_references) references = page_check_references(page, sc); switch (references) { case PAGEREF_ACTIVATE: goto activate_locked; case PAGEREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: ; /* try to reclaim the page below */ } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree page could be freed directly */ if (PageAnon(page) && PageSwapBacked(page)) { if (!PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (page_maybe_dma_pinned(page)) goto keep_locked; if (PageTransHuge(page)) { /* cannot split THP, skip it */ if (!can_split_huge_page(page, NULL)) goto activate_locked; /* * Split pages without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ if (!compound_mapcount(page) && split_huge_page_to_list(page, page_list)) goto activate_locked; } if (!add_to_swap(page)) { if (!PageTransHuge(page)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_huge_page_to_list(page, page_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(page)) goto activate_locked_split; } may_enter_fs = true; /* Adding to swap updated mapping */ mapping = page_mapping(page); } } else if (unlikely(PageTransHuge(page))) { /* Split file THP */ if (split_huge_page_to_list(page, page_list)) goto keep_locked; } /* * THP may get split above, need minus tail pages and update * nr_pages to avoid accounting tail pages twice. * * The tail pages that are added into swap cache successfully * reach here. */ if ((nr_pages > 1) && !PageTransHuge(page)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (page_mapped(page)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = PageSwapBacked(page); if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; if (!try_to_unmap(page, flags)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && PageSwapBacked(page)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } if (PageDirty(page)) { /* * Only kswapd can writeback filesystem pages * to avoid risk of stack overflow. But avoid * injecting inefficient single-page IO into * flusher writeback as much as possible: only * write pages when we've encountered many * dirty pages, and when we've already scanned * the rest of the LRU for clean pages and see * the same dirty pages again (PageReclaim). */ if (page_is_file_lru(page) && (!current_is_kswapd() || !PageReclaim(page) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() * except we already have the page isolated * and know it's dirty */ inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); SetPageReclaim(page); goto activate_locked; } if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Page is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after IO * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(page, mapping)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: stat->nr_pageout += thp_nr_pages(page); if (PageWriteback(page)) goto keep; if (PageDirty(page)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the page. */ if (!trylock_page(page)) goto keep; if (PageDirty(page) || PageWriteback(page)) goto keep_locked; mapping = page_mapping(page); case PAGE_CLEAN: ; /* try to free the page below */ } } /* * If the page has buffers, try to free the buffer mappings * associated with this page. If we succeed we try to free * the page as well. * * We do this even if the page is PageDirty(). * try_to_release_page() does not perform I/O, but it is * possible for a page to have PageDirty set, but it is actually * clean (all its buffers are clean). This happens if the * buffers were written out directly, with submit_bh(). ext3 * will do this, as well as the blockdev mapping. * try_to_release_page() will discover that cleanness and will * drop the buffers and mark the page clean - it can be freed. * * Rarely, pages can have buffers and no ->mapping. These are * the pages which were not successfully invalidated in * truncate_complete_page(). We try to drop those buffers here * and if that worked, and the page is no longer mapped into * process address space (page_count == 1) it can be freed. * Otherwise, leave the page on the LRU so it is swappable. */ if (page_has_private(page)) { if (!try_to_release_page(page, sc->gfp_mask)) goto activate_locked; if (!mapping && page_count(page) == 1) { unlock_page(page); if (put_page_testzero(page)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this page shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed++; continue; } } } if (PageAnon(page) && !PageSwapBacked(page)) { /* follow __remove_mapping for reference */ if (!page_ref_freeze(page, 1)) goto keep_locked; if (PageDirty(page)) { page_ref_unfreeze(page, 1); goto keep_locked; } count_vm_event(PGLAZYFREED); count_memcg_page_event(page, PGLAZYFREED); } else if (!mapping || !__remove_mapping(mapping, page, true, sc->target_mem_cgroup)) goto keep_locked; unlock_page(page); free_it: /* * THP may get swapped out in a whole, need account * all base pages. */ nr_reclaimed += nr_pages; /* * Is there need to periodically free_page_list? It would * appear not as the counts should be low */ if (unlikely(PageTransHuge(page))) destroy_compound_page(page); else list_add(&page->lru, &free_pages); continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || PageMlocked(page))) try_to_free_swap(page); VM_BUG_ON_PAGE(PageActive(page), page); if (!PageMlocked(page)) { int type = page_is_file_lru(page); SetPageActive(page); stat->nr_activate[type] += nr_pages; count_memcg_page_event(page, PGACTIVATE); } keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_list(&free_pages); try_to_unmap_flush(); free_unref_page_list(&free_pages); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct page *page, *next; LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { if (page_is_file_lru(page) && !PageDirty(page) && !__PageMovable(page) && !PageUnevictable(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } } nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, &stat, true); list_splice(&clean_pages, page_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Attempt to remove the specified page from its LRU. Only take this page * if it is of the appropriate PageActive status. Pages which are being * freed elsewhere are also ignored. * * page: page to consider * mode: one of the LRU isolation modes defined above * * returns 0 on success, -ve errno on failure. */ int __isolate_lru_page(struct page *page, isolate_mode_t mode) { int ret = -EINVAL; /* Only take pages on the LRU. */ if (!PageLRU(page)) return ret; /* Compaction should not handle unevictable pages but CMA can do so */ if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) return ret; ret = -EBUSY; /* * To minimise LRU disruption, the caller can indicate that it only * wants to isolate pages it will be able to operate on without * blocking - clean pages for the most part. * * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages * that it is possible to migrate without blocking */ if (mode & ISOLATE_ASYNC_MIGRATE) { /* All the caller can do on PageWriteback is block */ if (PageWriteback(page)) return ret; if (PageDirty(page)) { struct address_space *mapping; bool migrate_dirty; /* * Only pages without mappings or that have a * ->migratepage callback are possible to migrate * without blocking. However, we can be racing with * truncation so it's necessary to lock the page * to stabilise the mapping as truncation holds * the page lock until after the page is removed * from the page cache. */ if (!trylock_page(page)) return ret; mapping = page_mapping(page); migrate_dirty = !mapping || mapping->a_ops->migratepage; unlock_page(page); if (!migrate_dirty) return ret; } } if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) return ret; if (likely(get_page_unless_zero(page))) { /* * Be careful not to clear PageLRU until after we're * sure the page is not being freed elsewhere -- the * page release code relies on it. */ ClearPageLRU(page); ret = 0; } return ret; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /** * pgdat->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Appropriate locks must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(pages_skipped); isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct page *page; page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); VM_BUG_ON_PAGE(!PageLRU(page), page); nr_pages = compound_nr(page); total_scan += nr_pages; if (page_zonenum(page) > sc->reclaim_idx) { list_move(&page->lru, &pages_skipped); nr_skipped[page_zonenum(page)] += nr_pages; continue; } /* * Do not count skipped pages because that makes the function * return with no isolated pages if the LRU mostly contains * ineligible pages. This causes the VM to not reclaim any * pages, triggering a premature OOM. * * Account all tail pages of THP. This would not cause * premature OOM since __isolate_lru_page() returns -EBUSY * only when the page is being freed somewhere else. */ scan += nr_pages; switch (__isolate_lru_page(page, mode)) { case 0: nr_taken += nr_pages; nr_zone_taken[page_zonenum(page)] += nr_pages; list_move(&page->lru, dst); break; case -EBUSY: /* else it is being freed elsewhere */ list_move(&page->lru, src); continue; default: BUG(); } } /* * Splice any skipped pages to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same pages to skip and put the * system at risk of premature OOM. */ if (!list_empty(&pages_skipped)) { int zid; list_splice(&pages_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, mode, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * isolate_lru_page - tries to isolate a page from its LRU list * @page: page to isolate from its LRU list * * Isolates a @page from an LRU list, clears PageLRU and adjusts the * vmstat statistic corresponding to whatever LRU list the page was on. * * Returns 0 if the page was removed from an LRU list. * Returns -EBUSY if the page was not on an LRU list. * * The returned page will have PageLRU() cleared. If it was found on * the active list, it will have PageActive set. If it was found on * the unevictable list, it will have the PageUnevictable bit set. That flag * may need to be cleared by the caller before letting the page go. * * The vmstat statistic corresponding to the list on which the page was * found will be decremented. * * Restrictions: * * (1) Must be called with an elevated refcount on the page. This is a * fundamental difference from isolate_lru_pages (which is called * without a stable reference). * (2) the lru_lock must not be held. * (3) interrupts must be enabled. */ int isolate_lru_page(struct page *page) { int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; spin_lock_irq(&pgdat->lru_lock); lruvec = mem_cgroup_page_lruvec(page, pgdat); if (PageLRU(page)) { int lru = page_lru(page); get_page(page); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, lru); ret = 0; } spin_unlock_irq(&pgdat->lru_lock); } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; if (current_is_kswapd()) return 0; if (!writeback_throttling_sane(sc)) return 0; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; return isolated > inactive; } /* * This moves pages from @list to corresponding LRU list. * * We move them the other way if the page is referenced by one or more * processes, from rmap. * * If the pages are mostly unmapped, the processing is fast and it is * appropriate to hold zone_lru_lock across the whole operation. But if * the pages are mapped, the processing is slow (page_referenced()) so we * should drop zone_lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because * nobody will play with that bit on a non-LRU page. * * The downside is that we have to touch page->_refcount against each page. * But we had to alter page->flags anyway. * * Returns the number of pages moved to the given lruvec. */ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, struct list_head *list) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); int nr_pages, nr_moved = 0; LIST_HEAD(pages_to_free); struct page *page; enum lru_list lru; while (!list_empty(list)) { page = lru_to_page(list); VM_BUG_ON_PAGE(PageLRU(page), page); if (unlikely(!page_evictable(page))) { list_del(&page->lru); spin_unlock_irq(&pgdat->lru_lock); putback_lru_page(page); spin_lock_irq(&pgdat->lru_lock); continue; } lruvec = mem_cgroup_page_lruvec(page, pgdat); SetPageLRU(page); lru = page_lru(page); nr_pages = thp_nr_pages(page); update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); list_move(&page->lru, &lruvec->lists[lru]); if (put_page_testzero(page)) { __ClearPageLRU(page); __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { spin_unlock_irq(&pgdat->lru_lock); destroy_compound_page(page); spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, &pages_to_free); } else { nr_moved += nr_pages; if (PageActive(page)) workingset_age_nonresident(lruvec, nr_pages); } } /* * To save our caller's stack, now use input list for pages to free. */ list_splice(&pages_to_free, list); return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE. * In that case we should only throttle if the backing device it is * writing to is congested. In other cases it is safe to throttle. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE) || current->backing_dev_info == NULL || bdi_write_congested(current->backing_dev_info); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static noinline_for_stack unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(page_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ msleep(100); stalled = true; /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false); spin_lock_irq(&pgdat->lru_lock); move_pages_to_lru(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); lru_note_cost(lruvec, file, stat.nr_pageout); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&page_list); free_unref_page_list(&page_list); /* * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty pages to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty pages grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) wakeup_flusher_threads(WB_REASON_VMSCAN); sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The pages which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); struct page *page; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); while (!list_empty(&l_hold)) { cond_resched(); page = lru_to_page(&l_hold); list_del(&page->lru); if (unlikely(!page_evictable(page))) { putback_lru_page(page); continue; } if (unlikely(buffer_heads_over_limit)) { if (page_has_private(page) && trylock_page(page)) { if (page_has_private(page)) try_to_release_page(page, 0); unlock_page(page); } } if (page_referenced(page, 0, sc->target_mem_cgroup, &vm_flags)) { /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon pages * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC pages, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) { nr_rotated += thp_nr_pages(page); list_add(&page->lru, &l_active); continue; } } ClearPageActive(page); /* we are de-activating */ SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } /* * Move pages back to the lru list. */ spin_lock_irq(&pgdat->lru_lock); nr_activate = move_pages_to_lru(lruvec, &l_active); nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); /* Keep all free pages in l_active list */ list_splice(&l_inactive, &l_active); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&l_active); free_unref_page_list(&l_active); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } unsigned long reclaim_pages(struct list_head *page_list) { int nid = NUMA_NO_NODE; unsigned int nr_reclaimed = 0; LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; struct page *page; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, }; while (!list_empty(page_list)) { page = lru_to_page(page_list); if (nid == NUMA_NO_NODE) { nid = page_to_nid(page); INIT_LIST_HEAD(&node_page_list); } if (nid == page_to_nid(page)) { ClearPageActive(page); list_move(&page->lru, &node_page_list); continue; } nr_reclaimed += shrink_page_list(&node_page_list, NODE_DATA(nid), &sc, &dummy_stat, false); while (!list_empty(&node_page_list)) { page = lru_to_page(&node_page_list); list_del(&page->lru); putback_lru_page(page); } nid = NUMA_NO_NODE; } if (!list_empty(&node_page_list)) { nr_reclaimed += shrink_page_list(&node_page_list, NODE_DATA(nid), &sc, &dummy_stat, false); while (!list_empty(&node_page_list)) { page = lru_to_page(&node_page_list); list_del(&page->lru); putback_lru_page(page); } } return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * page has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the pages are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; /* * Determine how aggressively the anon and file LRU lists should be * scanned. The relative value of each set of LRU lists is determined * by looking at the fraction of the pages scanned we did rotate back * onto the active list instead of evict. * * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (200 - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { case COMPACT_SUCCESS: case COMPACT_CONTINUE: return false; default: /* check next zone */ ; } } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup *memcg; memcg = mem_cgroup_iter(target_memcg, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable = false; unsigned long file; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&pgdat->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&pgdat->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[0] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[1] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } shrink_node_memcgs(pgdat, sc); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; reclaim_state->reclaimed_slab = 0; } /* Record the subtree's reclaim efficiency */ vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so also forcibly stall. */ if (sc->nr.immediate) congestion_wait(BLK_RW_ASYNC, HZ/10); } /* * Tag a node/memcg as congested if all the dirty pages * scanned were backed by a congested BDI and * wait_iff_congested will stall. * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in wait_iff_congested(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && sc->nr.dirty && sc->nr.dirty == sc->nr.congested) set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* * Stall direct reclaim for IO completions if underlying BDIs * and node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) wait_iff_congested(BLK_RW_ASYNC, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; enum compact_result suitable; if (!gfp_compaction_allowed(sc->gfp_mask)) return false; suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ return true; if (suitable == COMPACT_SKIPPED) /* Compaction cannot yet proceed. Do reclaim. */ return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[0] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[1] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) { wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); goto check_pending; } /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); check_pending: if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_ORDER > S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = may_swap, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void age_active_anon(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (!total_swap_pages) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no populated zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging of the anon list, to give * pages a chance to be referenced before reclaiming. All * pages are rotated regardless of classzone as this is * about consistent aging. */ age_active_anon(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(); ret = try_to_freeze(); __fs_reclaim_acquire(); if (ret || kthread_should_stop()) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); for ( ; ; ) { bool ret; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (ret) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ int kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); int ret = 0; if (pgdat->kswapd) return 0; pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state < SYSTEM_RUNNING); pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); pgdat->kswapd = NULL; } return ret; } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; if (kswapd) { kthread_stop(kswapd); NODE_DATA(nid)->kswapd = NULL; } } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * These bit locations are exposed in the vm.zone_reclaim_mode sysctl * ABI. New bits are OK, but existing bits can never change. */ #define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ #define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ #define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP * and we also need to be able to write out pages for RECLAIM_WRITE * and RECLAIM_UNMAP. */ noreclaim_flag = memalloc_noreclaim_save(); p->flags |= PF_SWAPWRITE; set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); current->flags &= ~PF_SWAPWRITE; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_pages - check pages for evictability and move to * appropriate zone lru list * @pvec: pagevec with lru pages to check * * Checks pages for evictability, if an evictable page is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru pages. */ void check_move_unevictable_pages(struct pagevec *pvec) { struct lruvec *lruvec; struct pglist_data *pgdat = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); int nr_pages; if (PageTransTail(page)) continue; nr_pages = thp_nr_pages(page); pgscanned += nr_pages; if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irq(&pgdat->lru_lock); pgdat = pagepgdat; spin_lock_irq(&pgdat->lru_lock); } lruvec = mem_cgroup_page_lruvec(page, pgdat); if (!PageLRU(page) || !PageUnevictable(page)) continue; if (page_evictable(page)) { enum lru_list lru = page_lru_base_type(page); VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); pgrescued += nr_pages; } } if (pgdat) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); spin_unlock_irq(&pgdat->lru_lock); } } EXPORT_SYMBOL_GPL(check_move_unevictable_pages); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/iso_fs.h> #include <asm/unaligned.h> enum isofs_file_format { isofs_file_normal = 0, isofs_file_sparse = 1, isofs_file_compressed = 2, }; /* * iso fs inode data in memory */ struct iso_inode_info { unsigned long i_iget5_block; unsigned long i_iget5_offset; unsigned int i_first_extent; unsigned char i_file_format; unsigned char i_format_parm[3]; unsigned long i_next_section_block; unsigned long i_next_section_offset; off_t i_section_size; struct inode vfs_inode; }; /* * iso9660 super-block data in memory */ struct isofs_sb_info { unsigned long s_ninodes; unsigned long s_nzones; unsigned long s_firstdatazone; unsigned long s_log_zone_size; unsigned long s_max_size; int s_rock_offset; /* offset of SUSP fields within SU area */ s32 s_sbsector; unsigned char s_joliet_level; unsigned char s_mapping; unsigned char s_check; unsigned char s_session; unsigned int s_high_sierra:1; unsigned int s_rock:2; unsigned int s_cruft:1; /* Broken disks with high byte of length * containing junk */ unsigned int s_nocompress:1; unsigned int s_hide:1; unsigned int s_showassoc:1; unsigned int s_overriderockperm:1; unsigned int s_uid_set:1; unsigned int s_gid_set:1; umode_t s_fmode; umode_t s_dmode; kgid_t s_gid; kuid_t s_uid; struct nls_table *s_nls_iocharset; /* Native language support table */ }; #define ISOFS_INVALID_MODE ((umode_t) -1) static inline struct isofs_sb_info *ISOFS_SB(struct super_block *sb) { return sb->s_fs_info; } static inline struct iso_inode_info *ISOFS_I(struct inode *inode) { return container_of(inode, struct iso_inode_info, vfs_inode); } static inline int isonum_711(u8 *p) { return *p; } static inline int isonum_712(s8 *p) { return *p; } static inline unsigned int isonum_721(u8 *p) { return get_unaligned_le16(p); } static inline unsigned int isonum_722(u8 *p) { return get_unaligned_be16(p); } static inline unsigned int isonum_723(u8 *p) { /* Ignore bigendian datum due to broken mastering programs */ return get_unaligned_le16(p); } static inline unsigned int isonum_731(u8 *p) { return get_unaligned_le32(p); } static inline unsigned int isonum_732(u8 *p) { return get_unaligned_be32(p); } static inline unsigned int isonum_733(u8 *p) { /* Ignore bigendian datum due to broken mastering programs */ return get_unaligned_le32(p); } extern int iso_date(u8 *, int); struct inode; /* To make gcc happy */ extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated); extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *); extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *); int get_joliet_filename(struct iso_directory_record *, unsigned char *, struct inode *); int get_acorn_filename(struct iso_directory_record *, char *, struct inode *); extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int flags); extern struct buffer_head *isofs_bread(struct inode *, sector_t); extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); struct inode *__isofs_iget(struct super_block *sb, unsigned long block, unsigned long offset, int relocated); static inline struct inode *isofs_iget(struct super_block *sb, unsigned long block, unsigned long offset) { return __isofs_iget(sb, block, offset, 0); } static inline struct inode *isofs_iget_reloc(struct super_block *sb, unsigned long block, unsigned long offset) { return __isofs_iget(sb, block, offset, 1); } /* Because the inode number is no longer relevant to finding the * underlying meta-data for an inode, we are free to choose a more * convenient 32-bit number as the inode number. The inode numbering * scheme was recommended by Sergey Vlasov and Eric Lammerts. */ static inline unsigned long isofs_get_ino(unsigned long block, unsigned long offset, unsigned long bufbits) { return (block << (bufbits - 5)) | (offset >> 5); } /* Every directory can have many redundant directory entries scattered * throughout the directory tree. First there is the directory entry * with the name of the directory stored in the parent directory. * Then, there is the "." directory entry stored in the directory * itself. Finally, there are possibly many ".." directory entries * stored in all the subdirectories. * * In order for the NFS get_parent() method to work and for the * general consistency of the dcache, we need to make sure the * "i_iget5_block" and "i_iget5_offset" all point to exactly one of * the many redundant entries for each directory. We normalize the * block and offset by always making them point to the "." directory. * * Notice that we do not use the entry for the directory with the name * that is located in the parent directory. Even though choosing this * first directory is more natural, it is much easier to find the "." * entry in the NFS get_parent() method because it is implicitly * encoded in the "extent + ext_attr_length" fields of _all_ the * redundant entries for the directory. Thus, it can always be * reached regardless of which directory entry you have in hand. * * This works because the "." entry is simply the first directory * record when you start reading the file that holds all the directory * records, and this file starts at "extent + ext_attr_length" blocks. * Because the "." entry is always the first entry listed in the * directories file, the normalized "offset" value is always 0. * * You should pass the directory entry in "de". On return, "block" * and "offset" will hold normalized values. Only directories are * affected making it safe to call even for non-directory file * types. */ static inline void isofs_normalize_block_and_offset(struct iso_directory_record* de, unsigned long *block, unsigned long *offset) { /* Only directories are normalized. */ if (de->flags[0] & 2) { *offset = 0; *block = (unsigned long)isonum_733(de->extent) + (unsigned long)isonum_711(de->ext_attr_length); } } extern const struct inode_operations isofs_dir_inode_operations; extern const struct file_operations isofs_dir_operations; extern const struct address_space_operations isofs_symlink_aops; extern const struct export_operations isofs_export_ops; |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H #include <linux/mmdebug.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); } static inline void mmap_write_lock(struct mm_struct *mm) { down_write(&mm->mmap_lock); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { down_write_nested(&mm->mmap_lock, subclass); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { return down_write_killable(&mm->mmap_lock); } static inline bool mmap_write_trylock(struct mm_struct *mm) { return down_write_trylock(&mm->mmap_lock) != 0; } static inline void mmap_write_unlock(struct mm_struct *mm) { up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { down_read(&mm->mmap_lock); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { return down_read_killable(&mm->mmap_lock); } static inline bool mmap_read_trylock(struct mm_struct *mm) { return down_read_trylock(&mm->mmap_lock) != 0; } static inline void mmap_read_unlock(struct mm_struct *mm) { up_read(&mm->mmap_lock); } static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) { if (down_read_trylock(&mm->mmap_lock)) { rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); return true; } return false; } static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { up_read_non_owner(&mm->mmap_lock); } static inline void mmap_assert_locked(struct mm_struct *mm) { lockdep_assert_held(&mm->mmap_lock); VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline void mmap_assert_write_locked(struct mm_struct *mm) { lockdep_assert_held_write(&mm->mmap_lock); VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); } #endif /* _LINUX_MMAP_LOCK_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/ima.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags, int *empty) { struct filename *result; char *kname; int len; result = audit_reusename(filename); if (result) return result; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { __putname(result); return ERR_PTR(len); } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) { const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; /* * size is chosen that way we to guarantee that * result->iname[0] is within the same object and that * kname can't be equal to result->iname, no matter what. */ result = kzalloc(size, GFP_KERNEL); if (unlikely(!result)) { __putname(kname); return ERR_PTR(-ENOMEM); } result->name = kname; len = strncpy_from_user(kname, filename, PATH_MAX); if (unlikely(len < 0)) { __putname(kname); kfree(result); return ERR_PTR(len); } if (unlikely(len == PATH_MAX)) { __putname(kname); kfree(result); return ERR_PTR(-ENAMETOOLONG); } } result->refcnt = 1; /* The empty path is special. */ if (unlikely(!len)) { if (empty) *empty = 1; if (!(flags & LOOKUP_EMPTY)) { putname(result); return ERR_PTR(-ENOENT); } } result->uptr = filename; result->aname = NULL; audit_getname(result); return result; } struct filename * getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } struct filename * getname_kernel(const char * filename) { struct filename *result; int len = strlen(filename) + 1; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { result->name = (char *)result->iname; } else if (len <= PATH_MAX) { const size_t size = offsetof(struct filename, iname[1]); struct filename *tmp; tmp = kmalloc(size, GFP_KERNEL); if (unlikely(!tmp)) { __putname(result); return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; result = tmp; } else { __putname(result); return ERR_PTR(-ENAMETOOLONG); } memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; result->refcnt = 1; audit_getname(result); return result; } void putname(struct filename *name) { BUG_ON(name->refcnt <= 0); if (--name->refcnt > 0) return; if (name->name != name->iname) { __putname(name->name); kfree(name); } else __putname(name); } static int check_acl(struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(inode, acl, mask); } acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * This does the basic UNIX permission checking. * * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit, * for RCU walking. */ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; /* Are we the owner? If so, ACL's don't matter */ if (likely(uid_eq(current_fsuid(), inode->i_uid))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { if (in_group_p(inode->i_gid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. */ int generic_permission(struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /* * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; if (unlikely(mask & MAY_WRITE)) { /* * Nobody gets write access to an immutable file. */ if (IS_IMMUTABLE(inode)) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EACCES; } retval = do_inode_permission(inode, mask); if (retval) return retval; retval = devcgroup_inode_permission(inode, mask); if (retval) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags; unsigned seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; unsigned root_seq; int dfd; kuid_t dir_uid; umode_t dir_mode; } __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->dfd = dfd; p->name = name; p->path.mnt = NULL; p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void terminate_walk(struct nameidata *nd) { drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->flags & LOOKUP_ROOT_GRABBED) { path_put(&nd->root); nd->flags &= ~LOOKUP_ROOT_GRABBED; } } else { nd->flags &= ~LOOKUP_RCU; rcu_read_unlock(); } nd->depth = 0; nd->path.mnt = NULL; nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; return false; } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* * For scoped-lookups (where nd->root has been zeroed), we need to * restart the whole lookup from scratch -- because set_root() is wrong * for these lookups (nd->dfd is the root, not the filesystem root). */ if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED)) return false; /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT)) return true; nd->flags |= LOOKUP_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); return false; } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * @seq: seq number to check @dentry against * Returns: true on success, false on failure * * Similar to to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) goto out2; if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: rcu_read_unlock(); return false; out_dput: rcu_read_unlock(); dput(dentry); return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->flags & LOOKUP_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (error) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->flags |= LOOKUP_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->flags |= LOOKUP_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } int sysctl_protected_symlinks __read_mostly = 0; int sysctl_protected_hardlinks __read_mostly = 0; int sysctl_protected_fifos __read_mostly; int sysctl_protected_regular __read_mostly; /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { if (!sysctl_protected_symlinks) return 0; /* Allowed if owner and follower match. */ if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * Returns 0 if successful, -ve on error. */ int may_linkat(struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @dir_mode: mode bits of directory * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; if (likely(dir_mode & 0002) || (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { const char *operation = S_ISFIFO(inode->i_mode) ? "sticky_create_fifo" : "sticky_create_regular"; audit_log_path_denied(AUDIT_ANOM_CREAT, operation); return -EACCES; } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; /* No need to trigger automounts if mountpoint crossing is disabled. */ if (lookup_flags & LOOKUP_NO_XDEV) return -EXDEV; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { if (lookup_flags & LOOKUP_NO_XDEV) { ret = -EXDEV; break; } ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, 0); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, struct inode **inode, unsigned *seqp) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (likely(!(flags & DCACHE_MANAGED_DENTRY))) return true; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->flags |= LOOKUP_JUMPED; *seqp = read_seqcount_begin(&dentry->d_seq); *inode = dentry->d_inode; /* * We don't need to re-check ->d_seq after this * ->d_inode read - there will be an RCU delay * between mount hash removal and ->mnt_root * becoming unpinned. */ flags = dentry->d_flags; if (read_seqretry(&mount_lock, nd->m_seq)) return false; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path, struct inode **inode, unsigned int *seqp) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = *seqp; if (unlikely(!*inode)) return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; path->dentry = dentry; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV)) ret = -EXDEV; else nd->flags |= LOOKUP_JUMPED; } if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } else { *inode = d_backing_inode(path->dentry); *seqp = 0; /* out of RCU mode, so the value doesn't matter */ } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. */ static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; struct inode *dir = base->d_inode; if (dentry) return dentry; /* Don't create child dentry for a dead directory. */ if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } return dentry; } static struct dentry *lookup_fast(struct nameidata *nd, struct inode **inode, unsigned *seqp) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the inode matches * the dentry name information from lookup. */ *inode = d_backing_inode(dentry); if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) return ERR_PTR(-ECHILD); /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. * * The memory barrier in read_seqcount_begin of child is * enough, we can use __read_seqcount_retry here. */ if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) return ERR_PTR(-ECHILD); *seqp = seq; status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); if (unlikely(status == -ECHILD)) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name, &wq); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD || !try_to_unlazy(nd)) return err; } return inode_permission(nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, unsigned seq, int flags) { struct saved *last; const char *res; int error = reserve_stack(nd, link, seq); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (!(nd->flags & LOOKUP_RCU)) { touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. */ static const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry, struct inode *inode, unsigned seq) { struct path path; int err = handle_mounts(nd, dentry, &path, &inode, &seq); if (err < 0) return ERR_PTR(err); if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (!(nd->flags & LOOKUP_RCU)) { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = seq; return NULL; } if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink above matches inode */ if (read_seqcount_retry(&path.dentry->d_seq, seq)) return ERR_PTR(-ECHILD); } else { if (path.mnt == nd->path.mnt) mntget(path.mnt); } return pick_link(nd, &path, inode, seq, flags); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; *inodep = parent->d_inode; *seqp = read_seqcount_begin(&parent->d_seq); if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq))) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); return NULL; } static struct dentry *follow_dotdot(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } *seqp = 0; *inodep = parent->d_inode; return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); dget(nd->path.dentry); return NULL; } static const char *handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; struct inode *inode; unsigned seq; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (error) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd, &inode, &seq); else parent = follow_dotdot(nd, &inode, &seq); if (IS_ERR(parent)) return ERR_CAST(parent); if (unlikely(!parent)) error = step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq); else error = step_into(nd, WALK_NOFOLLOW, parent, inode, seq); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))) return ERR_PTR(-EAGAIN); if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))) return ERR_PTR(-EAGAIN); } } return NULL; } static const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; struct inode *inode; unsigned seq; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return step_into(nd, flags, dentry, inode, seq); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * Calculate the length and hash of the path component, and * return the "hash_len" as the result. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long a = 0, b, x = 0, y = (unsigned long)salt; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; do { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); return hashlen_create(end_name_hash(hash), len); } #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); while (*name=='/') name++; if (!*name) return 0; /* At this point we know we have a real path component. */ for(;;) { const char *link; u64 hash_len; int type; err = may_lookup(nd); if (err) return err; hash_len = hash_name(nd->path.dentry, name); type = LAST_NORM; if (name[0] == '.') switch (hashlen_len(hash_len)) { case 2: if (name[1] == '.') { type = LAST_DOTDOT; nd->flags |= LOOKUP_JUMPED; } break; case 1: type = LAST_DOT; } if (likely(type == LAST_NORM)) { struct dentry *parent = nd->path.dentry; nd->flags &= ~LOOKUP_JUMPED; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { struct qstr this = { { .hash_len = hash_len }, .name = name }; err = parent->d_op->d_hash(parent, &this); if (err < 0) return err; hash_len = this.hash_len; name = this.name; } } nd->last.hash_len = hash_len; nd->last.name = name; nd->last_type = type; name += hashlen_len(hash_len); if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (!depth) { nd->dir_uid = nd->inode->i_uid; nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->name->name; /* LOOKUP_CACHED requires RCU, ask caller to retry */ if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) return ERR_PTR(-EAGAIN); if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); nd->flags = flags | LOOKUP_JUMPED; nd->depth = 0; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ struct fd f = fdget_raw(nd->dfd); struct dentry *dentry; if (!f.file) return ERR_PTR(-EBADF); dentry = f.file->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) { fdput(f); return ERR_PTR(-ENOTDIR); } nd->path = f.file->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } fdput(f); } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (flags & LOOKUP_IS_SCOPED) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq)); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); if (unlikely(root)) { nd.root = *root; flags |= LOOKUP_ROOT; } set_nameidata(&nd, dfd, name); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); putname(name); return retval; } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } static struct filename *filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { int retval; struct nameidata nd; if (IS_ERR(name)) return name; set_nameidata(&nd, dfd, name); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } else { putname(name); name = ERR_PTR(retval); } restore_nameidata(); return name; } /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { struct filename *filename; struct dentry *d; struct qstr last; int type; filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path, &last, &type); if (IS_ERR(filename)) return ERR_CAST(filename); if (unlikely(type != LAST_NORM)) { path_put(path); putname(filename); return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); d = __lookup_hash(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); } putname(filename); return d; } int kern_path(const char *name, unsigned int flags, struct path *path) { return filename_lookup(AT_FDCWD, getname_kernel(name), flags, path, NULL); } EXPORT_SYMBOL(kern_path); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { struct path root = {.mnt = mnt, .dentry = dentry}; /* the first argument of filename_lookup() is ignored with root */ return filename_lookup(AT_FDCWD, getname_kernel(name), flags , path, &root); } EXPORT_SYMBOL(vfs_path_lookup); static int lookup_one_len_common(const char *name, struct dentry *base, int len, struct qstr *this) { this->name = name; this->len = len; this->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (unlikely(name[0] == '.')) { if (len < 2 || (len == 2 && name[1] == '.')) return -EACCES; } while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, this); if (err < 0) return err; } return inode_permission(base->d_inode, MAY_EXEC); } /** * try_lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) { struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); return lookup_dcache(&this, base, 0); } EXPORT_SYMBOL(try_lookup_one_len); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { struct dentry *dentry; struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0); return dentry ? dentry : __lookup_slow(&this, base, 0); } EXPORT_SYMBOL(lookup_one_len); /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { struct qstr this; int err; struct dentry *ret; err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); ret = lookup_dcache(&this, base, 0); if (!ret) ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_len_unlocked); /* * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_one_len_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { struct dentry *ret = lookup_one_len_unlocked(name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_positive_unlocked); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; struct qstr this = QSTR_INIT("pts", 3); if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; dput(parent); follow_down(path); return 0; } #endif int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { return filename_lookup(dfd, getname_flags(name, flags, empty), flags, path, NULL); } EXPORT_SYMBOL(user_path_at_empty); int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ static inline int may_create(struct inode *dir, struct dentry *child) { struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; s_user_ns = dir->i_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; return inode_permission(dir, MAY_WRITE | MAY_EXEC); } /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { struct dentry *p; if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } p = d_ancestor(p1, p2); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return p; } EXPORT_SYMBOL(lock_rename); void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } EXPORT_SYMBOL(unlock_rename); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * Umask stripping depends on whether or not the filesystem supports POSIX * ACLs. If the filesystem doesn't support it umask stripping is done directly * in here. If the filesystem does support POSIX ACLs umask stripping is * deferred until the filesystem calls posix_acl_create(). * * Returns: mode */ static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir)) mode &= ~current_umask(); return mode; } /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Note that it's currently valid for @type to be 0 if a directory is created. * Filesystems raise that flag individually and we need to check whether each * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a * non-zero type. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { mode = mode_strip_sgid(dir, mode); mode = mode_strip_umask(dir, mode); /* * Apply the vfs mandated allowed permission mask and set the type of * file to be created before we call into the filesystem. */ mode &= (mask_perms & ~S_IFMT); mode |= (type & S_IFMT); return mode; } int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode = vfs_prepare_mode(dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; error = dir->i_op->create(dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create(dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; } error = inode_permission(inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(inode)) return -EPERM; return 0; } static int handle_truncate(struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; /* * Refuse to truncate files with mandatory locks held on them. */ error = locks_verify_locked(filp); if (!error) error = security_path_truncate(path); if (!error) { error = do_truncate(path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; s_user_ns = dir->dentry->d_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; int error; if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; error = dir->i_op->atomic_open(dir, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { if (unlikely(dentry != file->f_path.dentry)) { dput(dentry); dentry = dget(file->f_path.dentry); } } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { if (file->f_path.dentry) { dput(dentry); dentry = file->f_path.dentry; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } } if (error) { dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) return dentry; } if (d_in_lookup(dentry)) break; error = d_revalidate(dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ return dentry; } /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; mode = vfs_prepare_mode(dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(&nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { dentry = atomic_open(nd, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error); return dentry; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } return dentry; out_dput: dput(dentry); return ERR_PTR(error); } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; unsigned seq; struct inode *inode; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ if (unlikely(nd->last.name[nd->last.len])) return ERR_PTR(-EISDIR); } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be * dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write); if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED)) fsnotify_create(dir->d_inode, dentry); if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry, inode, seq); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(nd->dir_mode, nd->dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(&nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; int error; /* we want directory to be writable */ error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; mode = vfs_prepare_mode(dir, mode, mode, mode); error = dir->i_op->tmpfile(dir, child, mode); if (error) goto out_err; error = -ENOENT; inode = child->d_inode; if (unlikely(!inode)) goto out_err; if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } ima_post_create_tmpfile(inode); return child; out_err: dput(child); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_tmpfile); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct dentry *child; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); error = PTR_ERR(child); if (IS_ERR(child)) goto out2; dput(path.dentry); path.dentry = child; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; error = finish_open(file, child, NULL); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; set_nameidata(&nd, dfd, pathname); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; struct filename *filename; int flags = op->lookup_flags | LOOKUP_ROOT; nd.root.mnt = mnt; nd.root.dentry = dentry; if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); filename = getname_kernel(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); putname(filename); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; int type; int err2; int error; bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); /* * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any * other flags passed in are ignored! */ lookup_flags &= LOOKUP_REVAL; name = filename_parentat(dfd, name, lookup_flags, path, &last, &type); if (IS_ERR(name)) return ERR_CAST(name); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* * Do the final lookup. */ lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path->dentry, lookup_flags); if (IS_ERR(dentry)) goto unlock; error = -EEXIST; if (d_is_positive(dentry)) goto fail; /* * Special case - lookup gave negative, but... we had foo/bar/ * From the vfs_mknod() POV we just have a negative dentry - * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ if (unlikely(!is_dir && last.name[last.len])) { error = -ENOENT; goto fail; } if (unlikely(err2)) { error = err2; goto fail; } putname(name); return dentry; fail: dput(dentry); dentry = ERR_PTR(error); unlock: inode_unlock(path->dentry->d_inode); if (!err2) mnt_drop_write(path->mnt); out: path_put(path); putname(name); return dentry; } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname_kernel(pathname), path, lookup_flags); } EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) { dput(dentry); inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname(pathname), path, lookup_flags); } EXPORT_SYMBOL(user_path_create); int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create(dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; mode = vfs_prepare_mode(dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = dir->i_op->mknod(dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } static long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) return error; retry: dentry = user_path_create(dfd, filename, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mknod(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(path.dentry->d_inode,dentry,mode,true); if (!error) ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); break; } out: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { return do_mknodat(dfd, filename, mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { return do_mknodat(AT_FDCWD, filename, mode, dev); } int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error = may_create(dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) return error; if (!dir->i_op->mkdir) return -EPERM; mode = vfs_prepare_mode(dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; if (max_links && dir->i_nlink >= max_links) return -EMLINK; error = dir->i_op->mkdir(dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkdir); static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: dentry = user_path_create(dfd, pathname, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) error = vfs_mkdir(path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { return do_mkdirat(dfd, pathname, mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { return do_mkdirat(AT_FDCWD, pathname, mode); } int vfs_rmdir(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 1); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); long do_rmdir(int dfd, struct filename *name) { int error = 0; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; goto exit1; case LAST_DOT: error = -EINVAL; goto exit1; case LAST_ROOT: error = -EBUSY; goto exit1; } error = mnt_want_write(path.mnt); if (error) goto exit1; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit2; if (!dentry->d_inode) { error = -ENOENT; goto exit3; } error = security_path_rmdir(&path, dentry); if (error) goto exit3; error = vfs_rmdir(path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } putname(name); return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { return do_rmdir(AT_FDCWD, getname(pathname)); } /** * vfs_unlink - unlink a filesystem object * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_mutex. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete(dir, dentry, 0); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(target, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { fsnotify_unlink(dir, dentry); } else if (!error) { fsnotify_link_count(target); d_delete_notify(dir, dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_mutex. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ long do_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; struct inode *inode = NULL; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); error = -EISDIR; if (type != LAST_NORM) goto exit1; error = mnt_want_write(path.mnt); if (error) goto exit1; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ if (last.name[last.len]) goto slashes; inode = dentry->d_inode; if (d_is_negative(dentry)) goto slashes; ihold(inode); error = security_path_unlink(&path, dentry); if (error) goto exit2; error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); exit2: dput(dentry); } inode_unlock(path.dentry->d_inode); if (inode) iput(inode); /* truncate the inode here */ inode = NULL; if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; inode = NULL; goto retry; } putname(name); return error; slashes: if (d_is_negative(dentry)) error = -ENOENT; else if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; goto exit2; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; if (flag & AT_REMOVEDIR) return do_rmdir(dfd, getname(pathname)); return do_unlinkat(dfd, getname(pathname)); } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { return do_unlinkat(AT_FDCWD, getname(pathname)); } int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->symlink) return -EPERM; error = security_inode_symlink(dir, dentry, oldname); if (error) return error; error = dir->i_op->symlink(dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); static long do_symlinkat(const char __user *oldname, int newdfd, const char __user *newname) { int error; struct filename *from; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; from = getname(oldname); if (IS_ERR(from)) return PTR_ERR(from); retry: dentry = user_path_create(newdfd, newname, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putname; error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out_putname: putname(from); return error; } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_symlinkat(oldname, newdfd, newname); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { return do_symlinkat(oldname, AT_FDCWD, newname); } /** * vfs_link - create a new link * @old_dentry: object to be linked * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_mutex * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; int error; if (!inode) return -ENOENT; error = may_create(dir, new_dentry); if (error) return error; if (dir->i_sb != inode->i_sb) return -EXDEV; /* * A link to an append-only or immutable file cannot be created. */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; /* * Updating the link count will likely cause i_uid and i_gid to * be writen back improperly if their true value is unknown to * the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; if (S_ISDIR(inode->i_mode)) return -EPERM; error = security_inode_link(old_dentry, dir, new_dentry); if (error) return error; inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { error = try_break_deleg(inode, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } if (!error && (inode->i_state & I_LINKABLE)) { spin_lock(&inode->i_lock); inode->i_state &= ~I_LINKABLE; spin_unlock(&inode->i_lock); } inode_unlock(inode); if (!error) fsnotify_link(dir, inode, new_dentry); return error; } EXPORT_SYMBOL(vfs_link); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ static int do_linkat(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, int flags) { struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; int how = 0; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; /* * To use null names we require CAP_DAC_READ_SEARCH * This ensures that not everyone will be able to create * handlink using the passed filedescriptor. */ if (flags & AT_EMPTY_PATH) { if (!capable(CAP_DAC_READ_SEARCH)) return -ENOENT; how = LOOKUP_EMPTY; } if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: error = user_path_at(olddfd, oldname, how, &old_path); if (error) return error; new_dentry = user_path_create(newdfd, newname, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; error = may_linkat(&old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); goto retry; } } if (retry_estale(error, how)) { path_put(&old_path); how |= LOOKUP_REVAL; goto retry; } out: path_put(&old_path); return error; } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { return do_linkat(olddfd, oldname, newdfd, newname, flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } /** * vfs_rename - rename a filesystem object * @old_dir: parent of source * @old_dentry: source * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct renamedata *rd) { int error; struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir; struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; struct inode **delegated_inode = rd->delegated_inode; unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; error = may_delete(old_dir, old_dentry, is_dir); if (error) return error; if (!target) { error = may_create(new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) error = may_delete(new_dir, new_dentry, is_dir); else error = may_delete(new_dir, new_dentry, new_is_dir); } if (error) return error; if (!old_dir->i_op->rename) return -EPERM; /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { if (is_dir) { error = inode_permission(source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { error = inode_permission(target, MAY_WRITE); if (error) return error; } } error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) return error; take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* * Lock children. * The source subdirectory needs to be locked on cross-directory * rename or cross-directory exchange since its parent changes. * The target subdirectory needs to be locked on cross-directory * exchange due to parent change and on any rename due to becoming * a victim. * Non-directories need locking in all cases (for NFS reasons); * they get locked after any subdirectories (in inode address order). * * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ lock_old_subdir = new_dir != old_dir; lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); if (is_dir) { if (lock_old_subdir) inode_lock_nested(source, I_MUTEX_CHILD); if (target && (!new_is_dir || lock_new_subdir)) inode_lock(target); } else if (new_is_dir) { if (lock_new_subdir) inode_lock_nested(target, I_MUTEX_CHILD); inode_lock(source); } else { lock_two_nondirectories(source, target); } error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) goto out; if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && old_dir->i_nlink >= max_links) goto out; } if (!is_dir) { error = try_break_deleg(source, delegated_inode); if (error) goto out; } if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; if (!(flags & RENAME_EXCHANGE) && target) { if (is_dir) { shrink_dcache_parent(new_dentry); target->i_flags |= S_DEAD; } dont_mount(new_dentry); detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE)) d_move(old_dentry, new_dentry); else d_exchange(old_dentry, new_dentry); } out: if (!is_dir || lock_old_subdir) inode_unlock(source); if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } release_dentry_name_snapshot(&old_name); return error; } EXPORT_SYMBOL(vfs_rename); int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct renamedata rd; struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) goto put_both; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) goto put_both; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: from = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); if (IS_ERR(from)) { error = PTR_ERR(from); goto put_new; } to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, &new_type); if (IS_ERR(to)) { error = PTR_ERR(to); goto exit1; } error = -EXDEV; if (old_path.mnt != new_path.mnt) goto exit2; error = -EBUSY; if (old_type != LAST_NORM) goto exit2; if (flags & RENAME_NOREPLACE) error = -EEXIST; if (new_type != LAST_NORM) goto exit2; error = mnt_want_write(old_path.mnt); if (error) goto exit2; retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; /* source must exist */ error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; error = -EEXIST; if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) goto exit5; if (flags & RENAME_EXCHANGE) { error = -ENOENT; if (d_is_negative(new_dentry)) goto exit5; if (!d_is_dir(new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) goto exit5; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) goto exit5; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) goto exit5; } /* source should not be ancestor of target */ error = -EINVAL; if (old_dentry == trap) goto exit5; /* target should not be an ancestor of source */ if (!(flags & RENAME_EXCHANGE)) error = -ENOTEMPTY; if (new_dentry == trap) goto exit5; error = security_path_rename(&old_path, old_dentry, &new_path, new_dentry, flags); if (error) goto exit5; rd.old_dir = old_path.dentry->d_inode; rd.old_dentry = old_dentry; rd.new_dir = new_path.dentry->d_inode; rd.new_dentry = new_dentry; rd.delegated_inode = &delegated_inode; rd.flags = flags; error = vfs_rename(&rd); exit5: dput(new_dentry); exit4: dput(old_dentry); exit3: unlock_rename(new_path.dentry, old_path.dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(old_path.mnt); exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); exit1: path_put(&old_path); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } put_both: if (!IS_ERR(from)) putname(from); put_new: if (!IS_ERR(to)) putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0); } int readlink_copy(char __user *buffer, int buflen, const char *link) { int len = PTR_ERR(link); if (IS_ERR(link)) goto out; len = strlen(link); if (len > (unsigned) buflen) len = buflen; if (copy_to_user(buffer, link, len)) len = -EFAULT; out: return len; } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); DEFINE_DELAYED_CALL(done); const char *link; int res; if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); if (!d_is_symlink(dentry)) return -EINVAL; spin_lock(&inode->i_lock); inode->i_opflags |= IOP_DEFAULT_READLINK; spin_unlock(&inode->i_lock); } link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link); do_delayed_call(&done); return res; } EXPORT_SYMBOL(vfs_readlink); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { const char *res = ERR_PTR(-EINVAL); struct inode *inode = d_inode(dentry); if (d_is_symlink(dentry)) { res = ERR_PTR(security_inode_readlink(dentry)); if (!res) res = inode->i_op->get_link(dentry, inode, done); } return res; } EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ static char *__page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { struct page *page; struct address_space *mapping = inode->i_mapping; if (!dentry) { page = find_get_page(mapping, 0); if (!page) return ERR_PTR(-ECHILD); if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } } else { page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) return (char*)page; } set_delayed_call(callback, page_put_link, page); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); return page_address(page); } const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { return __page_get_link(dentry, inode, callback); } EXPORT_SYMBOL_GPL(page_get_link_raw); const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { char *kaddr = __page_get_link(dentry, inode, callback); if (!IS_ERR(kaddr)) nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } EXPORT_SYMBOL(page_get_link); void page_put_link(void *arg) { put_page(arg); } EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { DEFINE_DELAYED_CALL(done); int res = readlink_copy(buffer, buflen, page_get_link(dentry, d_inode(dentry), &done)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(page_readlink); /* * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS */ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; unsigned int flags = 0; if (nofs) flags |= AOP_FLAG_NOFS; retry: err = pagecache_write_begin(NULL, mapping, 0, len-1, flags, &page, &fsdata); if (err) goto fail; memcpy(page_address(page), symname, len-1); err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); if (err < 0) goto fail; if (err < len-1) goto retry; mark_inode_dirty(inode); return 0; fail: return err; } EXPORT_SYMBOL(__page_symlink); int page_symlink(struct inode *inode, const char *symname, int len) { return __page_symlink(inode, symname, len, !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 | /* * linux/fs/nls/nls_base.c * * Native language support--charsets and unicode translations. * By Gordon Chaffee 1996, 1997 * * Unicode based case conversion 1999 by Wolfram Pienkoss * */ #include <linux/module.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/kmod.h> #include <linux/spinlock.h> #include <asm/byteorder.h> static struct nls_table default_table; static struct nls_table *tables = &default_table; static DEFINE_SPINLOCK(nls_lock); /* * Sample implementation from Unicode home page. * http://www.stonehand.com/unicode/standard/fss-utf.html */ struct utf8_table { int cmask; int cval; int shift; long lmask; long lval; }; static const struct utf8_table utf8_table[] = { {0x80, 0x00, 0*6, 0x7F, 0, /* 1 byte sequence */}, {0xE0, 0xC0, 1*6, 0x7FF, 0x80, /* 2 byte sequence */}, {0xF0, 0xE0, 2*6, 0xFFFF, 0x800, /* 3 byte sequence */}, {0xF8, 0xF0, 3*6, 0x1FFFFF, 0x10000, /* 4 byte sequence */}, {0xFC, 0xF8, 4*6, 0x3FFFFFF, 0x200000, /* 5 byte sequence */}, {0xFE, 0xFC, 5*6, 0x7FFFFFFF, 0x4000000, /* 6 byte sequence */}, {0, /* end of table */} }; #define UNICODE_MAX 0x0010ffff #define PLANE_SIZE 0x00010000 #define SURROGATE_MASK 0xfffff800 #define SURROGATE_PAIR 0x0000d800 #define SURROGATE_LOW 0x00000400 #define SURROGATE_BITS 0x000003ff int utf8_to_utf32(const u8 *s, int inlen, unicode_t *pu) { unsigned long l; int c0, c, nc; const struct utf8_table *t; nc = 0; c0 = *s; l = c0; for (t = utf8_table; t->cmask; t++) { nc++; if ((c0 & t->cmask) == t->cval) { l &= t->lmask; if (l < t->lval || l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR) return -EILSEQ; *pu = (unicode_t) l; return nc; } if (inlen <= nc) return -EOVERFLOW; s++; c = (*s ^ 0x80) & 0xFF; if (c & 0xC0) return -EILSEQ; l = (l << 6) | c; } return -EILSEQ; } EXPORT_SYMBOL(utf8_to_utf32); int utf32_to_utf8(unicode_t u, u8 *s, int maxout) { unsigned long l; int c, nc; const struct utf8_table *t; if (!s) return 0; l = u; if (l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR) return -EILSEQ; nc = 0; for (t = utf8_table; t->cmask && maxout; t++, maxout--) { nc++; if (l <= t->lmask) { c = t->shift; *s = (u8) (t->cval | (l >> c)); while (c > 0) { c -= 6; s++; *s = (u8) (0x80 | ((l >> c) & 0x3F)); } return nc; } } return -EOVERFLOW; } EXPORT_SYMBOL(utf32_to_utf8); static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian) { switch (endian) { default: *s = (wchar_t) c; break; case UTF16_LITTLE_ENDIAN: *s = __cpu_to_le16(c); break; case UTF16_BIG_ENDIAN: *s = __cpu_to_be16(c); break; } } int utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian, wchar_t *pwcs, int maxout) { u16 *op; int size; unicode_t u; op = pwcs; while (inlen > 0 && maxout > 0 && *s) { if (*s & 0x80) { size = utf8_to_utf32(s, inlen, &u); if (size < 0) return -EINVAL; s += size; inlen -= size; if (u >= PLANE_SIZE) { if (maxout < 2) break; u -= PLANE_SIZE; put_utf16(op++, SURROGATE_PAIR | ((u >> 10) & SURROGATE_BITS), endian); put_utf16(op++, SURROGATE_PAIR | SURROGATE_LOW | (u & SURROGATE_BITS), endian); maxout -= 2; } else { put_utf16(op++, u, endian); maxout--; } } else { put_utf16(op++, *s++, endian); inlen--; maxout--; } } return op - pwcs; } EXPORT_SYMBOL(utf8s_to_utf16s); static inline unsigned long get_utf16(unsigned c, enum utf16_endian endian) { switch (endian) { default: return c; case UTF16_LITTLE_ENDIAN: return __le16_to_cpu(c); case UTF16_BIG_ENDIAN: return __be16_to_cpu(c); } } int utf16s_to_utf8s(const wchar_t *pwcs, int inlen, enum utf16_endian endian, u8 *s, int maxout) { u8 *op; int size; unsigned long u, v; op = s; while (inlen > 0 && maxout > 0) { u = get_utf16(*pwcs, endian); if (!u) break; pwcs++; inlen--; if (u > 0x7f) { if ((u & SURROGATE_MASK) == SURROGATE_PAIR) { if (u & SURROGATE_LOW) { /* Ignore character and move on */ continue; } if (inlen <= 0) break; v = get_utf16(*pwcs, endian); if ((v & SURROGATE_MASK) != SURROGATE_PAIR || !(v & SURROGATE_LOW)) { /* Ignore character and move on */ continue; } u = PLANE_SIZE + ((u & SURROGATE_BITS) << 10) + (v & SURROGATE_BITS); pwcs++; inlen--; } size = utf32_to_utf8(u, op, maxout); if (size < 0) { if (size == -EILSEQ) { /* Ignore character and move on */ continue; } /* * Stop filling the buffer with data once a character * does not fit anymore. */ break; } else { op += size; maxout -= size; } } else { *op++ = (u8) u; maxout--; } } return op - s; } EXPORT_SYMBOL(utf16s_to_utf8s); int __register_nls(struct nls_table *nls, struct module *owner) { struct nls_table ** tmp = &tables; if (nls->next) return -EBUSY; nls->owner = owner; spin_lock(&nls_lock); while (*tmp) { if (nls == *tmp) { spin_unlock(&nls_lock); return -EBUSY; } tmp = &(*tmp)->next; } nls->next = tables; tables = nls; spin_unlock(&nls_lock); return 0; } EXPORT_SYMBOL(__register_nls); int unregister_nls(struct nls_table * nls) { struct nls_table ** tmp = &tables; spin_lock(&nls_lock); while (*tmp) { if (nls == *tmp) { *tmp = nls->next; spin_unlock(&nls_lock); return 0; } tmp = &(*tmp)->next; } spin_unlock(&nls_lock); return -EINVAL; } static struct nls_table *find_nls(const char *charset) { struct nls_table *nls; spin_lock(&nls_lock); for (nls = tables; nls; nls = nls->next) { if (!strcmp(nls->charset, charset)) break; if (nls->alias && !strcmp(nls->alias, charset)) break; } if (nls && !try_module_get(nls->owner)) nls = NULL; spin_unlock(&nls_lock); return nls; } struct nls_table *load_nls(const char *charset) { return try_then_request_module(find_nls(charset), "nls_%s", charset); } void unload_nls(struct nls_table *nls) { if (nls) module_put(nls->owner); } static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, /* 0x90*/ 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, /* 0xa0*/ 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, /* 0xb0*/ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, /* 0xc0*/ 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, /* 0xd0*/ 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, /* 0xe0*/ 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, /* 0xf0*/ 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00 }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table default_table = { .charset = "default", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; /* Returns a simple default translation table */ struct nls_table *load_nls_default(void) { struct nls_table *default_nls; default_nls = load_nls(CONFIG_NLS_DEFAULT); if (default_nls != NULL) return default_nls; else return &default_table; } EXPORT_SYMBOL(unregister_nls); EXPORT_SYMBOL(unload_nls); EXPORT_SYMBOL(load_nls); EXPORT_SYMBOL(load_nls_default); MODULE_LICENSE("Dual BSD/GPL"); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_vm_get_page_prot #define arch_vm_get_page_prot(vm_flags) __pgprot(0) #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); #endif /* _LINUX_MMAN_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/internal.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <linux/hardirq.h> #include <linux/pkeys.h> #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ union fpregs_state init_fpstate __read_mostly; /* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? */ bool irq_fpu_usable(void) { if (WARN_ON_ONCE(in_nmi())) return false; /* In kernel FPU usage already active? */ if (this_cpu_read(in_kernel_fpu)) return false; /* * When not in NMI or hard interrupt context, FPU can be used in: * * - Task context except from within fpregs_lock()'ed critical * regions. * * - Soft interrupt processing context which cannot happen * while in a fpregs_lock()'ed critical region. */ if (!in_irq()) return true; /* * In hard interrupt context it's safe when soft interrupts * are enabled, which means the interrupt did not hit in * a fpregs_lock()'ed critical region. */ return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact and we can * keep registers active. * * The legacy FNSAVE instruction cleared all FPU state * unconditionally, so registers are essentially destroyed. * Modern FPU state can be kept in registers, if there are * no pending FP exceptions. */ int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); /* * AVX512 state is tracked here because its use is * known to slow the max clock speed of the core. */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; return 1; } if (likely(use_fxsr())) { copy_fxregs_to_kernel(fpu); return 1; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to mark them inactive: */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); return 0; } EXPORT_SYMBOL(copy_fpregs_to_fpstate); void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); WARN_ON_FPU(!irq_fpu_usable()); WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, true); if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); /* * Ignore return value -- we don't care if reg state * is clobbered. */ copy_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, false); preempt_enable(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Save the FPU state (mark it for reload if necessary): * * This only ever gets called for the current task. */ void fpu__save(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } } trace_x86_fpu_after_save(fpu); fpregs_unlock(); } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fregs_state *fp) { fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; fp->fos = 0xffff0000u; } void fpstate_init(union fpregs_state *state) { if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, fpu_kernel_xstate_size); if (static_cpu_has(X86_FEATURE_XSAVES)) fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); } EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct task_struct *dst, struct task_struct *src) { struct fpu *dst_fpu = &dst->thread.fpu; struct fpu *src_fpu = &src->thread.fpu; dst_fpu->last_cpu = -1; if (!static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); /* * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: */ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* * If the FPU registers are not current just memcpy() the state. * Otherwise save current FPU registers directly into the child's FPU * context, without any memory-to-memory copying. * * ( The function 'fails' in the FNSAVE case, which destroys * register contents so we have to load them back. ) */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); else if (!copy_fpregs_to_fpstate(dst_fpu)) copy_kernel_to_fpregs(&dst_fpu->state); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * Activate the current task's in-memory FPU context, * if it has not been used before: */ static void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); set_thread_flag(TIF_NEED_FPU_LOAD); fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); } /* * This function must be called before we read a task's fpstate. * * There's two cases where this gets called: * * - for the current task (when coredumping), in which case we have * to save the latest FPU registers into the fpstate, * * - or it's called for stopped tasks (ptrace), in which case the * registers were already saved by the context-switch code when * the task scheduled out. * * If the task has used the FPU before then save it. */ void fpu__prepare_read(struct fpu *fpu) { if (fpu == ¤t->thread.fpu) fpu__save(fpu); } /* * This function must be called before we write a task's fpstate. * * Invalidate any cached FPU registers. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU * state in the fpstate buffer: */ WARN_ON_FPU(fpu == ¤t->thread.fpu); /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct fpu *fpu) { preempt_disable(); if (fpu == ¤t->thread.fpu) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); } /* * Clear the FPU state back to init state. * * Called by sys_execve(), by the signal handler code and by various * error paths. */ static void fpu__clear(struct fpu *fpu, bool user_only) { WARN_ON_FPU(fpu != ¤t->thread.fpu); if (!static_cpu_has(X86_FEATURE_FPU)) { fpu__drop(fpu); fpu__initialize(fpu); return; } fpregs_lock(); if (user_only) { if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) copy_kernel_to_xregs(&fpu->state.xsave, xfeatures_mask_supervisor()); copy_init_fpstate_to_fpregs(xfeatures_mask_user()); } else { copy_init_fpstate_to_fpregs(xfeatures_mask_all); } fpregs_mark_activate(); fpregs_unlock(); } void fpu__clear_user_states(struct fpu *fpu) { fpu__clear(fpu, true); } void fpu__clear_all(struct fpu *fpu) { fpu__clear(fpu, false); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; __fpregs_load_activate(); } EXPORT_SYMBOL_GPL(switch_fpu_return); #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = ¤t->thread.fpu; if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = ¤t->thread.fpu; fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } EXPORT_SYMBOL_GPL(fpregs_mark_activate); /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->state.fxsave.cwd; swd = fpu->state.fxsave.swd; } else { cwd = (unsigned short)fpu->state.fsave.cwd; swd = (unsigned short)fpu->state.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->state.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item, bool replace) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * __radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item, false); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Operations on the network namespace */ #ifndef __NET_NET_NAMESPACE_H #define __NET_NET_NAMESPACE_H #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/sysctl.h> #include <linux/uidgid.h> #include <net/flow.h> #include <net/netns/core.h> #include <net/netns/mib.h> #include <net/netns/unix.h> #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> #include <net/netns/nexthop.h> #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/dccp.h> #include <net/netns/netfilter.h> #include <net/netns/x_tables.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> #include <net/netns/bpf.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> #include <linux/notifier.h> struct user_namespace; struct proc_dir_entry; struct net_device; struct sock; struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; struct bpf_prog; #define NETDEV_HASHBITS 8 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { /* First cache line can be often dirtied. * Do not place here read-mostly fields. */ refcount_t passive; /* To decide when the network * namespace should be freed. */ refcount_t count; /* To decided when the network * namespace should be shut down. */ spinlock_t rules_mod_lock; unsigned int dev_unreg_count; unsigned int dev_base_seq; /* protected by rtnl_mutex */ int ifindex; spinlock_t nsid_lock; atomic_t fnhe_genid; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit * methods on dead net ( * pernet_ops_rwsem read locked), * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS struct key_tag *key_domain; /* Key domain of operation tag */ #endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; struct idr netns_ids; struct ns_common ns; struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; #ifdef CONFIG_SYSCTL struct ctl_table_set sysctls; #endif struct sock *rtnl; /* rtnetlink socket */ struct sock *genl_sock; struct uevent_sock *uevent_sock; /* uevent socket */ struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; struct raw_notifier_head netdev_chain; /* Note that @hash_mix can be read millions times per second, * it is critical that it is on a read_mostly cache line. */ u32 hash_mix; struct net_device *loopback_dev; /* The loopback */ /* core fib_rules */ struct list_head rules_ops; struct netns_core core; struct netns_mib mib; struct netns_packet packet; struct netns_unix unx; struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct netns_ieee802154_lowpan ieee802154_lowpan; #endif #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) struct netns_sctp sctp; #endif #if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) struct netns_dccp dccp; #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; struct netns_xt xt; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif #if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE) struct netns_nftables nft; #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag nf_frag; struct ctl_table_header *nf_frag_frags_hdr; #endif struct sock *nfnl; struct sock *nfnl_stash; #if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT) struct list_head nfnl_acct_list; #endif #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) struct list_head nfct_timeout_list; #endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; #endif struct net_generic __rcu *gen; /* Used to store attached BPF programs */ struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif atomic64_t net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif #if IS_ENABLED(CONFIG_MPLS) struct netns_mpls mpls; #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; #endif #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; } __randomize_layout; #include <linux/seq_file_net.h> /* Init's network namespace */ extern struct net init_net; #ifdef CONFIG_NET_NS struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> static inline struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { if (flags & CLONE_NEWNET) return ERR_PTR(-EINVAL); return old_net; } static inline void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } static inline void net_ns_barrier(void) {} static inline struct ns_common *get_net_ns(struct ns_common *ns) { return ERR_PTR(-EINVAL); } #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int fd); u64 __net_gen_cookie(struct net *net); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); #else #define ipx_register_sysctl() #define ipx_unregister_sysctl() #endif #ifdef CONFIG_NET_NS void __put_net(struct net *net); static inline struct net *get_net(struct net *net) { refcount_inc(&net->count); return net; } static inline struct net *maybe_get_net(struct net *net) { /* Used when we know struct net exists but we * aren't guaranteed a previous reference count * exists. If the reference count is zero this * function fails and returns NULL. */ if (!refcount_inc_not_zero(&net->count)) net = NULL; return net; } static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->count)) __put_net(net); } static inline int net_eq(const struct net *net1, const struct net *net2) { return net1 == net2; } static inline int check_net(const struct net *net) { return refcount_read(&net->count) != 0; } void net_drop_ns(void *); #else static inline struct net *get_net(struct net *net) { return net; } static inline void put_net(struct net *net) { } static inline struct net *maybe_get_net(struct net *net) { return net; } static inline int net_eq(const struct net *net1, const struct net *net2) { return 1; } static inline int check_net(const struct net *net) { return 1; } #define net_drop_ns NULL #endif typedef struct { #ifdef CONFIG_NET_NS struct net __rcu *net; #endif } possible_net_t; static inline void write_pnet(possible_net_t *pnet, struct net *net) { #ifdef CONFIG_NET_NS rcu_assign_pointer(pnet->net, net); #endif } static inline struct net *read_pnet(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference_protected(pnet->net, true); #else return &init_net; #endif } static inline struct net *read_pnet_rcu(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); #else return &init_net; #endif } /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) #define for_each_net_continue_reverse(VAR) \ list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) #ifdef CONFIG_NET_NS #define __net_init #define __net_exit #define __net_initdata #define __net_initconst #else #define __net_init __init #define __net_exit __ref #define __net_initdata __initdata #define __net_initconst __initconst #endif int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); int peernet2id(const struct net *net, struct net *peer); bool peernet_has_id(const struct net *net, struct net *peer); struct net *get_net_ns_by_id(const struct net *net, int id); struct pernet_operations { struct list_head list; /* * Below methods are called without any exclusive locks. * More than one net may be constructed and destructed * in parallel on several cpus. Every pernet_operations * have to keep in mind all other pernet_operations and * to introduce a locking, if they share common resources. * * The only time they are called with exclusive lock is * from register_pernet_subsys(), unregister_pernet_subsys() * register_pernet_device() and unregister_pernet_device(). * * Exit methods using blocking RCU primitives, such as * synchronize_rcu(), should be implemented via exit_batch. * Then, destruction of a group of net requires single * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. * * Note that a combination of pre_exit() and exit() can * be used, since a synchronize_rcu() is guaranteed between * the calls. */ int (*init)(struct net *net); void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); /* Following method is called with RTNL held. */ void (*exit_batch_rtnl)(struct list_head *net_exit_list, struct list_head *dev_kill_list); unsigned int *id; size_t size; }; /* * Use these carefully. If you implement a network device and it * needs per network namespace operations use device pernet operations, * otherwise use pernet subsys operations. * * Network interfaces need to be removed from a dying netns _before_ * subsys notifiers can be called, as most of the network code cleanup * (which is done from subsys notifiers) runs with the assumption that * dev_remove_pack has been called so no new packets will arrive during * and after the cleanup functions have been called. dev_remove_pack * is not per namespace so instead the guarantee of no more packets * arriving in a network namespace is provided by ensuring that all * network devices and all sockets have left the network namespace * before the cleanup methods are called. * * For the longest time the ipv4 icmp code was registered as a pernet * device which caused kernel oops, and panics during network * namespace cleanup. So please don't get this wrong. */ int register_pernet_subsys(struct pernet_operations *); void unregister_pernet_subsys(struct pernet_operations *); int register_pernet_device(struct pernet_operations *); void unregister_pernet_device(struct pernet_operations *); struct ctl_table; struct ctl_table_header; #ifdef CONFIG_SYSCTL int net_sysctl_init(void); struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table); void unregister_net_sysctl_table(struct ctl_table_header *header); #else static inline int net_sysctl_init(void) { return 0; } static inline struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { return NULL; } static inline void unregister_net_sysctl_table(struct ctl_table_header *header) { } #endif static inline int rt_genid_ipv4(const struct net *net) { return atomic_read(&net->ipv4.rt_genid); } #if IS_ENABLED(CONFIG_IPV6) static inline int rt_genid_ipv6(const struct net *net) { return atomic_read(&net->ipv6.fib6_sernum); } #endif static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); } extern void (*__fib6_flush_trees)(struct net *net); static inline void rt_genid_bump_ipv6(struct net *net) { if (__fib6_flush_trees) __fib6_flush_trees(net); } #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) static inline struct netns_ieee802154_lowpan * net_ieee802154_lowpan(struct net *net) { return &net->ieee802154_lowpan; } #endif /* For callers who don't really care about whether it's IPv4 or IPv6 */ static inline void rt_genid_bump_all(struct net *net) { rt_genid_bump_ipv4(net); rt_genid_bump_ipv6(net); } static inline int fnhe_genid(const struct net *net) { return atomic_read(&net->fnhe_genid); } static inline void fnhe_genid_bump(struct net *net) { atomic_inc(&net->fnhe_genid); } #endif /* __NET_NET_NAMESPACE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_VSYSCALL_H #define _ASM_X86_VSYSCALL_H #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> #include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); extern void set_vsyscall_pgtable_user_bits(pgd_t *root); /* * Called on instruction fetch fault in vsyscall page. * Returns true if handled. */ extern bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address); #else static inline void map_vsyscall(void) {} static inline bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { return false; } #endif /* * The (legacy) vsyscall page is the long page in the kernel portion * of the address space that has user-accessible permissions. */ static inline bool is_vsyscall_vaddr(unsigned long vaddr) { return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); } #endif /* _ASM_X86_VSYSCALL_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/workqueue.h> #include <linux/rtnetlink.h> #include <linux/cache.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/idr.h> #include <linux/rculist.h> #include <linux/nsproxy.h> #include <linux/fs.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> #include <linux/cookie.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* * Our network namespace constructor/destructor lists */ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); /* Protects net_namespace_list. Nests iside rtnl_lock() */ DECLARE_RWSEM(net_rwsem); EXPORT_SYMBOL_GPL(net_rwsem); #ifdef CONFIG_KEYS static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif struct net init_net = { .count = REFCOUNT_INIT(1), .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), #ifdef CONFIG_KEYS .key_domain = &init_net_key_domain, #endif }; EXPORT_SYMBOL(init_net); static bool init_net_initialized; /* * pernet_ops_rwsem: protects: pernet_list, net_generic_ids, * init_net_initialized and first_device pointer. * This is internal net namespace object. Please, don't use it * outside. */ DECLARE_RWSEM(pernet_ops_rwsem); EXPORT_SYMBOL_GPL(pernet_ops_rwsem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; DEFINE_COOKIE(net_cookie); u64 __net_gen_cookie(struct net *net) { while (1) { u64 res = atomic64_read(&net->net_cookie); if (res) return res; res = gen_cookie_next(&net_cookie); atomic64_cmpxchg(&net->net_cookie, 0, res); } } static struct net_generic *net_alloc_generic(void) { unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); unsigned int generic_size; struct net_generic *ng; generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) ng->s.len = gen_ptrs; return ng; } static int net_assign_generic(struct net *net, unsigned int id, void *data) { struct net_generic *ng, *old_ng; BUG_ON(id < MIN_PERNET_OPS_ID); old_ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); if (old_ng->s.len > id) { old_ng->ptr[id] = data; return 0; } ng = net_alloc_generic(); if (!ng) return -ENOMEM; /* * Some synchronisation notes: * * The net_generic explores the net->gen array inside rcu * read section. Besides once set the net->gen->ptr[x] * pointer never changes (see rules in netns/generic.h). * * That said, we simply duplicate this array and schedule * the old copy for kfree after a grace period. */ memcpy(&ng->ptr[MIN_PERNET_OPS_ID], &old_ng->ptr[MIN_PERNET_OPS_ID], (old_ng->s.len - MIN_PERNET_OPS_ID) * sizeof(void *)); ng->ptr[id] = data; rcu_assign_pointer(net->gen, ng); kfree_rcu(old_ng, s.rcu); return 0; } static int ops_init(const struct pernet_operations *ops, struct net *net) { struct net_generic *ng; int err = -ENOMEM; void *data = NULL; if (ops->id && ops->size) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; err = net_assign_generic(net, *ops->id, data); if (err) goto cleanup; } err = 0; if (ops->init) err = ops->init(net); if (!err) return 0; if (ops->id && ops->size) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; } cleanup: kfree(data); out: return err; } static void ops_pre_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->pre_exit) { list_for_each_entry(net, net_exit_list, exit_list) ops->pre_exit(net); } } static void ops_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->exit) { list_for_each_entry(net, net_exit_list, exit_list) { ops->exit(net); cond_resched(); } } if (ops->exit_batch) ops->exit_batch(net_exit_list); } static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->size && ops->id) { list_for_each_entry(net, net_exit_list, exit_list) kfree(net_generic(net, *ops->id)); } } /* should be called with nsid_lock held */ static int alloc_netid(struct net *net, struct net *peer, int reqid) { int min = 0, max = 0; if (reqid >= 0) { min = reqid; max = reqid + 1; } return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC); } /* This function is used by idr_for_each(). If net is equal to peer, the * function returns the id so that idr_for_each() stops. Because we cannot * returns the id 0 (idr_for_each() will not stop), we return the magic value * NET_ID_ZERO (-1) for it. */ #define NET_ID_ZERO -1 static int net_eq_idr(int id, void *net, void *peer) { if (net_eq(net, peer)) return id ? : NET_ID_ZERO; return 0; } /* Must be called from RCU-critical section or with nsid_lock held */ static int __peernet2id(const struct net *net, struct net *peer) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); /* Magic value for id 0. */ if (id == NET_ID_ZERO) return 0; if (id > 0) return id; return NETNSA_NSID_NOT_ASSIGNED; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { int id; if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED; spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { spin_unlock_bh(&net->nsid_lock); return id; } /* When peer is obtained from RCU lists, we may race with * its cleanup. Check whether it's alive, and this guarantees * we never hash a peer back to net->netns_ids, after it has * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); spin_unlock_bh(&net->nsid_lock); put_net(peer); if (id < 0) return NETNSA_NSID_NOT_ASSIGNED; rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(const struct net *net, struct net *peer) { int id; rcu_read_lock(); id = __peernet2id(net, peer); rcu_read_unlock(); return id; } EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. */ bool peernet_has_id(const struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } struct net *get_net_ns_by_id(const struct net *net, int id) { struct net *peer; if (id < 0) return NULL; rcu_read_lock(); peer = idr_find(&net->netns_ids, id); if (peer) peer = maybe_get_net(peer); rcu_read_unlock(); return peer; } /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); int error = 0; refcount_set(&net->count, 1); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); spin_lock_init(&net->nsid_lock); mutex_init(&net->ipv4.ra_mutex); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); if (error < 0) goto out_undo; } down_write(&net_rwsem); list_add_tail_rcu(&net->list, &net_namespace_list); up_write(&net_rwsem); out: return error; out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ list_add(&net->exit_list, &net_exit_list); saved_ops = ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops = saved_ops; rtnl_lock(); list_for_each_entry_continue_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; } static int __net_init net_defaults_init_net(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; return 0; } static struct pernet_operations net_defaults_ops = { .init = net_defaults_init_net, }; static __init int net_defaults_init(void) { if (register_pernet_subsys(&net_defaults_ops)) panic("Cannot initialize net default settings"); return 0; } core_initcall(net_defaults_init); #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_NET_NAMESPACES); } static void dec_net_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); } static struct kmem_cache *net_cachep __ro_after_init; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) { struct net *net = NULL; struct net_generic *ng; ng = net_alloc_generic(); if (!ng) goto out; net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); if (!net) goto out_free; #ifdef CONFIG_KEYS net->key_domain = kzalloc(sizeof(struct key_tag), GFP_KERNEL); if (!net->key_domain) goto out_free_2; refcount_set(&net->key_domain->usage, 1); #endif rcu_assign_pointer(net->gen, ng); out: return net; #ifdef CONFIG_KEYS out_free_2: kmem_cache_free(net_cachep, net); net = NULL; #endif out_free: kfree(ng); goto out; } static LLIST_HEAD(defer_free_list); static void net_complete_free(void) { struct llist_node *kill_list; struct net *net, *next; /* Get the list of namespaces to free from last round. */ kill_list = llist_del_all(&defer_free_list); llist_for_each_entry_safe(net, next, kill_list, defer_free_list) kmem_cache_free(net_cachep, net); } static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); /* Wait for an extra rcu_barrier() before final free. */ llist_add(&net->defer_free_list, &defer_free_list); } } void net_drop_ns(void *p) { struct net *net = (struct net *)p; if (net) net_free(net); } struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { struct ucounts *ucounts; struct net *net; int rv; if (!(flags & CLONE_NEWNET)) return get_net(old_net); ucounts = inc_net_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); net = net_alloc(); if (!net) { rv = -ENOMEM; goto dec_ucounts; } refcount_set(&net->passive, 1); net->ucounts = ucounts; get_user_ns(user_ns); rv = down_read_killable(&pernet_ops_rwsem); if (rv < 0) goto put_userns; rv = setup_net(net, user_ns); up_read(&pernet_ops_rwsem); if (rv < 0) { put_userns: #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); net_free(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); } return net; } /** * net_ns_get_ownership - get sysfs ownership data for @net * @net: network namespace in question (can be NULL) * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns the uid/gid pair of root in the user namespace associated with the * given network namespace. */ void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { if (net) { kuid_t ns_root_uid = make_kuid(net->user_ns, 0); kgid_t ns_root_gid = make_kgid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } else { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } } EXPORT_SYMBOL_GPL(net_ns_get_ownership); static void unhash_nsid(struct net *net, struct net *last) { struct net *tmp; /* This function is only called from cleanup_net() work, * and this work is the only process, that may delete * a net from net_namespace_list. So, when the below * is executing, the list may only grow. Thus, we do not * use for_each_net_rcu() or net_rwsem. */ for_each_net(tmp) { int id; spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); spin_unlock_bh(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp, *last; struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); down_read(&pernet_ops_rwsem); /* Don't let anyone else find us. */ down_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) list_del_rcu(&net->list); /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer * to a net from net_kill_list (see peernet2id_alloc()). * So, we skip them in unhash_nsid(). * * Note, that unhash_nsid() does not delete nsid links * between net_kill_list's nets, as they've already * deleted from net_namespace_list. But, this would be * useless anyway, as netns_ids are destroyed there. */ last = list_last_entry(&net_namespace_list, struct net, list); up_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) { unhash_nsid(net, last); list_add_tail(&net->exit_list, &net_exit_list); } /* Run all of the network namespace pre_exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); /* * Another CPU might be rcu-iterating the list, wait for it. * This needs to be before calling the exit() notifiers, so * the rcu_barrier() below isn't sufficient alone. * Also the pre_exit() and exit() methods need this barrier. */ synchronize_rcu(); rtnl_lock(); list_for_each_entry_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); /* Free the net generic variables */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); up_read(&pernet_ops_rwsem); /* Ensure there are no outstanding rcu callbacks using this * network namespace. */ rcu_barrier(); net_complete_free(); /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); dec_net_namespaces(net->ucounts); #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); net_free(net); } } /** * net_ns_barrier - wait until concurrent net_cleanup_work is done * * cleanup_net runs from work queue and will first remove namespaces * from the global list, then run net exit functions. * * Call this in module exit path to make sure that all netns * ->exit ops have been invoked before the function is removed. */ void net_ns_barrier(void) { down_write(&pernet_ops_rwsem); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL(net_ns_barrier); static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ if (llist_add(&net->cleanup_list, &cleanup_list)) queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); /** * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { struct net *net; net = maybe_get_net(container_of(ns, struct net, ns)); if (net) return &net->ns; return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); struct net *get_net_ns_by_fd(int fd) { struct file *file; struct ns_common *ns; struct net *net; file = proc_ns_fget(fd); if (IS_ERR(file)) return ERR_CAST(file); ns = get_proc_ns(file_inode(file)); if (ns->ops == &netns_operations) net = get_net(container_of(ns, struct net, ns)); else net = ERR_PTR(-EINVAL); fput(file); return net; } #else struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); } #endif EXPORT_SYMBOL_GPL(get_net_ns_by_fd); struct net *get_net_ns_by_pid(pid_t pid) { struct task_struct *tsk; struct net *net; /* Lookup the network namespace */ net = ERR_PTR(-ESRCH); rcu_read_lock(); tsk = find_task_by_vpid(pid); if (tsk) { struct nsproxy *nsproxy; task_lock(tsk); nsproxy = tsk->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(tsk); } rcu_read_unlock(); return net; } EXPORT_SYMBOL_GPL(get_net_ns_by_pid); static __net_init int net_ns_net_init(struct net *net) { #ifdef CONFIG_NET_NS net->ns.ops = &netns_operations; #endif return ns_alloc_inum(&net->ns); } static __net_exit void net_ns_net_exit(struct net *net) { ns_free_inum(&net->ns); } static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, .exit = net_ns_net_exit, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { [NETNSA_NONE] = { .type = NLA_UNSPEC }, [NETNSA_NSID] = { .type = NLA_S32 }, [NETNSA_PID] = { .type = NLA_U32 }, [NETNSA_FD] = { .type = NLA_U32 }, [NETNSA_TARGET_NSID] = { .type = NLA_S32 }, }; static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct nlattr *nla; struct net *peer; int nsid, err; err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; if (!tb[NETNSA_NSID]) { NL_SET_ERR_MSG(extack, "nsid is missing"); return -EINVAL; } nsid = nla_get_s32(tb[NETNSA_NSID]); if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns already has a nsid assigned"); goto out; } err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]); NL_SET_ERR_MSG(extack, "The specified nsid is already used"); } out: put_net(peer); return err; } static int rtnl_net_get_size(void) { return NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(sizeof(s32)) /* NETNSA_NSID */ + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */ ; } struct net_fill_args { u32 portid; u32 seq; int flags; int cmd; int nsid; bool add_ref; int ref_nsid; }; static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args) { struct nlmsghdr *nlh; struct rtgenmsg *rth; nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth), args->flags); if (!nlh) return -EMSGSIZE; rth = nlmsg_data(nlh); rth->rtgen_family = AF_UNSPEC; if (nla_put_s32(skb, NETNSA_NSID, args->nsid)) goto nla_put_failure; if (args->add_ref && nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int rtnl_net_valid_getid_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETNSA_PID: case NETNSA_FD: case NETNSA_NSID: case NETNSA_TARGET_NSID: break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request"); return -EINVAL; } } return 0; } static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct net_fill_args fillargs = { .portid = NETLINK_CB(skb).portid, .seq = nlh->nlmsg_seq, .cmd = RTM_NEWNSID, }; struct net *peer, *target = net; struct nlattr *nla; struct sk_buff *msg; int err; err = rtnl_net_valid_getid_req(skb, nlh, tb, extack); if (err < 0) return err; if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else if (tb[NETNSA_NSID]) { peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID])); if (!peer) peer = ERR_PTR(-ENOENT); nla = tb[NETNSA_NSID]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } if (tb[NETNSA_TARGET_NSID]) { int id = nla_get_s32(tb[NETNSA_TARGET_NSID]); target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id); if (IS_ERR(target)) { NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]); NL_SET_ERR_MSG(extack, "Target netns reference is invalid"); err = PTR_ERR(target); goto out; } fillargs.add_ref = true; fillargs.ref_nsid = peernet2id(net, peer); } msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); if (!msg) { err = -ENOMEM; goto out; } fillargs.nsid = peernet2id(target, peer); err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid); goto out; err_out: nlmsg_free(msg); out: if (fillargs.add_ref) put_net(target); put_net(peer); return err; } struct rtnl_net_dump_cb { struct net *tgt_net; struct net *ref_net; struct sk_buff *skb; struct net_fill_args fillargs; int idx; int s_idx; }; /* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; int ret; if (net_cb->idx < net_cb->s_idx) goto cont; net_cb->fillargs.nsid = id; if (net_cb->fillargs.add_ref) net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer); ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs); if (ret < 0) return ret; cont: net_cb->idx++; return 0; } static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk, struct rtnl_net_dump_cb *net_cb, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NETNSA_MAX + 1]; int err, i; err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; if (i == NETNSA_TARGET_NSID) { struct net *net; net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i])); if (IS_ERR(net)) { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Invalid target network namespace id"); return PTR_ERR(net); } net_cb->fillargs.add_ref = true; net_cb->ref_net = net_cb->tgt_net; net_cb->tgt_net = net; } else { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) { struct rtnl_net_dump_cb net_cb = { .tgt_net = sock_net(skb->sk), .skb = skb, .fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = cb->nlh->nlmsg_seq, .flags = NLM_F_MULTI, .cmd = RTM_NEWNSID, }, .idx = 0, .s_idx = cb->args[0], }; int err = 0; if (cb->strict_check) { err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb); if (err < 0) goto end; } rcu_read_lock(); idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); rcu_read_unlock(); cb->args[0] = net_cb.idx; end: if (net_cb.fillargs.add_ref) put_net(net_cb.tgt_net); return err < 0 ? err : skb->len; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp) { struct net_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; struct sk_buff *msg; int err = -ENOMEM; msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); return; err_out: nlmsg_free(msg); out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } static int __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Create workqueue for cleanup */ netns_wq = create_singlethread_workqueue("netns"); if (!netns_wq) panic("Could not create netns workq"); #endif ng = net_alloc_generic(); if (!ng) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); preempt_disable(); __net_gen_cookie(&init_net); preempt_enable(); down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); init_net_initialized = true; up_write(&pernet_ops_rwsem); if (register_pernet_subsys(&net_ns_ops)) panic("Could not register network namespace subsystems"); rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, RTNL_FLAG_DOIT_UNLOCKED); return 0; } pure_initcall(net_ns_init); static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) { ops_pre_exit_list(ops, net_exit_list); synchronize_rcu(); if (ops->exit_batch_rtnl) { LIST_HEAD(dev_kill_list); rtnl_lock(); ops->exit_batch_rtnl(net_exit_list, &dev_kill_list); unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } ops_exit_list(ops, net_exit_list); ops_free_list(ops, net_exit_list); } #ifdef CONFIG_NET_NS static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { struct net *net; int error; LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); if (ops->init || (ops->id && ops->size)) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { error = ops_init(ops, net); if (error) goto out_undo; list_add_tail(&net->exit_list, &net_exit_list); } } return 0; out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); free_exit_list(ops, &net_exit_list); return error; } static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; LIST_HEAD(net_exit_list); list_del(&ops->list); /* See comment in __register_pernet_operations() */ for_each_net(net) list_add_tail(&net->exit_list, &net_exit_list); free_exit_list(ops, &net_exit_list); } #else static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { if (!init_net_initialized) { list_add_tail(&ops->list, list); return 0; } return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) { if (!init_net_initialized) { list_del(&ops->list); } else { LIST_HEAD(net_exit_list); list_add(&init_net.exit_list, &net_exit_list); free_exit_list(ops, &net_exit_list); } } #endif /* CONFIG_NET_NS */ static DEFINE_IDA(net_generic_ids); static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { int error; if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); if (error < 0) return error; *ops->id = error; /* This does not require READ_ONCE as writers already hold * pernet_ops_rwsem. But WRITE_ONCE is needed to protect * net_alloc_generic. */ WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } /** * register_pernet_subsys - register a network namespace subsystem * @ops: pernet operations structure for the subsystem * * Register a subsystem which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_subsys(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(first_device, ops); up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_subsys); /** * unregister_pernet_subsys - unregister a network namespace subsystem * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_subsys(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem * * Register a device which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_device(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(&pernet_list, ops); if (!error && (first_device == &pernet_list)) first_device = &ops->list; up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_device); /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_device(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); if (&ops->list == first_device) first_device = first_device->next; unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_device); #ifdef CONFIG_NET_NS static struct ns_common *netns_get(struct task_struct *task) { struct net *net = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(task); return net ? &net->ns : NULL; } static inline struct net *to_net_ns(struct ns_common *ns) { return container_of(ns, struct net, ns); } static void netns_put(struct ns_common *ns) { put_net(to_net_ns(ns)); } static int netns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct net *net = to_net_ns(ns); if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; put_net(nsproxy->net_ns); nsproxy->net_ns = get_net(net); return 0; } static struct user_namespace *netns_owner(struct ns_common *ns) { return to_net_ns(ns)->user_ns; } const struct proc_ns_operations netns_operations = { .name = "net", .type = CLONE_NEWNET, .get = netns_get, .put = netns_put, .install = netns_install, .owner = netns_owner, }; #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/bad_inode.c * * Copyright (C) 1997, Stephen Tweedie * * Provide stub functions for unreadable inodes * * Fabian Frederick : August 2003 - All file operations assigned to EIO */ #include <linux/fs.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/time.h> #include <linux/namei.h> #include <linux/poll.h> #include <linux/fiemap.h> static int bad_file_open(struct inode *inode, struct file *filp) { return -EIO; } static const struct file_operations bad_file_ops = { .open = bad_file_open, }; static int bad_inode_create (struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return -EIO; } static struct dentry *bad_inode_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-EIO); } static int bad_inode_link (struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_unlink(struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_symlink (struct inode *dir, struct dentry *dentry, const char *symname) { return -EIO; } static int bad_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { return -EIO; } static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_mknod (struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { return -EIO; } static int bad_inode_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { return -EIO; } static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, int buflen) { return -EIO; } static int bad_inode_permission(struct inode *inode, int mask) { return -EIO; } static int bad_inode_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { return -EIO; } static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs) { return -EIO; } static ssize_t bad_inode_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { return -EIO; } static const char *bad_inode_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return ERR_PTR(-EIO); } static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type) { return ERR_PTR(-EIO); } static int bad_inode_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { return -EIO; } static int bad_inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { return -EIO; } static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry, struct file *file, unsigned int open_flag, umode_t create_mode) { return -EIO; } static int bad_inode_tmpfile(struct inode *inode, struct dentry *dentry, umode_t mode) { return -EIO; } static int bad_inode_set_acl(struct inode *inode, struct posix_acl *acl, int type) { return -EIO; } static const struct inode_operations bad_inode_ops = { .create = bad_inode_create, .lookup = bad_inode_lookup, .link = bad_inode_link, .unlink = bad_inode_unlink, .symlink = bad_inode_symlink, .mkdir = bad_inode_mkdir, .rmdir = bad_inode_rmdir, .mknod = bad_inode_mknod, .rename = bad_inode_rename2, .readlink = bad_inode_readlink, .permission = bad_inode_permission, .getattr = bad_inode_getattr, .setattr = bad_inode_setattr, .listxattr = bad_inode_listxattr, .get_link = bad_inode_get_link, .get_acl = bad_inode_get_acl, .fiemap = bad_inode_fiemap, .update_time = bad_inode_update_time, .atomic_open = bad_inode_atomic_open, .tmpfile = bad_inode_tmpfile, .set_acl = bad_inode_set_acl, }; /* * When a filesystem is unable to read an inode due to an I/O error in * its read_inode() function, it can call make_bad_inode() to return a * set of stubs which will return EIO errors as required. * * We only need to do limited initialisation: all other fields are * preinitialised to zero automatically. */ /** * make_bad_inode - mark an inode bad due to an I/O error * @inode: Inode to mark bad * * When an inode cannot be read due to a media or remote network * failure this function makes the inode "bad" and causes I/O operations * on it to fail from this point on. */ void make_bad_inode(struct inode *inode) { remove_inode_hash(inode); inode->i_mode = S_IFREG; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_op = &bad_inode_ops; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &bad_file_ops; } EXPORT_SYMBOL(make_bad_inode); /* * This tests whether an inode has been flagged as bad. The test uses * &bad_inode_ops to cover the case of invalidated inodes as well as * those created by make_bad_inode() above. */ /** * is_bad_inode - is an inode errored * @inode: inode to test * * Returns true if the inode in question has been marked as bad. */ bool is_bad_inode(struct inode *inode) { return (inode->i_op == &bad_inode_ops); } EXPORT_SYMBOL(is_bad_inode); /** * iget_failed - Mark an under-construction inode as dead and release it * @inode: The inode to discard * * Mark an under-construction inode as dead and release it. */ void iget_failed(struct inode *inode) { make_bad_inode(inode); unlock_new_inode(inode); iput(inode); } EXPORT_SYMBOL(iget_failed); |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/spinlock.h> #include <linux/debug_locks.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/irq_work.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* * printk() could not take logbuf_lock in NMI context. Instead, * it uses an alternative implementation that temporary stores * the strings into a per-CPU buffer. The content of the buffer * is later flushed into the main ring buffer via IRQ work. * * The alternative implementation is chosen transparently * by examining current printk() context mask stored in @printk_context * per-CPU variable. * * The implementation allows to flush the strings also from another CPU. * There are situations when we want to make sure that all buffers * were handled or when IRQs are blocked. */ #define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) - \ sizeof(atomic_t) - \ sizeof(atomic_t) - \ sizeof(struct irq_work)) struct printk_safe_seq_buf { atomic_t len; /* length of written data */ atomic_t message_lost; struct irq_work work; /* IRQ work that flushes the buffer */ unsigned char buffer[SAFE_LOG_BUF_LEN]; }; static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq); static DEFINE_PER_CPU(int, printk_context); static DEFINE_RAW_SPINLOCK(safe_read_lock); #ifdef CONFIG_PRINTK_NMI static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq); #endif /* Get flushed in a more safe context. */ static void queue_flush_work(struct printk_safe_seq_buf *s) { if (printk_percpu_data_ready()) irq_work_queue(&s->work); } /* * Add a message to per-CPU context-dependent buffer. NMI and printk-safe * have dedicated buffers, because otherwise printk-safe preempted by * NMI-printk would have overwritten the NMI messages. * * The messages are flushed from irq work (or from panic()), possibly, * from other CPU, concurrently with printk_safe_log_store(). Should this * happen, printk_safe_log_store() will notice the buffer->len mismatch * and repeat the write. */ static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s, const char *fmt, va_list args) { int add; size_t len; va_list ap; again: len = atomic_read(&s->len); /* The trailing '\0' is not counted into len. */ if (len >= sizeof(s->buffer) - 1) { atomic_inc(&s->message_lost); queue_flush_work(s); return 0; } /* * Make sure that all old data have been read before the buffer * was reset. This is not needed when we just append data. */ if (!len) smp_rmb(); va_copy(ap, args); add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap); va_end(ap); if (!add) return 0; /* * Do it once again if the buffer has been flushed in the meantime. * Note that atomic_cmpxchg() is an implicit memory barrier that * makes sure that the data were written before updating s->len. */ if (atomic_cmpxchg(&s->len, len, len + add) != len) goto again; queue_flush_work(s); return add; } static inline void printk_safe_flush_line(const char *text, int len) { /* * Avoid any console drivers calls from here, because we may be * in NMI or printk_safe context (when in panic). The messages * must go only into the ring buffer at this stage. Consoles will * get explicitly called later when a crashdump is not generated. */ printk_deferred("%.*s", len, text); } /* printk part of the temporary buffer line by line */ static int printk_safe_flush_buffer(const char *start, size_t len) { const char *c, *end; bool header; c = start; end = start + len; header = true; /* Print line by line. */ while (c < end) { if (*c == '\n') { printk_safe_flush_line(start, c - start + 1); start = ++c; header = true; continue; } /* Handle continuous lines or missing new line. */ if ((c + 1 < end) && printk_get_level(c)) { if (header) { c = printk_skip_level(c); continue; } printk_safe_flush_line(start, c - start); start = c++; header = true; continue; } header = false; c++; } /* Check if there was a partial line. Ignore pure header. */ if (start < end && !header) { static const char newline[] = KERN_CONT "\n"; printk_safe_flush_line(start, end - start); printk_safe_flush_line(newline, strlen(newline)); } return len; } static void report_message_lost(struct printk_safe_seq_buf *s) { int lost = atomic_xchg(&s->message_lost, 0); if (lost) printk_deferred("Lost %d message(s)!\n", lost); } /* * Flush data from the associated per-CPU buffer. The function * can be called either via IRQ work or independently. */ static void __printk_safe_flush(struct irq_work *work) { struct printk_safe_seq_buf *s = container_of(work, struct printk_safe_seq_buf, work); unsigned long flags; size_t len; int i; /* * The lock has two functions. First, one reader has to flush all * available message to make the lockless synchronization with * writers easier. Second, we do not want to mix messages from * different CPUs. This is especially important when printing * a backtrace. */ raw_spin_lock_irqsave(&safe_read_lock, flags); i = 0; more: len = atomic_read(&s->len); /* * This is just a paranoid check that nobody has manipulated * the buffer an unexpected way. If we printed something then * @len must only increase. Also it should never overflow the * buffer size. */ if ((i && i >= len) || len > sizeof(s->buffer)) { const char *msg = "printk_safe_flush: internal error\n"; printk_safe_flush_line(msg, strlen(msg)); len = 0; } if (!len) goto out; /* Someone else has already flushed the buffer. */ /* Make sure that data has been written up to the @len */ smp_rmb(); i += printk_safe_flush_buffer(s->buffer + i, len - i); /* * Check that nothing has got added in the meantime and truncate * the buffer. Note that atomic_cmpxchg() is an implicit memory * barrier that makes sure that the data were copied before * updating s->len. */ if (atomic_cmpxchg(&s->len, len, 0) != len) goto more; out: report_message_lost(s); raw_spin_unlock_irqrestore(&safe_read_lock, flags); } /** * printk_safe_flush - flush all per-cpu nmi buffers. * * The buffers are flushed automatically via IRQ work. This function * is useful only when someone wants to be sure that all buffers have * been flushed at some point. */ void printk_safe_flush(void) { int cpu; for_each_possible_cpu(cpu) { #ifdef CONFIG_PRINTK_NMI __printk_safe_flush(&per_cpu(nmi_print_seq, cpu).work); #endif __printk_safe_flush(&per_cpu(safe_print_seq, cpu).work); } } /** * printk_safe_flush_on_panic - flush all per-cpu nmi buffers when the system * goes down. * * Similar to printk_safe_flush() but it can be called even in NMI context when * the system goes down. It does the best effort to get NMI messages into * the main ring buffer. * * Note that it could try harder when there is only one CPU online. */ void printk_safe_flush_on_panic(void) { /* * Make sure that we could access the main ring buffer. * Do not risk a double release when more CPUs are up. */ if (raw_spin_is_locked(&logbuf_lock)) { if (num_online_cpus() > 1) return; debug_locks_off(); raw_spin_lock_init(&logbuf_lock); } if (raw_spin_is_locked(&safe_read_lock)) { if (num_online_cpus() > 1) return; debug_locks_off(); raw_spin_lock_init(&safe_read_lock); } printk_safe_flush(); } #ifdef CONFIG_PRINTK_NMI /* * Safe printk() for NMI context. It uses a per-CPU buffer to * store the message. NMIs are not nested, so there is always only * one writer running. But the buffer might get flushed from another * CPU, so we need to be careful. */ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) { struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq); return printk_safe_log_store(s, fmt, args); } void noinstr printk_nmi_enter(void) { this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET); } void noinstr printk_nmi_exit(void) { this_cpu_sub(printk_context, PRINTK_NMI_CONTEXT_OFFSET); } /* * Marks a code that might produce many messages in NMI context * and the risk of losing them is more critical than eventual * reordering. * * It has effect only when called in NMI context. Then printk() * will try to store the messages into the main logbuf directly * and use the per-CPU buffers only as a fallback when the lock * is not available. */ void printk_nmi_direct_enter(void) { if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK); } void printk_nmi_direct_exit(void) { this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK); } #else static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) { return 0; } #endif /* CONFIG_PRINTK_NMI */ /* * Lock-less printk(), to avoid deadlocks should the printk() recurse * into itself. It uses a per-CPU buffer to store the message, just like * NMI. */ static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args) { struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq); return printk_safe_log_store(s, fmt, args); } /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif /* * Try to use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK) && raw_spin_trylock(&logbuf_lock)) { int len; len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); raw_spin_unlock(&logbuf_lock); defer_console_output(); return len; } /* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */ if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) return vprintk_nmi(fmt, args); /* Use extra buffer to prevent a recursion deadlock in safe mode. */ if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) return vprintk_safe(fmt, args); /* No obstacles. */ return vprintk_default(fmt, args); } void __init printk_safe_init(void) { int cpu; for_each_possible_cpu(cpu) { struct printk_safe_seq_buf *s; s = &per_cpu(safe_print_seq, cpu); init_irq_work(&s->work, __printk_safe_flush); #ifdef CONFIG_PRINTK_NMI s = &per_cpu(nmi_print_seq, cpu); init_irq_work(&s->work, __printk_safe_flush); #endif } /* Flush pending messages that did not have scheduled IRQ works. */ printk_safe_flush(); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/inotify_user.c - inotify support for userspace * * Authors: * John McCutchan <ttb@tentacle.dhs.org> * Robert Love <rml@novell.com> * * Copyright (C) 2005 John McCutchan * Copyright 2006 Hewlett-Packard Development Company, L.P. * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * inotify was largely rewriten to make use of the fsnotify infrastructure */ #include <linux/dcache.h> /* d_unlinked */ #include <linux/fs.h> /* struct inode */ #include <linux/fsnotify_backend.h> #include <linux/inotify.h> #include <linux/path.h> /* struct path */ #include <linux/slab.h> /* kmem_* */ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/user.h> #include <linux/sched/mm.h> #include "inotify.h" /* * Check if 2 events contain the same information. */ static bool event_compare(struct fsnotify_event *old_fsn, struct fsnotify_event *new_fsn) { struct inotify_event_info *old, *new; old = INOTIFY_E(old_fsn); new = INOTIFY_E(new_fsn); if (old->mask & FS_IN_IGNORED) return false; if ((old->mask == new->mask) && (old->wd == new->wd) && (old->name_len == new->name_len) && (!old->name_len || !strcmp(old->name, new->name))) return true; return false; } static int inotify_merge(struct fsnotify_group *group, struct fsnotify_event *event) { struct list_head *list = &group->notification_list; struct fsnotify_event *last_event; last_event = list_entry(list->prev, struct fsnotify_event, list); return event_compare(last_event, event); } int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct inotify_inode_mark *i_mark; struct inotify_event_info *event; struct fsnotify_event *fsn_event; struct fsnotify_group *group = inode_mark->group; int ret; int len = 0, wd; int alloc_len = sizeof(struct inotify_event_info); struct mem_cgroup *old_memcg; if (name) { len = name->len; alloc_len += len + 1; } pr_debug("%s: group=%p mark=%p mask=%x\n", __func__, group, inode_mark, mask); i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); /* * We can be racing with mark being detached. Don't report event with * invalid wd. */ wd = READ_ONCE(i_mark->wd); if (wd == -1) return 0; /* * Whoever is interested in the event, pays for the allocation. Do not * trigger OOM killer in the target monitoring memcg as it may have * security repercussion. */ old_memcg = set_active_memcg(group->memcg); event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); set_active_memcg(old_memcg); if (unlikely(!event)) { /* * Treat lost event due to ENOMEM the same way as queue * overflow to let userspace know event was lost. */ fsnotify_queue_overflow(group); return -ENOMEM; } /* * We now report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events * for fanotify. inotify never reported IN_ISDIR with those events. * It looks like an oversight, but to avoid the risk of breaking * existing inotify programs, mask the flag out from those events. */ if (mask & (IN_MOVE_SELF | IN_DELETE_SELF)) mask &= ~IN_ISDIR; fsn_event = &event->fse; fsnotify_init_event(fsn_event); event->mask = mask; event->wd = wd; event->sync_cookie = cookie; event->name_len = len; if (len) strcpy(event->name, name->name); ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); } if (inode_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT) fsnotify_destroy_mark(inode_mark, group); return 0; } static void inotify_freeing_mark(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group) { inotify_ignored_and_remove_idr(fsn_mark, group); } /* * This is NEVER supposed to be called. Inotify marks should either have been * removed from the idr when the watch was removed or in the * fsnotify_destroy_mark_by_group() call when the inotify instance was being * torn down. This is only called if the idr is about to be freed but there * are still marks in it. */ static int idr_callback(int id, void *p, void *data) { struct fsnotify_mark *fsn_mark; struct inotify_inode_mark *i_mark; static bool warned = false; if (warned) return 0; warned = true; fsn_mark = p; i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); WARN(1, "inotify closing but id=%d for fsn_mark=%p in group=%p still in " "idr. Probably leaking memory\n", id, p, data); /* * I'm taking the liberty of assuming that the mark in question is a * valid address and I'm dereferencing it. This might help to figure * out why we got here and the panic is no worse than the original * BUG() that was here. */ if (fsn_mark) printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n", fsn_mark->group, i_mark->wd); return 0; } static void inotify_free_group_priv(struct fsnotify_group *group) { /* ideally the idr is empty and we won't hit the BUG in the callback */ idr_for_each(&group->inotify_data.idr, idr_callback, group); idr_destroy(&group->inotify_data.idr); if (group->inotify_data.ucounts) dec_inotify_instances(group->inotify_data.ucounts); } static void inotify_free_event(struct fsnotify_group *group, struct fsnotify_event *fsn_event) { kfree(INOTIFY_E(fsn_event)); } /* ding dong the mark is dead */ static void inotify_free_mark(struct fsnotify_mark *fsn_mark) { struct inotify_inode_mark *i_mark; i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); kmem_cache_free(inotify_inode_mark_cachep, i_mark); } const struct fsnotify_ops inotify_fsnotify_ops = { .handle_inode_event = inotify_handle_inode_event, .free_group_priv = inotify_free_group_priv, .free_event = inotify_free_event, .freeing_mark = inotify_freeing_mark, .free_mark = inotify_free_mark, }; |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #elif defined(CONFIG_SRCU) #error "Unknown SRCU implementation specified to kernel configuration" #else /* Dummy definition for things like notifiers. Actual use gets link error. */ struct srcu_struct { }; #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * Note that srcu_read_lock() and the matching srcu_read_unlock() must * occur in the same context, for example, it is illegal to invoke * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() * was invoked in process context. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; retval = __srcu_read_lock(ssp); rcu_lock_acquire(&(ssp)->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; retval = __srcu_read_lock(ssp); return retval; } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); rcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), int idx) #endif |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Access vector cache interface for object managers. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SELINUX_AVC_H_ #define _SELINUX_AVC_H_ #include <linux/stddef.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kdev_t.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/audit.h> #include <linux/lsm_audit.h> #include <linux/in6.h> #include "flask.h" #include "av_permissions.h" #include "security.h" /* * An entry in the AVC. */ struct avc_entry; struct task_struct; struct inode; struct sock; struct sk_buff; /* * AVC statistics */ struct avc_cache_stats { unsigned int lookups; unsigned int misses; unsigned int allocations; unsigned int reclaims; unsigned int frees; }; /* * We only need this data after we have decided to send an audit message. */ struct selinux_audit_data { u32 ssid; u32 tsid; u16 tclass; u32 requested; u32 audited; u32 denied; int result; struct selinux_state *state; }; /* * AVC operations */ void __init avc_init(void); static inline u32 avc_audit_required(u32 requested, struct av_decision *avd, int result, u32 auditdeny, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; /* * auditdeny is TRICKY! Setting a bit in * this field means that ANY denials should NOT be audited if * the policy contains an explicit dontaudit rule for that * permission. Take notice that this is unrelated to the * actual permissions that were denied. As an example lets * assume: * * denied == READ * avd.auditdeny & ACCESS == 0 (not set means explicit rule) * auditdeny & ACCESS == 1 * * We will NOT audit the denial even though the denied * permission was READ and the auditdeny checks were for * ACCESS */ if (auditdeny && !(auditdeny & avd->auditdeny)) audited = 0; } else if (result) audited = denied = requested; else audited = requested & avd->auditallow; *deniedp = denied; return audited; } int slow_avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a); /** * avc_audit - Audit the granting or denial of permissions. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions * @avd: access vector decisions * @result: result from avc_has_perm_noaudit * @a: auxiliary audit data * @flags: VFS walk flags * * Audit the granting or denial of permissions in accordance * with the policy. This function is typically called by * avc_has_perm() after a permission check, but can also be * called directly by callers who use avc_has_perm_noaudit() * in order to separate the permission check from the auditing. * For example, this separation is useful when the permission check must * be performed under a lock, to allow the lock to be released * before calling the auditing code. */ static inline int avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, int result, struct common_audit_data *a, int flags) { u32 audited, denied; audited = avc_audit_required(requested, avd, result, 0, &denied); if (likely(!audited)) return 0; /* fall back to ref-walk if we have to generate audit */ if (flags & MAY_NOT_BLOCK) return -ECHILD; return slow_avc_audit(state, ssid, tsid, tclass, requested, audited, denied, result, a); } #define AVC_STRICT 1 /* Ignore permissive mode. */ #define AVC_EXTENDED_PERMS 2 /* update extended permissions */ #define AVC_NONBLOCKING 4 /* non blocking */ int avc_has_perm_noaudit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned flags, struct av_decision *avd); int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); int avc_has_perm_flags(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata, int flags); int avc_has_extended_perms(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 perm, struct common_audit_data *ad); u32 avc_policy_seqno(struct selinux_state *state); #define AVC_CALLBACK_GRANT 1 #define AVC_CALLBACK_TRY_REVOKE 2 #define AVC_CALLBACK_REVOKE 4 #define AVC_CALLBACK_RESET 8 #define AVC_CALLBACK_AUDITALLOW_ENABLE 16 #define AVC_CALLBACK_AUDITALLOW_DISABLE 32 #define AVC_CALLBACK_AUDITDENY_ENABLE 64 #define AVC_CALLBACK_AUDITDENY_DISABLE 128 #define AVC_CALLBACK_ADD_XPERMS 256 int avc_add_callback(int (*callback)(u32 event), u32 events); /* Exported to selinuxfs */ struct selinux_avc; int avc_get_hash_stats(struct selinux_avc *avc, char *page); unsigned int avc_get_cache_threshold(struct selinux_avc *avc); void avc_set_cache_threshold(struct selinux_avc *avc, unsigned int cache_threshold); /* Attempt to free avc node cache */ void avc_disable(void); #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats); #endif #endif /* _SELINUX_AVC_H_ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H #include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> /* * Macro to mark a page protection value as UC- */ #define pgprot_noncached(prot) \ ((boot_cpu_data.x86 > 3) \ ? (__pgprot(pgprot_val(prot) | \ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) /* * Macros to add or remove encryption attribute */ #define pgprot_encrypted(prot) __pgprot(__sme_set(pgprot_val(prot))) #define pgprot_decrypted(prot) __pgprot(__sme_clr(pgprot_val(prot))) #ifndef __ASSEMBLY__ #include <asm/x86_init.h> #include <asm/fpu/xstate.h> #include <asm/fpu/api.h> #include <asm-generic/pgtable_uffd.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); void ptdump_walk_pgd_level_checkwx(void); void ptdump_walk_user_pgd_level_checkwx(void); #ifdef CONFIG_DEBUG_WX #define debug_checkwx() ptdump_walk_pgd_level_checkwx() #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else #define debug_checkwx() do { } while (0) #define debug_checkwx_user() do { } while (0) #endif /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; #define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d # define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) #endif #ifndef __PAGETABLE_PUD_FOLDED #define p4d_clear(p4d) native_p4d_clear(p4d) #endif #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif #define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) #define pmd_clear(pmd) native_pmd_clear(pmd) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) #ifndef __PAGETABLE_P4D_FOLDED #define p4d_val(x) native_p4d_val(x) #define __p4d(x) native_make_p4d(x) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) #endif #ifndef __PAGETABLE_PMD_FOLDED #define pmd_val(x) native_pmd_val(x) #define __pmd(x) native_make_pmd(x) #endif #define pte_val(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) #endif /* CONFIG_PARAVIRT_XXL */ /* * The following only work if pte_present() is true. * Undefined behaviour if not.. */ static inline int pte_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_DIRTY; } static inline u32 read_pkru(void) { if (boot_cpu_has(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { struct pkru_state *pk; if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; pk = get_xsave_addr(¤t->thread.fpu.state.xsave, XFEATURE_PKRU); /* * The PKRU value in xstate needs to be in sync with the value that is * written to the CPU. The FPU restore on return to userland would * otherwise load the previous value again. */ fpregs_lock(); if (pk) pk->pkru = pkru; __write_pkru(pkru); fpregs_unlock(); } static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; } static inline int pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY; } static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; } static inline int pud_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_DIRTY; } static inline int pud_young(pud_t pud) { return pud_flags(pud) & _PAGE_ACCESSED; } static inline int pte_write(pte_t pte) { return pte_flags(pte) & _PAGE_RW; } static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) { return pte_flags(pte) & _PAGE_SPECIAL; } /* Entries that were set to PROT_NONE are inverted */ static inline u64 protnone_mask(u64 val); static inline unsigned long pte_pfn(pte_t pte) { phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) { return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } static inline unsigned long pgd_pfn(pgd_t pgd) { return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } #define p4d_leaf p4d_large static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ return 0; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #endif #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { return boot_cpu_has(X86_FEATURE_PSE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_devmap(pud_t pud) { return !!(pud_val(pud) & _PAGE_DEVMAP); } #else static inline int pud_devmap(pud_t pud) { return 0; } #endif static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); return native_make_pte(v | set); } static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) { pteval_t v = native_pte_val(pte); return native_make_pte(v & ~clear); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_UFFD_WP); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pte_t pte_mkclean(pte_t pte) { return pte_clear_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkold(pte_t pte) { return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_wrprotect(pte_t pte) { return pte_clear_flags(pte, _PAGE_RW); } static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL); } static inline pte_t pte_mkdevmap(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); } static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v & ~clear); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_UFFD_WP; } static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_UFFD_WP); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pmd_t pmd_mkold(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkclean(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DEVMAP); } static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkwrite(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkclean(pud_t pud) { return pud_clear_flags(pud, _PAGE_DIRTY); } static inline pud_t pud_wrprotect(pud_t pud) { return pud_clear_flags(pud, _PAGE_RW); } static inline pud_t pud_mkdirty(pud_t pud) { return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pud_t pud_mkdevmap(pud_t pud) { return pud_set_flags(pud, _PAGE_DEVMAP); } static inline pud_t pud_mkhuge(pud_t pud) { return pud_set_flags(pud, _PAGE_PSE); } static inline pud_t pud_mkyoung(pud_t pud) { return pud_set_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkwrite(pud_t pud) { return pud_set_flags(pud, _PAGE_RW); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; } static inline int pmd_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } static inline int pud_soft_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_SOFT_DIRTY; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_mksoft_dirty(pud_t pud) { return pud_set_flags(pud, _PAGE_SOFT_DIRTY); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_clear_soft_dirty(pud_t pud) { return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. */ static inline pgprotval_t massage_pgprot(pgprot_t pgprot) { pgprotval_t protval = pgprot_val(pgprot); if (protval & _PAGE_PRESENT) protval &= __supported_pte_mask; return protval; } static inline pgprotval_t check_pgprot(pgprot_t pgprot) { pgprotval_t massaged_val = massage_pgprot(pgprot); /* mmdebug.h can not be included here because of dependencies */ #ifdef CONFIG_DEBUG_VM WARN_ONCE(pgprot_val(pgprot) != massaged_val, "attempted to set unsupported pgprot: %016llx " "bits: %016llx supported: %016llx\n", (u64)pgprot_val(pgprot), (u64)pgprot_val(pgprot) ^ massaged_val, (u64)__supported_pte_mask); #endif return massaged_val; } static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PUD_PAGE_MASK; return __pud(pfn | check_pgprot(pgprot)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; /* * Chop off the NX bit (if present), and add the NX portion of * the newprot (if present): */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); } /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) #define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline pgprot_t arch_filter_pgprot(pgprot_t prot) { return canon_pgprot(prot); } static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. */ if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* * Certain new memtypes are not allowed with certain * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back * - request is write-through, return cannot be write-back * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } return 1; } pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); #ifdef CONFIG_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* * Take a PGD location (pgdp) and a pgd value that needs to be set there. * Populates the user and returns the resulting PGD that must be set in * the kernel copy of the page tables. */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { if (!static_cpu_has(X86_FEATURE_PTI)) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } #else /* CONFIG_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } #endif /* CONFIG_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else # include <asm/pgtable_64.h> #endif #ifndef __ASSEMBLY__ #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> #include <asm/fixmap.h> static inline int pte_none(pte_t pte) { return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) { return a.pte == b.pte; } static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t a) { return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; } #endif #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { if (pte_flags(a) & _PAGE_PRESENT) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && mm_tlb_flush_pending(mm)) return true; return false; } static inline int pmd_present(pmd_t pmd) { /* * Checking for _PAGE_PSE is needed too because * split_huge_page will temporarily clear the present bit (but * the _PAGE_PSE flag will remain set at all times while the * _PAGE_PRESENT bit is clear). */ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } #ifdef CONFIG_NUMA_BALANCING /* * These work without NUMA balancing but the kernel does not care. See the * comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } static inline int pmd_protnone(pmd_t pmd) { return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } #endif /* CONFIG_NUMA_BALANCING */ static inline int pmd_none(pmd_t pmd) { /* Only check low word on 32-bit platforms, since it might be out of sync with upper half. */ unsigned long val = native_pmd_val(pmd); return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * * (Currently stuck as a macro because of indirect forward reference * to linux/mm.h:page_to_nid()) */ #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE; } static inline unsigned long pages_to_mb(unsigned long npg) { return npg >> (20 - PAGE_SHIFT); } #if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int pud_present(pud_t pud) { return pud_flags(pud) & _PAGE_PRESENT; } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) #define pud_leaf pud_large static inline int pud_large(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == (_PAGE_PSE | _PAGE_PRESENT); } static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #else #define pud_leaf pud_large static inline int pud_large(pud_t pud) { return 0; } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline int p4d_none(p4d_t p4d) { return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int p4d_present(p4d_t p4d) { return p4d_flags(p4d) & _PAGE_PRESENT; } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ static inline unsigned long p4d_index(unsigned long address) { return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); } #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { if (!pgtable_l5_enabled()) return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } static inline unsigned long pgd_page_vaddr(pgd_t pgd) { return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; if (!pgtable_l5_enabled()) return 0; if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) { if (!pgtable_l5_enabled()) return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables * except on 32-bit non-PAE which is not supported on * KNL. */ return !native_pgd_val(pgd); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) #ifndef __ASSEMBLY__ extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); extern void memblock_find_dma_reserve(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); #ifdef CONFIG_X86_64 extern pgd_t trampoline_pgd_entry; #endif /* local pte updates need not use xchg for locking */ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) { pte_t res = *ptep; /* Pure native function needs no input for mm, addr */ native_pte_clear(NULL, 0, ptep); return res; } static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) { pmd_t res = *pmdp; native_pmd_clear(pmdp); return res; } static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) { pud_t res = *pudp; native_pud_clear(pudp); return res; } static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { native_set_pud(pudp, pud); } /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to * race with other CPU's that might be updating the dirty * bit at the same time. */ struct vm_area_struct; #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH extern int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; if (full) { /* * Full address destruction in progress; paravirt does not * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte); } #define flush_tlb_fix_spurious_fault(vma, address) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_RW; } #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { return native_pmdp_get_and_clear(pmdp); } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { return native_pudp_get_and_clear(pudp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); } #define pud_write pud_write static inline int pud_write(pud_t pud) { return pud_flags(pud) & _PAGE_RW; } #ifndef pmdp_establish #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; WRITE_ONCE(*pmdp, pmd); return old; } } #endif /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. * * Returns true for parts of the PGD that map userspace and * false for the parts that map the kernel. */ static inline bool pgdp_maps_userspace(void *__ptr) { unsigned long ptr = (unsigned long)__ptr; return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } #define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } #ifdef CONFIG_PAGE_TABLE_ISOLATION /* * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. */ #define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT /* * This generates better code than the inline assembly in * __set_bit(). */ static inline void *ptr_set_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr |= BIT(bit); return (void *)__ptr; } static inline void *ptr_clear_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr &= ~BIT(bit); return (void *)__ptr; } static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) { return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) { return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) { return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } #endif /* CONFIG_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * * dst - pointer to pgd range anwhere on a pgd page * src - "" * count - the number of pgds to copy. * * dst and src can be on the same page, but the range must not overlap, * and must not cross a page boundary. */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), count * sizeof(pgd_t)); #endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) static inline int page_level_shift(enum pg_level level) { return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; } static inline unsigned long page_level_size(enum pg_level level) { return 1UL << page_level_shift(level); } static inline unsigned long page_level_mask(enum pg_level level) { return ~(page_level_size(level) - 1); } /* * The x86 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } #endif #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_UFFD_WP); } static inline int pte_swp_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_UFFD_WP; } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP); } static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP); } static inline int pmd_swp_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP; } static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #else #define init_pkru_value 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* ifdef to avoid doing 59-bit shift on 32-bit values */ return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; #else return 0; #endif } static inline bool __pkru_allows_pkey(u16 pkey, bool write) { u32 pkru = read_pkru(); if (!__pkru_allows_read(pkru, pkey)) return false; if (write && !__pkru_allows_write(pkru, pkey)) return false; return true; } /* * 'pteval' can come from a PTE, PMD or PUD. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the * same value on all 3 types. */ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; if (write) need_pte_bits |= _PAGE_RW; if ((pteval & need_pte_bits) != need_pte_bits) return 0; return __pkru_allows_pkey(pte_flags_pkey(pteval), write); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { return __pte_access_permitted(pte_val(pte), write); } #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { return __pte_access_permitted(pmd_val(pmd), write); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return __pte_access_permitted(pud_val(pud), write); } #define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); static inline bool arch_has_pfn_modify_check(void) { return boot_cpu_has_bug(X86_BUG_L1TF); } #define arch_faults_on_old_pte arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { return false; } #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_STACK_H #define _LINUX_SCHED_TASK_STACK_H /* * task->stack (kernel stack) handling interfaces: */ #include <linux/sched.h> #include <linux/magic.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * When accessing the stack of a non-current task that might exit, use * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } #define setup_thread_stack(new,old) do { } while(0) static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; #else return task->stack; #endif } #elif !defined(__HAVE_THREAD_FUNCTIONS) #define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { *task_thread_info(p) = *task_thread_info(org); task_thread_info(p)->task = p; } /* * Return the address of the last usable long on the stack. * * When the stack grows down, this is just above the thread * info struct. Going any lower will corrupt the threadinfo. * * When the stack grows up, this is the highest address. * Beyond that position, we corrupt data on the next page. */ static inline unsigned long *end_of_stack(struct task_struct *p) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; #else return (unsigned long *)(task_thread_info(p) + 1); #endif } #endif #ifdef CONFIG_THREAD_INFO_IN_TASK static inline void *try_get_task_stack(struct task_struct *tsk) { return refcount_inc_not_zero(&tsk->stack_refcount) ? task_stack_page(tsk) : NULL; } extern void put_task_stack(struct task_struct *tsk); #else static inline void *try_get_task_stack(struct task_struct *tsk) { return task_stack_page(tsk); } static inline void put_task_stack(struct task_struct *tsk) {} #endif #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE static inline unsigned long stack_not_used(struct task_struct *p) { unsigned long *n = end_of_stack(p); do { /* Skip over canary */ # ifdef CONFIG_STACK_GROWSUP n--; # else n++; # endif } while (!*n); # ifdef CONFIG_STACK_GROWSUP return (unsigned long)end_of_stack(p) - (unsigned long)n; # else return (unsigned long)n - (unsigned long)end_of_stack(p); # endif } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); #ifndef __HAVE_ARCH_KSTACK_END static inline int kstack_end(void *addr) { /* Reliable end of stack detection: * Some APM bios versions misalign the stack */ return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); } #endif #endif /* _LINUX_SCHED_TASK_STACK_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/userfaultfd_k.h> #include <linux/page_owner.h> #include "internal.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; #endif static unsigned long hugetlb_cma_size __initdata; /* * Minimum page order among possible hugepage sizes, set to a proper value * at boot time. */ static unsigned int minimum_order __read_mostly = UINT_MAX; __initdata LIST_HEAD(huge_boot_pages); /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; static inline bool PageHugeFreed(struct page *head) { return page_private(head + 4) == -1UL; } static inline void SetPageHugeFreed(struct page *head) { set_page_private(head + 4, -1UL); } static inline void ClearPageHugeFreed(struct page *head) { set_page_private(head + 4, 0); } /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks); static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { bool free = (spool->count == 0) && (spool->used_hpages == 0); spin_unlock(&spool->lock); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (free) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { spin_lock(&spool->lock); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return delta; spin_lock(&spool->lock); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool); return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg = NULL; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg && org && rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg = NULL, *prg = NULL; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *rg = NULL, *trg = NULL, *nrg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, rg->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(rg, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (rg->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (rg->to > last_accounted_offset) last_accounted_offset = rg->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (rg->from > t) break; /* Add an entry for last_accounted_offset -> rg->from, and * update last_accounted_offset. */ if (rg->from > last_accounted_offset) { add += rg->from - last_accounted_offset; if (!regions_needed) { nrg = get_file_region_entry_from_cache( resv, last_accounted_offset, rg->from); record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg); list_add(&nrg->link, rg->link.prev); coalesce_file_region(resv, nrg); } else *regions_needed += 1; } last_accounted_offset = rg->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (last_accounted_offset < t) { add += t - last_accounted_offset; if (!regions_needed) { nrg = get_file_region_entry_from_cache( resv, last_accounted_offset, t); record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg); list_add(&nrg->link, rg->link.prev); coalesce_file_region(resv, nrg); } else *regions_needed += 1; } VM_BUG_ON(add < 0); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { struct list_head allocated_regions; int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); INIT_LIST_HEAD(&allocated_regions); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existings adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); VM_BUG_ON(add < 0); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, in pagecache page units; huge pages here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address) { return vma_hugecache_offset(hstate_vma(vma), vma, address); } EXPORT_SYMBOL_GPL(linear_hugepage_index); /* * Return the size of the pages allocated when backing a VMA. In the majority * cases this will be same size as used by the page table entries. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of reset_vma_resv_huge_pages() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (get_vma_private_data(vma) & HPAGE_RESV_MASK) | (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } /* Reset counters to 0 and clear all HPAGE_RESV_* flags */ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (!(vma->vm_flags & VM_MAYSHARE)) vma->vm_private_data = (void *)0; } /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { if (vma->vm_flags & VM_NORESERVE) { /* * This address is already reserved by other process(chg == 0), * so, we should decrement reserved count. Without decrementing, * reserve count remains after releasing inode, because this * allocated page will go into page cache and is regarded as * coming from reserved pool in releasing step. Currently, we * don't have any other solution to deal with this situation * properly, so add work-around here. */ if (vma->vm_flags & VM_MAYSHARE && chg == 0) return true; else return false; } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) { /* * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) return false; else return true; } /* * Only the process that called mmap() has reserves for * private mappings. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Like the shared case above, a hole punch or truncate * could have been performed on the private mapping. * Examine the value of chg to determine if reserves * actually exist or were previously consumed. * Very Subtle - The value of chg comes from a previous * call to vma_needs_reserves(). The reserve map for * private mappings has different (opposite) semantics * than that of shared mappings. vma_needs_reserves() * has already taken this difference in semantics into * account. Therefore, the meaning of chg is the same * as in the shared case above. Code could easily be * combined, but keeping it separate draws attention to * subtle differences. */ if (chg) return false; else return true; } return false; } static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; SetPageHugeFreed(page); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) { struct page *page; bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA); list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { if (nocma && is_migrate_cma_page(page)) continue; if (PageHWPoison(page)) continue; list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); ClearPageHugeFreed(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return page; } return NULL; } static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct page *page; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); page = dequeue_huge_page_node_exact(h, node); if (page) return page; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) { struct page *page; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ if (!vma_has_reserves(vma, chg) && h->free_huge_pages - h->resv_huge_pages == 0) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); if (page && !avoid_reserve && vma_has_reserves(vma, chg)) { SetPagePrivate(page); h->resv_huge_pages--; } mpol_cond_put(mpol); return page; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for free_pool_huge_page() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static void destroy_compound_gigantic_page(struct page *page, unsigned int order) { int i; int nr_pages = 1 << order; struct page *p = page + 1; atomic_set(compound_mapcount_ptr(page), 0); atomic_set(compound_pincount_ptr(page), 0); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { clear_compound_head(p); set_page_refcounted(p); } set_compound_order(page, 0); page[1].compound_nr = 0; __ClearPageHead(page); } static void free_gigantic_page(struct page *page, unsigned int order) { /* * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ #ifdef CONFIG_CMA if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) return; #endif free_contig_range(page_to_pfn(page), 1 << order); } #ifdef CONFIG_CONTIG_ALLOC static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { unsigned long nr_pages = 1UL << huge_page_order(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); #ifdef CONFIG_CMA { struct page *page; int node; if (hugetlb_cma[nid]) { page = cma_alloc(hugetlb_cma[nid], nr_pages, huge_page_order(h), true); if (page) return page; } if (!(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; page = cma_alloc(hugetlb_cma[node], nr_pages, huge_page_order(h), true); if (page) return page; } } } #endif return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } #else /* !CONFIG_CONTIG_ALLOC */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } static inline void free_gigantic_page(struct page *page, unsigned int order) { } static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } #endif static void update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage = page; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++, subpage = mem_map_next(subpage, page, i)) { subpage->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_private | 1 << PG_writeback); } VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); set_compound_page_dtor(page, NULL_COMPOUND_DTOR); set_page_refcounted(page); if (hstate_is_gigantic(h)) { /* * Temporarily drop the hugetlb_lock, because * we might block in free_gigantic_page(). */ spin_unlock(&hugetlb_lock); destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); spin_lock(&hugetlb_lock); } else { __free_pages(page, huge_page_order(h)); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } /* * Test to determine whether the hugepage is "active/in-use" (i.e. being linked * to hstate->hugepage_activelist.) * * This function can be called for tail pages, but never returns true for them. */ bool page_huge_active(struct page *page) { return PageHeadHuge(page) && PagePrivate(&page[1]); } /* never called for tail page */ void set_page_huge_active(struct page *page) { VM_BUG_ON_PAGE(!PageHeadHuge(page), page); SetPagePrivate(&page[1]); } static void clear_page_huge_active(struct page *page) { VM_BUG_ON_PAGE(!PageHeadHuge(page), page); ClearPagePrivate(&page[1]); } /* * Internal hugetlb specific page flag. Do not use outside of the hugetlb * code */ static inline bool PageHugeTemporary(struct page *page) { if (!PageHuge(page)) return false; return (unsigned long)page[2].mapping == -1U; } static inline void SetPageHugeTemporary(struct page *page) { page[2].mapping = (void *)-1U; } static inline void ClearPageHugeTemporary(struct page *page) { page[2].mapping = NULL; } static void __free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the * compound page destructor. */ struct hstate *h = page_hstate(page); int nid = page_to_nid(page); struct hugepage_subpool *spool = (struct hugepage_subpool *)page_private(page); bool restore_reserve; VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(page_mapcount(page), page); set_page_private(page, 0); page->mapping = NULL; restore_reserve = PagePrivate(page); ClearPagePrivate(page); /* * If PagePrivate() was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservtion, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock(&hugetlb_lock); clear_page_huge_active(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), pages_per_huge_page(h), page); if (restore_reserve) h->resv_huge_pages++; if (PageHugeTemporary(page)) { list_del(&page->lru); ClearPageHugeTemporary(page); update_and_free_page(h, page); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ list_del(&page->lru); update_and_free_page(h, page); h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); } /* * As free_huge_page() can be called from a non-task context, we have * to defer the actual freeing in a workqueue to prevent potential * hugetlb_lock deadlock. * * free_hpage_workfn() locklessly retrieves the linked list of pages to * be freed and frees them one-by-one. As the page->mapping pointer is * going to be cleared in __free_huge_page() anyway, it is reused as the * llist_node structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; struct page *page; node = llist_del_all(&hpage_freelist); while (node) { page = container_of((struct address_space **)node, struct page, mapping); node = node->next; __free_huge_page(page); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); void free_huge_page(struct page *page) { /* * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. */ if (!in_task()) { /* * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the * workfn hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); return; } __free_huge_page(page); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); set_hugetlb_cgroup(page, NULL); set_hugetlb_cgroup_rsvd(page, NULL); spin_lock(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; ClearPageHugeFreed(page); spin_unlock(&hugetlb_lock); } static void prep_compound_gigantic_page(struct page *page, unsigned int order) { int i; int nr_pages = 1 << order; struct page *p = page + 1; /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); __ClearPageReserved(page); __SetPageHead(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic * hugepages and clear the PG_reserved bit from all tail pages * too. Otherwise drivers using get_user_pages() to access tail * pages may get the reference counting wrong if they see * PG_reserved set on a tail page (despite the head page not * having PG_reserved set). Enforcing this consistency between * head and tail pages allows drivers to optimize away a check * on the head page when they need know if put_page() is needed * after get_user_pages(). */ __ClearPageReserved(p); set_page_count(p, 0); set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); atomic_set(compound_pincount_ptr(page), 0); } /* * PageHuge() only returns true for hugetlbfs pages, but not for normal or * transparent huge pages. See the PageTransHuge() documentation for more * details. */ int PageHuge(struct page *page) { if (!PageCompound(page)) return 0; page = compound_head(page); return page[1].compound_dtor == HUGETLB_PAGE_DTOR; } EXPORT_SYMBOL_GPL(PageHuge); /* * PageHeadHuge() only returns true for hugetlbfs head page, but not for * normal or transparent huge pages. */ int PageHeadHuge(struct page *page_head) { if (!PageHead(page_head)) return 0; return page_head[1].compound_dtor == HUGETLB_PAGE_DTOR; } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the page is locked which means that page_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) { struct address_space *mapping = page_mapping(hpage); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx; if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else compound_idx = page - page_head; return (index << compound_order(page_head)) + compound_idx; } static struct page *alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); struct page *page; bool alloc_try_hard = true; /* * By default we always try hard to allocate the page with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating pages in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; gfp_mask |= __GFP_COMP|__GFP_NOWARN; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask); if (page) __count_vm_event(HTLB_BUDDY_PGALLOC); else __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this * indicates an overall state change. Clear bit so that we resume * normal 'try hard' allocations. */ if (node_alloc_noretry && page && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a page but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !page && alloc_try_hard) node_set(nid, *node_alloc_noretry); return page; } /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages */ static struct page *alloc_fresh_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct page *page; if (hstate_is_gigantic(h)) page = alloc_gigantic_page(h, gfp_mask, nid, nmask); else page = alloc_buddy_huge_page(h, gfp_mask, nid, nmask, node_alloc_noretry); if (!page) return NULL; if (hstate_is_gigantic(h)) prep_compound_gigantic_page(page, huge_page_order(h)); prep_new_huge_page(h, page, page_to_nid(page)); return page; } /* * Allocates a fresh page to the hugetlb allocator pool in the node interleaved * manner. */ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry) { struct page *page; int nr_nodes, node; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (page) break; } if (!page) return 0; put_page(page); /* free it into the hugepage allocator */ return 1; } /* * Free huge page from pool from next node to free. * Attempt to keep persistent huge pages more or less * balanced over allowed nodes. * Called with hugetlb_lock locked. */ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; int ret = 0; for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { struct page *page = list_entry(h->hugepage_freelists[node].next, struct page, lru); list_del(&page->lru); h->free_huge_pages--; h->free_huge_pages_node[node]--; if (acct_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[node]--; } update_and_free_page(h, page); ret = 1; break; } } return ret; } /* * Dissolve a given free hugepage into free buddy pages. This function does * nothing for in-use hugepages and non-hugepages. * This function returns values like below: * * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!PageHuge(page)) return 0; spin_lock(&hugetlb_lock); if (!PageHuge(page)) { rc = 0; goto out; } if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); int nid = page_to_nid(head); if (h->free_huge_pages - h->resv_huge_pages == 0) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!PageHugeFreed(head))) { spin_unlock(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } /* * Move PageHWPoison flag from head page to the raw error page, * which makes any subpages rather than the error page reusable. */ if (PageHWPoison(head) && page != head) { SetPageHWPoison(page); ClearPageHWPoison(head); } list_del(&head->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; h->max_huge_pages--; update_and_free_page(h, head); rc = 0; } out: spin_unlock(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_huge_page() returns with an error, all * free hugepages that were dissolved before that error are lost. */ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; int rc = 0; if (!hugepages_supported()) return rc; for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { page = pfn_to_page(pfn); rc = dissolve_free_huge_page(page); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct page *page = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock(&hugetlb_lock); page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); if (!page) return NULL; spin_lock(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_page * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { SetPageHugeTemporary(page); spin_unlock(&hugetlb_lock); put_page(page); return NULL; } else { h->surplus_huge_pages++; h->surplus_huge_pages_node[page_to_nid(page)]++; } out_unlock: spin_unlock(&hugetlb_lock); return page; } static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct page *page; if (hstate_is_gigantic(h)) return NULL; page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); if (!page) return NULL; /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ SetPageHugeTemporary(page); return page; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct page *page; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return page; } /* page migration callback function */ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { spin_lock(&hugetlb_lock); if (h->free_huge_pages - h->resv_huge_pages > 0) { struct page *page; page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask); if (page) { spin_unlock(&hugetlb_lock); return page; } } spin_unlock(&hugetlb_lock); return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask); } /* mempolicy aware migration callback */ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct page *page; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); return page; } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, int delta) __must_hold(&hugetlb_lock) { struct list_head surplus_list; struct page *page, *tmp; int ret, i; int needed, allocated; bool alloc_ok = true; needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; INIT_LIST_HEAD(&surplus_list); ret = -ENOMEM; retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { page = alloc_surplus_huge_page(h, htlb_alloc_mask(h), NUMA_NO_NODE, NULL); if (!page) { alloc_ok = false; break; } list_add(&page->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* * This page is now managed by the hugetlb allocator and has * no users -- drop the buddy allocator's reference. */ put_page_testzero(page); VM_BUG_ON_PAGE(page_count(page), page); enqueue_huge_page(h, page); } free: spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) put_page(page); spin_lock(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. * * Called with hugetlb_lock held. However, the lock could be dropped (and * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, * we must make sure nobody else can claim pages we are in the process of * freeing. Do this by ensuring resv_huge_page always is greater than the * number of huge pages we plan to free when dropping the lock. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; /* Cannot return gigantic pages currently */ if (hstate_is_gigantic(h)) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * free_pool_huge_page() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. * * Note that we decrement resv_huge_pages as we free the pages. If * we drop the lock, resv_huge_pages will still be sufficiently large * to cover subsequent pages we may free. */ while (nr_pages--) { h->resv_huge_pages--; unused_resv_pages--; if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) goto out; cond_resched_lock(&hugetlb_lock); } out: /* Fully uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE) return ret; else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { /* * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret) return 0; else return 1; } else return ret < 0 ? ret : 0; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } /* * This routine is called to restore a reservation on error paths. In the * specific error paths, a huge page was allocated (via alloc_huge_page) * and is about to be freed. If a reservation for the page existed, * alloc_huge_page would have consumed the reservation and set PagePrivate * in the newly allocated page. When the page is freed via free_huge_page, * the global reservation count will be incremented if PagePrivate is set. * However, free_huge_page can not adjust the reserve map. Adjust the * reserve map here to be consistent with global reserve count adjustments * to be made by free_huge_page. */ static void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page) { if (unlikely(PagePrivate(page))) { long rc = vma_needs_reservation(h, vma, address); if (unlikely(rc < 0)) { /* * Rare out of memory condition in reserve map * manipulation. Clear PagePrivate so that * global reserve count will not be incremented * by free_huge_page. This will make it appear * as though the reservation for this page was * consumed. This may prevent the task from * faulting in the page at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ ClearPagePrivate(page); } else if (rc) { rc = vma_add_reservation(h, vma, address); if (unlikely(rc < 0)) /* * See above comment about rare out of * memory condition. */ ClearPagePrivate(page); } else vma_end_reservation(h, vma, address); } } struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; long map_chg, map_commit; long gbl_chg; int ret, idx; struct hugetlb_cgroup *h_cg; bool deferred_reserve; idx = hstate_index(h); /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); if (map_chg < 0) return ERR_PTR(-ENOMEM); /* * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Allocations for MAP_NORESERVE mappings also need to be * checked against any subpool limit. */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) { vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } /* * Even though there was no reservation in the region/reserve * map, there could be reservations associated with the * subpool that can be used. This would be indicated if the * return value of hugepage_subpool_get_pages() is zero. * However, if avoid_reserve is specified we still avoid even * the subpool reservations. */ if (avoid_reserve) gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. */ deferred_reserve = map_chg || avoid_reserve || !vma_resv_map(vma); if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!page) { spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; spin_lock(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { SetPagePrivate(page); h->resv_huge_pages--; } list_add(&page->lru, &h->hugepage_activelist); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, page); } spin_unlock(&hugetlb_lock); set_page_private(page, (unsigned long)spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), pages_per_huge_page(h), page); } return page; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (deferred_reserve) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } int alloc_bootmem_huge_page(struct hstate *h) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; int nr_nodes, node; for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; addr = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); if (addr) { /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). */ m = addr; goto found; } } return 0; found: BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); m->hstate = h; return 1; } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_ORDER) pages. */ static void __init gather_bootmem_prealloc(void) { struct huge_bootmem_page *m; list_for_each_entry(m, &huge_boot_pages, list) { struct page *page = virt_to_page(m); struct hstate *h = m->hstate; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(page_count(page) != 1); prep_compound_gigantic_page(page, huge_page_order(h)); WARN_ON(PageReserved(page)); prep_new_huge_page(h, page, page_to_nid(page)); put_page(page); /* free it into the hugepage allocator */ /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. */ adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } } static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. * Ignore errors as lower level routines can deal with * node_alloc_noretry == NULL. If this kmalloc fails at boot * time, we are likely in bigger trouble. */ node_alloc_noretry = kmalloc(sizeof(*node_alloc_noretry), GFP_KERNEL); } else { /* allocations done at boot time */ node_alloc_noretry = NULL; } /* bit mask controlling how hard we retry per-node allocations */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { if (hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); goto free; } if (!alloc_bootmem_huge_page(h)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], node_alloc_noretry)) break; cond_resched(); } if (i < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, i); h->max_huge_pages = i; } free: kfree(node_alloc_noretry); } static void __init hugetlb_init_hstates(void) { struct hstate *h; for_each_hstate(h) { if (minimum_order > huge_page_order(h)) minimum_order = huge_page_order(h); /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } VM_BUG_ON(minimum_order == UINT_MAX); } static void __init report_hugepages(void) { struct hstate *h; for_each_hstate(h) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; if (hstate_is_gigantic(h)) return; for_each_node_mask(i, *nodes_allowed) { struct page *page, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(page, next, freel, lru) { if (count >= h->nr_huge_pages) return; if (PageHighMem(page)) continue; list_del(&page->lru); update_and_free_page(h, page); h->free_huge_pages--; h->free_huge_pages_node[page_to_nid(page)]--; } } } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count, ret; NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; spin_lock(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock(&hugetlb_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_huge_page() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } while (count > persistent_huge_pages(h)) { /* * If this allocation races such that we no longer need the * page, free_huge_page will handle it by freeing the page * and reducing the surplus. */ spin_unlock(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); ret = alloc_pool_huge_page(h, nodes_allowed, node_alloc_noretry); spin_lock(&hugetlb_lock); if (!ret) goto out; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) goto out; } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_huge_page() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); while (min_count < persistent_huge_pages(h)) { if (!free_pool_huge_page(h, nodes_allowed, 0)) break; cond_resched_lock(&hugetlb_lock); } while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock(&hugetlb_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sprintf(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sprintf(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sprintf(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sprintf(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; } return retval; } static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s", h->name); } } #ifdef CONFIG_NUMA /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ static void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); if (nhs->hstate_kobjs[idx]) { kobject_put(nhs->hstate_kobjs[idx]); nhs->hstate_kobjs[idx] = NULL; } } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ static void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_node_state(nid, N_MEMORY) { struct node *node = node_devices[nid]; if (node->dev.id == nid) hugetlb_register_node(node); } /* * Let the node device driver know we're here so it can * [un]register hstate attributes on node hotplug. */ register_hugetlbfs_with_node(hugetlb_register_node, hugetlb_unregister_node); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif static int __init hugetlb_init(void) { int i; if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_register_all_nodes(); hugetlb_cgroup_file_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); h = &hstates[hugetlb_max_hstate++]; h->order = order; h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); h->nr_huge_pages = 0; h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); parsed_hstate = h; } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 0; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 0; } if (sscanf(s, "%lu", mhp) <= 0) *mhp = 0; /* * Global state is always initialized later in hugetlb_init. * But we need to allocate >= MAX_ORDER hstates here early to still * use the bootmem allocator. */ if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; } __setup("hugepages=", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return 0; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return 0; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 1; } __setup("hugepagesz=", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return 0; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return 0; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (>= MAX_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; } return 1; } __setup("default_hugepagesz=", default_hugepagesz_setup); static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mpol_allowed; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mpol_allowed = policy_nodemask_current(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mpol_allowed || (mpol_allowed && node_isset(node, *mpol_allowed))) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } int hugetlb_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ int hugetlb_overcommit_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock(&hugetlb_lock); } out: return ret; } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += (PAGE_SIZE << huge_page_order(h)) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, (PAGE_SIZE << huge_page_order(h)) / 1024); } seq_printf(m, "Hugetlb: %8lu kB\n", total / 1024); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo(void) { struct hstate *h; int nid; if (!hugepages_supported()) return; for_each_node_state(nid, N_MEMORY) for_each_hstate(h) pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", atomic_long_read(&mm->hugetlb_usage) << (PAGE_SHIFT - 10)); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; spin_lock(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; return 0; } void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) { /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. * This function is called in the middle of a VMA split operation, with * MM, VMA and rmap all write-locked to prevent concurrent page table * walks (except hardware and gup_fast()). */ mmap_assert_write_locked(vma->vm_mm); i_mmap_assert_write_locked(vma->vm_file->f_mapping); if (addr & ~PUD_MASK) { unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) { /* * Locking: * Use take_locks=false here. * The file rmap lock is already held. * The hugetlb VMA lock can't be taken when we already * hold the file rmap lock, and we don't need it because * its purpose is to synchronize against concurrent page * table walks, which are not possible thanks to the * locks held by our caller. */ hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); } } } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { struct hstate *hstate = hstate_vma(vma); return 1UL << huge_page_shift(hstate); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { entry = huge_pte_wrprotect(mk_huge_pte(page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = pte_mkhuge(entry); entry = arch_make_huge_pte(entry, vma, page, writable); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } static bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) { pte_t *src_pte, *dst_pte, entry; struct page *ptepage; unsigned long addr; int cow; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct address_space *mapping = vma->vm_file->f_mapping; struct mmu_notifier_range range; int ret = 0; cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, vma->vm_start, vma->vm_end); mmu_notifier_invalidate_range_start(&range); } else { /* * For shared mappings i_mmap_rwsem must be held to call * huge_pte_alloc, otherwise the returned ptep could go * away if part of a shared pmd and another thread calls * huge_pmd_unshare. */ i_mmap_lock_read(mapping); } for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE /* If the pagetables are shared, there is nothing to do */ if (atomic_read(&virt_to_page(dst_pte)->pt_share_count)) continue; #endif dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (huge_pte_none(entry)) { /* * Skip if src entry none. */ ; } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); if (is_write_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&swp_entry); entry = swp_entry_to_pte(swp_entry); set_huge_swap_pte_at(src, addr, src_pte, entry, sz); } set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); } else { if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); } entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); page_dup_rmap(ptepage, true); set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(pages_per_huge_page(h), dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) mmu_notifier_invalidate_range_end(&range); else i_mmap_unlock_read(mapping); return ret; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); /* * If sharing possible, alert mmu notifiers of worst case. */ mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); address = start; for (; address < end; address += sz) { ptep = huge_pte_offset(mm, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(tlb, vma, &address, ptep)) { spin_unlock(ptl); continue; } pte = huge_ptep_get(ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { if (page != ref_page) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, true); spin_unlock(ptl); tlb_remove_page_size(tlb, page, huge_page_size(h)); /* * Bail out after unmapping reference page if supplied */ if (ref_page) break; } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); huge_pmd_unshare_flush(tlb, vma); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { __unmap_hugepage_range(tlb, vma, start, end, ref_page); /* * Clear this flag so that x86's huge_pmd_share page_table_shareable * test will fail on a vma being torn down, and not grab a page table * on its way out. We're lucky that the flag has such an appropriate * name, and can in fact be safely cleared here. We could clear it * before the __unmap_hugepage_range above, but all that's necessary * is to clear it before releasing the i_mmap_rwsem. This works * because in the context this is called, the VMA is about to be * destroyed and the i_mmap_rwsem is held. */ vma->vm_flags &= ~VM_MAYSHARE; } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { struct mm_struct *mm; struct mmu_gather tlb; unsigned long tlb_start = start; unsigned long tlb_end = end; /* * If shared PMDs were possibly used within this vma range, adjust * start/end for worst case tlb flushing. * Note that we can not be sure if PMDs are shared until we try to * unmap pages. However, we want to make sure TLB flushing covers * the largest possible range. */ adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); mm = vma->vm_mm; tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); tlb_finish_mmu(&tlb, tlb_start, tlb_end); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mappping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page); } i_mmap_unlock_write(mapping); } /* * Hugetlb_cow() should be called with page lock of the original hugepage held. * Called with hugetlb_instantiation_mutex held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, struct page *pagecache_page, spinlock_t *ptl) { pte_t pte; struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; int outside_reserve = 0; vm_fault_t ret = 0; unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; pte = huge_ptep_get(ptep); old_page = pte_page(pte); retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { page_move_anon_rmap(old_page, vma); set_huge_ptep_writable(vma, haddr, ptep); return 0; } /* * If the process that created a MAP_PRIVATE mapping is about to * perform a COW due to a shared page count, attempt to satisfy * the allocation without using the existing reserves. The pagecache * page is used to determine if the reserve at this address was * consumed or not. If reserves were used, a partial faulted mapping * at the time of fork() could consume its reserves on COW instead * of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; get_page(old_page); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(ptl); new_page = alloc_huge_page(vma, haddr, outside_reserve); if (IS_ERR(new_page)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (outside_reserve) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; put_page(old_page); BUG_ON(huge_pte_none(pte)); /* * Drop hugetlb_fault_mutex and i_mmap_rwsem before * unmapping. unmapping needs to hold i_mmap_rwsem * in write mode. Dropping i_mmap_rwsem in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); unmap_ref_private(mm, vma, old_page, haddr); i_mmap_lock_read(mapping); mutex_lock(&hugetlb_fault_mutex_table[hash]); spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ return 0; } ret = vmf_error(PTR_ERR(new_page)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto out_release_all; } copy_user_huge_page(new_page, old_page, address, vma, pages_per_huge_page(h)); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, haddr, haddr + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { ClearPagePrivate(new_page); /* Break COW */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); set_huge_pte_at(mm, haddr, ptep, make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); set_page_huge_active(new_page); /* Make the old page be freed below */ new_page = old_page; } spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: restore_reserve_on_error(h, vma, haddr, new_page); put_page(new_page); out_release_old: put_page(old_page); spin_lock(ptl); /* Caller expects lock to be held */ return ret; } /* Return the pagecache page at a given address within a VMA */ static struct page *hugetlbfs_pagecache_page(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); return find_lock_page(mapping, idx); } /* * Return whether there is a pagecache page to back given address within VMA. * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page. */ static bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; struct page *page; mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); page = find_get_page(mapping, idx); if (page) put_page(page); return page != NULL; } int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL); if (err) return err; ClearPagePrivate(page); /* * set page dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ set_page_dirty(page); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, unsigned long address, pte_t *ptep, unsigned int flags) { struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct page *page; pte_t new_pte; spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); bool new_page = false; u32 hash = hugetlb_fault_mutex_hash(mapping, idx); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW. Warn that such a situation has occurred as it may not be obvious */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * We can not race with truncation due to holding i_mmap_rwsem. * i_size is modified when holding i_mmap_rwsem, so check here * once for faults beyond end of file. */ size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; retry: page = find_lock_page(mapping, idx); if (!page) { /* * Check for page in userfault range */ if (userfaultfd_missing(vma)) { struct vm_fault vmf = { .vma = vma, .address = haddr, .flags = flags, /* * Hard to debug if it ends up being * used by a callee that assumes * something about the other * uninitialized fields... same as in * memory.c */ }; /* * vma_lock and hugetlb_fault_mutex must be dropped * before handling userfault. Also mmap_lock will * be dropped during handling userfault, any vma * operation should be careful from here. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); return handle_userfault(&vmf, VM_UFFD_MISSING); } page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ ptl = huge_pte_lock(h, mm, ptep); if (!huge_pte_none(huge_ptep_get(ptep))) { ret = 0; spin_unlock(ptl); goto out; } spin_unlock(ptl); ret = vmf_error(PTR_ERR(page)); goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); new_page = true; if (vma->vm_flags & VM_MAYSHARE) { int err = huge_add_to_page_cache(page, mapping, idx); if (err) { put_page(page); if (err == -EEXIST) goto retry; goto out; } } else { lock_page(page); if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto backout_unlocked; } anon_rmap = 1; } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(PageHWPoison(page))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); ret = 0; if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; if (anon_rmap) { ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else page_dup_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, haddr, ptep, new_pte); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); } spin_unlock(ptl); /* * Only make newly allocated pages active. Existing pages found * in the pagecache could be !page_huge_active() if they have been * isolated for migration. */ if (new_page) set_page_huge_active(page); unlock_page(page); out: mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); return ret; backout: spin_unlock(ptl); backout_unlocked: unlock_page(page); restore_reserve_on_error(h, vma, haddr, page); put_page(page); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocesor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { pte_t *ptep, entry; spinlock_t *ptl; vm_fault_t ret; u32 hash; pgoff_t idx; struct page *page = NULL; struct page *pagecache_page = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; unsigned long haddr = address & huge_page_mask(h); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { /* * Since we hold no locks, ptep could be stale. That is * OK as we are only making decisions based on content and * not actually modifying content here. */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { migration_entry_wait_huge(vma, mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); } /* * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold * until finished with ptep. This serves two purposes: * 1) It prevents huge_pmd_unshare from being called elsewhere * and making the ptep no longer valid. * 2) It synchronizes us with i_size modifications during truncation. * * ptep could have already be assigned via huge_pte_offset. That * is OK, as huge_pte_alloc will return the same value unless * something has changed. */ mapping = vma->vm_file->f_mapping; i_mmap_lock_read(mapping); ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); if (!ptep) { i_mmap_unlock_read(mapping); return VM_FAULT_OOM; } /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); if (huge_pte_none(entry)) /* * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); ret = 0; /* * entry could be a migration/hwpoison entry at this point, so this * check prevents the kernel from going below assuming that we have * an active hugepage in pagecache. This goto expects the 2nd page * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will * properly handle it. */ if (!pte_present(entry)) goto out_mutex; /* * If we are going to COW the mapping later, we examine the pending * reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. For private mappings, we also lookup the pagecache * page now as it is used to determine if a reservation has been * consumed. */ if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); if (!(vma->vm_flags & VM_MAYSHARE)) pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); /* Check for a racing update before calling hugetlb_cow */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) goto out_ptl; /* * hugetlb_cow() requires page locks of pte_page(entry) and * pagecache_page, so here we need take the former one * when page != pagecache_page or !pagecache_page. */ page = pte_page(entry); if (page != pagecache_page) if (!trylock_page(page)) { need_wait_lock = 1; goto out_ptl; } get_page(page); if (flags & FAULT_FLAG_WRITE) { if (!huge_pte_write(entry)) { ret = hugetlb_cow(mm, vma, address, ptep, pagecache_page, ptl); goto out_put_page; } entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, haddr, ptep); out_put_page: if (page != pagecache_page) unlock_page(page); put_page(page); out_ptl: spin_unlock(ptl); if (pagecache_page) { unlock_page(pagecache_page); put_page(pagecache_page); } out_mutex: mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and * the page is not used after unlocked before returning from the current * page fault. So we are safe from accessing freed page, even if we wait * here without taking refcount. */ if (need_wait_lock) wait_on_page_locked(page); return ret; } /* * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with * modifications for huge pages. */ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep) { struct address_space *mapping; pgoff_t idx; unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; struct hstate *h = hstate_vma(dst_vma); pte_t _dst_pte; spinlock_t *ptl; int ret; struct page *page; if (!*pagep) { /* If a page already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } page = alloc_huge_page(dst_vma, dst_addr, 0); if (IS_ERR(page)) { ret = -ENOMEM; goto out; } ret = copy_huge_page_from_user(page, (const void __user *) src_addr, pages_per_huge_page(h), false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; *pagep = page; /* don't free the page */ goto out; } } else { page = *pagep; *pagep = NULL; } /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); mapping = dst_vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, dst_vma, dst_addr); /* * If shared, add to page cache */ if (vm_shared) { size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * huge_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = huge_add_to_page_cache(page, mapping, idx); if (ret) goto out_release_nounlock; } ptl = huge_pte_lockptr(h, dst_mm, dst_pte); spin_lock(ptl); /* * Recheck the i_size after holding PT lock to make sure not * to leave any page mapped (as page_mapped()) beyond the end * of the i_size (remove_inode_hugepages() is strict about * enforcing that). If we bail out here, we'll also leave a * page in the radix tree in the vm_shared case beyond the end * of the i_size, but remove_inode_hugepages() will take care * of it as soon as we drop the hugetlb_fault_mutex_table. */ size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) goto out_release_unlock; ret = -EEXIST; if (!huge_pte_none(huge_ptep_get(dst_pte))) goto out_release_unlock; if (vm_shared) { page_dup_rmap(page, true); } else { ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } _dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, dst_vma->vm_flags & VM_WRITE); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); set_page_huge_active(page); if (vm_shared) unlock_page(page); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared) unlock_page(page); out_release_nounlock: put_page(page); goto out; } long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, long i, unsigned int flags, int *locked) { unsigned long pfn_offset; unsigned long vaddr = *position; unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); int err = -EFAULT; while (vaddr < vma->vm_end && remainder) { pte_t *pte; spinlock_t *ptl = NULL; int absent; struct page *page; /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { remainder = 0; break; } /* * Some archs (sparc64, sh*) have multiple pte_ts to * each hugepage. We have to make sure we get the * first, for the page indexing below to work. * * Note that page table lock is not held when pte is null. */ pte = huge_pte_offset(mm, vaddr & huge_page_mask(h), huge_page_size(h)); if (pte) ptl = huge_pte_lock(h, mm, pte); absent = !pte || huge_pte_none(huge_ptep_get(pte)); /* * When coredumping, it suits get_dump_page if we just return * an error where there's an empty slot with no huge pagecache * to back it. This way, we avoid allocating a hugepage, and * the sparse dumpfile avoids allocating disk blocks, but its * huge holes still show up with zeroes where they need to be. */ if (absent && (flags & FOLL_DUMP) && !hugetlbfs_pagecache_present(h, vma, vaddr)) { if (pte) spin_unlock(ptl); remainder = 0; break; } /* * We need call hugetlb_fault for both hugepages under migration * (in which case hugetlb_fault waits for the migration,) and * hwpoisoned hugepages (in which case we need to prevent the * caller from accessing to them.) In order to do this, we use * here is_swap_pte instead of is_hugetlb_entry_migration and * is_hugetlb_entry_hwpoisoned. This is because it simply covers * both cases, and because we can't follow correct pages * directly from any kind of swap entries. */ if (absent || is_swap_pte(huge_ptep_get(pte)) || ((flags & FOLL_WRITE) && !huge_pte_write(huge_ptep_get(pte)))) { vm_fault_t ret; unsigned int fault_flags = 0; if (pte) spin_unlock(ptl); if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (locked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } ret = hugetlb_fault(mm, vma, vaddr, fault_flags); if (ret & VM_FAULT_ERROR) { err = vm_fault_to_errno(ret, flags); remainder = 0; break; } if (ret & VM_FAULT_RETRY) { if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; *nr_pages = 0; /* * VM_FAULT_RETRY must not return an * error, it will return zero * instead. * * No need to update "position" as the * caller will not check it after * *nr_pages is set to 0. */ return i; } continue; } pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); /* * If subpage information not requested, update counters * and skip the same_page loop below. */ if (!pages && !vmas && !pfn_offset && (vaddr + huge_page_size(h) < vma->vm_end) && (remainder >= pages_per_huge_page(h))) { vaddr += huge_page_size(h); remainder -= pages_per_huge_page(h); i += pages_per_huge_page(h); spin_unlock(ptl); continue; } same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); /* * try_grab_page() should always succeed here, because: * a) we hold the ptl lock, and b) we've just checked * that the huge page is present in the page tables. If * the huge page is present, then the tail pages must * also be present. The ptl prevents the head page and * tail pages from being rearranged in any way. So this * page must be available at this point, unless the page * refcount overflowed: */ if (WARN_ON_ONCE(!try_grab_page(pages[i], flags))) { spin_unlock(ptl); remainder = 0; err = -ENOMEM; break; } } if (vmas) vmas[i] = vma; vaddr += PAGE_SIZE; ++pfn_offset; --remainder; ++i; if (vaddr < vma->vm_end && remainder && pfn_offset < pages_per_huge_page(h)) { /* * We use pfn_offset to avoid touching the pageframes * of this compound page. */ goto same_page; } spin_unlock(ptl); } *nr_pages = remainder; /* * setting position is actually required only if remainder is * not zero but it's faster not to add a "if (remainder)" * branch. */ *position = vaddr; return i ? i : err; } #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); unsigned long pages = 0; struct mmu_notifier_range range; struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, vma, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); tlb_gather_mmu_vma(&tlb, vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; ptep = huge_pte_offset(mm, address, huge_page_size(h)); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(&tlb, vma, &address, ptep)) { pages++; spin_unlock(ptl); continue; } pte = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { spin_unlock(ptl); continue; } if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); if (is_write_migration_entry(entry)) { pte_t newpte; make_migration_entry_read(&entry); newpte = swp_entry_to_pte(entry); set_huge_swap_pte_at(mm, address, ptep, newpte, huge_page_size(h)); pages++; } spin_unlock(ptl); continue; } if (!huge_pte_none(pte)) { pte_t old_pte; old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } spin_unlock(ptl); cond_resched(); } tlb_flush_mmu_tlbonly(&tlb); huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. * * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, range.start, range.end); return pages << h->order; } /* Return true if reservation was successful, false otherwise. */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return false; } /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return true; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) return false; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_huge_page. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || sbase < svma->vm_start || svma->vm_end < s_end) return 0; return saddr; } static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) { unsigned long base = addr & PUD_MASK; unsigned long end = base + PUD_SIZE; /* * check on proper vm_flags and page table alignment */ if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma need span at least one aligned PUD size and the start,end range * must at least partialy within it. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. * * This routine must be called with i_mmap_rwsem held in at least read mode if * sharing is possible. For hugetlbfs, this prevents removal of any page * table entries associated with the address space. This is important as we * are setting up sharing based on existing page table entries (mappings). * * NOTE: This routine is only called from huge_pte_alloc. Some callers of * huge_pte_alloc know that sharing is not possible and do not take * i_mmap_rwsem as a performance optimization. This is handled by the * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is * only required for subsequent processing. */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; spinlock_t *ptl; if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_assert_locked(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr, vma_mmu_pagesize(svma)); if (spte) { atomic_inc(&virt_to_page(spte)->pt_share_count); break; } } } if (!spte) goto out; ptl = huge_pte_lock(hstate_vma(vma), mm, spte); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { atomic_dec(&virt_to_page(spte)->pt_share_count); } spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); return pte; } /** * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users * @tlb: the current mmu_gather. * @vma: the vma covering the pmd table. * @addr: pointer to the address we are trying to unshare. * @ptep: pointer into the (pmd) page table. * * Called with the page table lock held, the i_mmap_rwsem held in write mode * and the hugetlb vma lock held in write mode. * * Note: The caller must call huge_pmd_unshare_flush() before dropping the * i_mmap_rwsem. * * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it * was not a shared PMD table. */ int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long *addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, *addr); p4d_t *p4d = p4d_offset(pgd, *addr); pud_t *pud = pud_offset(p4d, *addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); if (sz != PMD_SIZE) return 0; if (!atomic_read(&virt_to_page(ptep)->pt_share_count)) return 0; pud_clear(pud); tlb_unshare_pmd_ptdesc(tlb, virt_to_page(ptep), *addr); mm_dec_nr_pmds(mm); /* * This update of passed address optimizes loops sequentially * processing addresses in increments of huge page size (PMD_SIZE * in this case). By clearing the pud, a PUD_SIZE area is unmapped. * Update address to the 'last page' in the cleared area so that * calling loop can move to first page past this area. */ *addr |= PUD_SIZE - PMD_SIZE; return 1; } /* * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls * @tlb: the current mmu_gather. * @vma: the vma covering the pmd table. * * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table * unsharing with concurrent page table walkers. * * This function must be called after a sequence of huge_pmd_unshare() * calls while still holding the i_mmap_rwsem. */ void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * We must synchronize page table unsharing such that nobody will * try reusing a previously-shared page table while it might still * be in use by previous sharers (TLB, GUP_fast). */ i_mmap_assert_write_locked(vma->vm_file->f_mapping); tlb_flush_unshared_tables(tlb); } #define want_pmd_share() (1) #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long *addr, pte_t *ptep) { return 0; } void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) { } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share() && pud_none(*pud)) pte = huge_pmd_share(mm, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } BUG_ON(pte && pte_present(*pte) && !pte_huge(*pte)); return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /* * These functions are overwritable if your architecture needs its own * behavior. */ struct page * __weak follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { return ERR_PTR(-EINVAL); } struct page * __weak follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift) { WARN(1, "hugepd follow called with no support for hugepage directory format\n"); return NULL; } struct page * __weak follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; struct page *page = NULL; spinlock_t *ptl; pte_t *ptep, pte; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return NULL; retry: ptep = huge_pte_offset(mm, address, huge_page_size(h)); if (!ptep) return NULL; ptl = huge_pte_lock(h, mm, ptep); pte = huge_ptep_get(ptep); if (pte_present(pte)) { page = pte_page(pte) + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); /* * try_grab_page() should always succeed here, because: a) we * hold the pmd (ptl) lock, and b) we've just checked that the * huge pmd (head) page is present in the page tables. The ptl * prevents the head page and tail pages from being rearranged * in any way. So this page must be available at this point, * unless the page refcount overflowed: */ if (WARN_ON_ONCE(!try_grab_page(page, flags))) { page = NULL; goto out; } } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); __migration_entry_wait(mm, ptep, ptl); goto retry; } /* * hwpoisoned entry is treated as no_page_table in * follow_page_mask(). */ } out: spin_unlock(ptl); return page; } struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags) { if (flags & (FOLL_GET | FOLL_PIN)) return NULL; return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); } struct page * __weak follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags) { if (flags & (FOLL_GET | FOLL_PIN)) return NULL; return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); } int isolate_hugetlb(struct page *page, struct list_head *list) { int ret = 0; spin_lock(&hugetlb_lock); if (!PageHeadHuge(page) || !page_huge_active(page) || !get_page_unless_zero(page)) { ret = -EBUSY; goto unlock; } clear_page_huge_active(page); list_move_tail(&page->lru, list); unlock: spin_unlock(&hugetlb_lock); return ret; } void putback_active_hugepage(struct page *page) { VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); set_page_huge_active(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); spin_unlock(&hugetlb_lock); put_page(page); } void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) { struct hstate *h = page_hstate(oldpage); hugetlb_cgroup_migrate(oldpage, newpage); set_page_owner_migrate_reason(newpage, reason); /* * transfer temporary state of the new huge page. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (PageHugeTemporary(newpage)) { int old_nid = page_to_nid(oldpage); int new_nid = page_to_nid(newpage); SetPageHugeTemporary(oldpage); ClearPageHugeTemporary(newpage); spin_lock(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock(&hugetlb_lock); } } /* * If @take_locks is false, the caller must ensure that no concurrent page table * access can happen (except for gup_fast() and hardware page walks). * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like * concurrent page fault handling) and the file rmap lock. */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); tlb_gather_mmu_vma(&tlb, vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, start, end); mmu_notifier_invalidate_range_start(&range); if (take_locks) { i_mmap_lock_write(vma->vm_file->f_mapping); } else { i_mmap_assert_write_locked(vma->vm_file->f_mapping); } for (address = start; address < end; address += PUD_SIZE) { unsigned long tmp = address; ptep = huge_pte_offset(mm, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); /* We don't want 'address' to be changed */ huge_pmd_unshare(&tlb, vma, &tmp, ptep); spin_unlock(ptl); } huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); } /* * No need to call mmu_notifier_invalidate_range(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, start, end); } #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { hugetlb_cma_size = memparse(p, &p); return 0; } early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; int nid; cma_reserve_called = true; if (!hugetlb_cma_size) return; if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); return; } /* * If 3 GB area is requested on a machine with 4 numa nodes, * let's allocate 1 GB on first three nodes and ignore the last one. */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); reserved = 0; for_each_node_state(nid, N_ONLINE) { int res; char name[CMA_MAX_NAME]; size = min(per_node, hugetlb_cma_size - reserved); size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, 0, false, name, &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); continue; } reserved += size; pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", size / SZ_1M, nid); if (reserved >= hugetlb_cma_size) break; } } void __init hugetlb_cma_check(void) { if (!hugetlb_cma_size || cma_reserve_called) return; pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); } #endif /* CONFIG_CMA */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/mempool.c * * memory buffer pool support. Such pools are mostly used * for guaranteed, deadlock-free memory allocations during * extreme VM load. * * started by Ingo Molnar, Copyright (C) 2001 * debugging by David Rientjes, Copyright (C) 2015 */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/kasan.h> #include <linux/kmemleak.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/blkdev.h> #include <linux/writeback.h> #include "slab.h" #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON) static void poison_error(mempool_t *pool, void *element, size_t size, size_t byte) { const int nr = pool->curr_nr; const int start = max_t(int, byte - (BITS_PER_LONG / 8), 0); const int end = min_t(int, byte + (BITS_PER_LONG / 8), size); int i; pr_err("BUG: mempool element poison mismatch\n"); pr_err("Mempool %p size %zu\n", pool, size); pr_err(" nr=%d @ %p: %s0x", nr, element, start > 0 ? "... " : ""); for (i = start; i < end; i++) pr_cont("%x ", *(u8 *)(element + i)); pr_cont("%s\n", end < size ? "..." : ""); dump_stack(); } static void __check_element(mempool_t *pool, void *element, size_t size) { u8 *obj = element; size_t i; for (i = 0; i < size; i++) { u8 exp = (i < size - 1) ? POISON_FREE : POISON_END; if (obj[i] != exp) { poison_error(pool, element, size, i); return; } } memset(obj, POISON_INUSE, size); } static void check_element(mempool_t *pool, void *element) { /* Mempools backed by slab allocator */ if (pool->free == mempool_free_slab || pool->free == mempool_kfree) { __check_element(pool, element, ksize(element)); } else if (pool->free == mempool_free_pages) { /* Mempools backed by page allocator */ int order = (int)(long)pool->pool_data; void *addr = kmap_atomic((struct page *)element); __check_element(pool, addr, 1UL << (PAGE_SHIFT + order)); kunmap_atomic(addr); } } static void __poison_element(void *element, size_t size) { u8 *obj = element; memset(obj, POISON_FREE, size - 1); obj[size - 1] = POISON_END; } static void poison_element(mempool_t *pool, void *element) { /* Mempools backed by slab allocator */ if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) { __poison_element(element, ksize(element)); } else if (pool->alloc == mempool_alloc_pages) { /* Mempools backed by page allocator */ int order = (int)(long)pool->pool_data; void *addr = kmap_atomic((struct page *)element); __poison_element(addr, 1UL << (PAGE_SHIFT + order)); kunmap_atomic(addr); } } #else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ static inline void check_element(mempool_t *pool, void *element) { } static inline void poison_element(mempool_t *pool, void *element) { } #endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ static __always_inline void kasan_poison_element(mempool_t *pool, void *element) { if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) kasan_poison_kfree(element, _RET_IP_); else if (pool->alloc == mempool_alloc_pages) kasan_free_pages(element, (unsigned long)pool->pool_data); } static void kasan_unpoison_element(mempool_t *pool, void *element) { if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) kasan_unpoison_slab(element); else if (pool->alloc == mempool_alloc_pages) kasan_alloc_pages(element, (unsigned long)pool->pool_data); } static __always_inline void add_element(mempool_t *pool, void *element) { BUG_ON(pool->curr_nr >= pool->min_nr); poison_element(pool, element); kasan_poison_element(pool, element); pool->elements[pool->curr_nr++] = element; } static void *remove_element(mempool_t *pool) { void *element = pool->elements[--pool->curr_nr]; BUG_ON(pool->curr_nr < 0); kasan_unpoison_element(pool, element); check_element(pool, element); return element; } /** * mempool_exit - exit a mempool initialized with mempool_init() * @pool: pointer to the memory pool which was initialized with * mempool_init(). * * Free all reserved elements in @pool and @pool itself. This function * only sleeps if the free_fn() function sleeps. * * May be called on a zeroed but uninitialized mempool (i.e. allocated with * kzalloc()). */ void mempool_exit(mempool_t *pool) { while (pool->curr_nr) { void *element = remove_element(pool); pool->free(element, pool->pool_data); } kfree(pool->elements); pool->elements = NULL; } EXPORT_SYMBOL(mempool_exit); /** * mempool_destroy - deallocate a memory pool * @pool: pointer to the memory pool which was allocated via * mempool_create(). * * Free all reserved elements in @pool and @pool itself. This function * only sleeps if the free_fn() function sleeps. */ void mempool_destroy(mempool_t *pool) { if (unlikely(!pool)) return; mempool_exit(pool); kfree(pool); } EXPORT_SYMBOL(mempool_destroy); int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id) { spin_lock_init(&pool->lock); pool->min_nr = min_nr; pool->pool_data = pool_data; pool->alloc = alloc_fn; pool->free = free_fn; init_waitqueue_head(&pool->wait); pool->elements = kmalloc_array_node(min_nr, sizeof(void *), gfp_mask, node_id); if (!pool->elements) return -ENOMEM; /* * First pre-allocate the guaranteed number of buffers. */ while (pool->curr_nr < pool->min_nr) { void *element; element = pool->alloc(gfp_mask, pool->pool_data); if (unlikely(!element)) { mempool_exit(pool); return -ENOMEM; } add_element(pool, element); } return 0; } EXPORT_SYMBOL(mempool_init_node); /** * mempool_init - initialize a memory pool * @pool: pointer to the memory pool that should be initialized * @min_nr: the minimum number of elements guaranteed to be * allocated for this pool. * @alloc_fn: user-defined element-allocation function. * @free_fn: user-defined element-freeing function. * @pool_data: optional private data available to the user-defined functions. * * Like mempool_create(), but initializes the pool in (i.e. embedded in another * structure). * * Return: %0 on success, negative error code otherwise. */ int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data) { return mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data, GFP_KERNEL, NUMA_NO_NODE); } EXPORT_SYMBOL(mempool_init); /** * mempool_create - create a memory pool * @min_nr: the minimum number of elements guaranteed to be * allocated for this pool. * @alloc_fn: user-defined element-allocation function. * @free_fn: user-defined element-freeing function. * @pool_data: optional private data available to the user-defined functions. * * this function creates and allocates a guaranteed size, preallocated * memory pool. The pool can be used from the mempool_alloc() and mempool_free() * functions. This function might sleep. Both the alloc_fn() and the free_fn() * functions might sleep - as long as the mempool_alloc() function is not called * from IRQ contexts. * * Return: pointer to the created memory pool object or %NULL on error. */ mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data) { return mempool_create_node(min_nr,alloc_fn,free_fn, pool_data, GFP_KERNEL, NUMA_NO_NODE); } EXPORT_SYMBOL(mempool_create); mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id) { mempool_t *pool; pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); if (!pool) return NULL; if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data, gfp_mask, node_id)) { kfree(pool); return NULL; } return pool; } EXPORT_SYMBOL(mempool_create_node); /** * mempool_resize - resize an existing memory pool * @pool: pointer to the memory pool which was allocated via * mempool_create(). * @new_min_nr: the new minimum number of elements guaranteed to be * allocated for this pool. * * This function shrinks/grows the pool. In the case of growing, * it cannot be guaranteed that the pool will be grown to the new * size immediately, but new mempool_free() calls will refill it. * This function may sleep. * * Note, the caller must guarantee that no mempool_destroy is called * while this function is running. mempool_alloc() & mempool_free() * might be called (eg. from IRQ contexts) while this function executes. * * Return: %0 on success, negative error code otherwise. */ int mempool_resize(mempool_t *pool, int new_min_nr) { void *element; void **new_elements; unsigned long flags; BUG_ON(new_min_nr <= 0); might_sleep(); spin_lock_irqsave(&pool->lock, flags); if (new_min_nr <= pool->min_nr) { while (new_min_nr < pool->curr_nr) { element = remove_element(pool); spin_unlock_irqrestore(&pool->lock, flags); pool->free(element, pool->pool_data); spin_lock_irqsave(&pool->lock, flags); } pool->min_nr = new_min_nr; goto out_unlock; } spin_unlock_irqrestore(&pool->lock, flags); /* Grow the pool */ new_elements = kmalloc_array(new_min_nr, sizeof(*new_elements), GFP_KERNEL); if (!new_elements) return -ENOMEM; spin_lock_irqsave(&pool->lock, flags); if (unlikely(new_min_nr <= pool->min_nr)) { /* Raced, other resize will do our work */ spin_unlock_irqrestore(&pool->lock, flags); kfree(new_elements); goto out; } memcpy(new_elements, pool->elements, pool->curr_nr * sizeof(*new_elements)); kfree(pool->elements); pool->elements = new_elements; pool->min_nr = new_min_nr; while (pool->curr_nr < pool->min_nr) { spin_unlock_irqrestore(&pool->lock, flags); element = pool->alloc(GFP_KERNEL, pool->pool_data); if (!element) goto out; spin_lock_irqsave(&pool->lock, flags); if (pool->curr_nr < pool->min_nr) { add_element(pool, element); } else { spin_unlock_irqrestore(&pool->lock, flags); pool->free(element, pool->pool_data); /* Raced */ goto out; } } out_unlock: spin_unlock_irqrestore(&pool->lock, flags); out: return 0; } EXPORT_SYMBOL(mempool_resize); /** * mempool_alloc - allocate an element from a specific memory pool * @pool: pointer to the memory pool which was allocated via * mempool_create(). * @gfp_mask: the usual allocation bitmask. * * this function only sleeps if the alloc_fn() function sleeps or * returns NULL. Note that due to preallocation, this function * *never* fails when called from process contexts. (it might * fail if called from an IRQ context.) * Note: using __GFP_ZERO is not supported. * * Return: pointer to the allocated element or %NULL on error. */ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) { void *element; unsigned long flags; wait_queue_entry_t wait; gfp_t gfp_temp; VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ gfp_mask |= __GFP_NOWARN; /* failures are OK */ gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO); repeat_alloc: element = pool->alloc(gfp_temp, pool->pool_data); if (likely(element != NULL)) return element; spin_lock_irqsave(&pool->lock, flags); if (likely(pool->curr_nr)) { element = remove_element(pool); spin_unlock_irqrestore(&pool->lock, flags); /* paired with rmb in mempool_free(), read comment there */ smp_wmb(); /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(element); return element; } /* * We use gfp mask w/o direct reclaim or IO for the first round. If * alloc failed with that and @pool was empty, retry immediately. */ if (gfp_temp != gfp_mask) { spin_unlock_irqrestore(&pool->lock, flags); gfp_temp = gfp_mask; goto repeat_alloc; } /* We must not sleep if !__GFP_DIRECT_RECLAIM */ if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { spin_unlock_irqrestore(&pool->lock, flags); return NULL; } /* Let's wait for someone else to return an element to @pool */ init_wait(&wait); prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_irqrestore(&pool->lock, flags); /* * FIXME: this should be io_schedule(). The timeout is there as a * workaround for some DM problems in 2.6.18. */ io_schedule_timeout(5*HZ); finish_wait(&pool->wait, &wait); goto repeat_alloc; } EXPORT_SYMBOL(mempool_alloc); /** * mempool_free - return an element to the pool. * @element: pool element pointer. * @pool: pointer to the memory pool which was allocated via * mempool_create(). * * this function only sleeps if the free_fn() function sleeps. */ void mempool_free(void *element, mempool_t *pool) { unsigned long flags; if (unlikely(element == NULL)) return; /* * Paired with the wmb in mempool_alloc(). The preceding read is * for @element and the following @pool->curr_nr. This ensures * that the visible value of @pool->curr_nr is from after the * allocation of @element. This is necessary for fringe cases * where @element was passed to this task without going through * barriers. * * For example, assume @p is %NULL at the beginning and one task * performs "p = mempool_alloc(...);" while another task is doing * "while (!p) cpu_relax(); mempool_free(p, ...);". This function * may end up using curr_nr value which is from before allocation * of @p without the following rmb. */ smp_rmb(); /* * For correctness, we need a test which is guaranteed to trigger * if curr_nr + #allocated == min_nr. Testing curr_nr < min_nr * without locking achieves that and refilling as soon as possible * is desirable. * * Because curr_nr visible here is always a value after the * allocation of @element, any task which decremented curr_nr below * min_nr is guaranteed to see curr_nr < min_nr unless curr_nr gets * incremented to min_nr afterwards. If curr_nr gets incremented * to min_nr after the allocation of @element, the elements * allocated after that are subject to the same guarantee. * * Waiters happen iff curr_nr is 0 and the above guarantee also * ensures that there will be frees which return elements to the * pool waking up the waiters. */ if (unlikely(READ_ONCE(pool->curr_nr) < pool->min_nr)) { spin_lock_irqsave(&pool->lock, flags); if (likely(pool->curr_nr < pool->min_nr)) { add_element(pool, element); spin_unlock_irqrestore(&pool->lock, flags); wake_up(&pool->wait); return; } spin_unlock_irqrestore(&pool->lock, flags); } pool->free(element, pool->pool_data); } EXPORT_SYMBOL(mempool_free); /* * A commonly used alloc and free fn. */ void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data) { struct kmem_cache *mem = pool_data; VM_BUG_ON(mem->ctor); return kmem_cache_alloc(mem, gfp_mask); } EXPORT_SYMBOL(mempool_alloc_slab); void mempool_free_slab(void *element, void *pool_data) { struct kmem_cache *mem = pool_data; kmem_cache_free(mem, element); } EXPORT_SYMBOL(mempool_free_slab); /* * A commonly used alloc and free fn that kmalloc/kfrees the amount of memory * specified by pool_data */ void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data) { size_t size = (size_t)pool_data; return kmalloc(size, gfp_mask); } EXPORT_SYMBOL(mempool_kmalloc); void mempool_kfree(void *element, void *pool_data) { kfree(element); } EXPORT_SYMBOL(mempool_kfree); /* * A simple mempool-backed page allocator that allocates pages * of the order specified by pool_data. */ void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data) { int order = (int)(long)pool_data; return alloc_pages(gfp_mask, order); } EXPORT_SYMBOL(mempool_alloc_pages); void mempool_free_pages(void *element, void *pool_data) { int order = (int)(long)pool_data; __free_pages(element, order); } EXPORT_SYMBOL(mempool_free_pages); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr), TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to segment and merge handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/scatterlist.h> #include <linux/blk-cgroup.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) { struct bio_vec pb, nb; if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; /* * Don't merge if the 1st bio starts with non-zero offset, otherwise it * is quite difficult to respect the sg gap limit. We work hard to * merge a huge number of small single bios in case of mkfs. */ if (prev_rq) bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); if (pb.bv_offset & queue_virt_boundary(q)) return true; /* * We don't need to worry about the situation that the merged segment * ends in unaligned virt boundary: * * - if 'pb' ends aligned, the merged segment ends aligned * - if 'pb' ends unaligned, the next bio must include * one single bvec of 'nb', otherwise the 'nb' can't * merge with 'pb' */ bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); if (biovec_phys_mergeable(q, &pb, &nb)) return false; return __bvec_gap_to_prev(q, &pb, nb.bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, req, req->biotail, bio); } static inline bool req_gap_front_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, NULL, bio, req->bio); } static struct bio *blk_bio_discard_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { unsigned int max_discard_sectors, granularity; int alignment; sector_t tmp; unsigned split_sectors; *nsegs = 1; /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); max_discard_sectors = min(q->limits.max_discard_sectors, bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { /* XXX: warn */ return NULL; } if (bio_sectors(bio) <= max_discard_sectors) return NULL; split_sectors = max_discard_sectors; /* * If the next starting sector would be misaligned, stop the discard at * the previous aligned sector. */ alignment = (q->limits.discard_alignment >> 9) % granularity; tmp = bio->bi_iter.bi_sector + split_sectors - alignment; tmp = sector_div(tmp, granularity); if (split_sectors > tmp) split_sectors -= tmp; return bio_split(bio, split_sectors, GFP_NOIO, bs); } static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { *nsegs = 0; if (!q->limits.max_write_zeroes_sectors) return NULL; if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors) return NULL; return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs); } static struct bio *blk_bio_write_same_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { *nsegs = 1; if (!q->limits.max_write_same_sectors) return NULL; if (bio_sectors(bio) <= q->limits.max_write_same_sectors) return NULL; return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } /* * Return the maximum number of sectors from the start of a bio that may be * submitted as a single request to a block device. If enough sectors remain, * align the end to the physical block size. Otherwise align the end to the * logical block size. This approach minimizes the number of non-aligned * requests that are submitted to a block device if the start of a bio is not * aligned to a physical block boundary. */ static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); unsigned max_sectors = sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1); max_sectors += start_offset; max_sectors &= ~(pbs - 1); if (max_sectors > start_offset) return max_sectors - start_offset; return sectors & ~(lbs - 1); } static inline unsigned get_max_segment_size(const struct request_queue *q, struct page *start_page, unsigned long offset) { unsigned long mask = queue_segment_boundary(q); offset = mask & (page_to_phys(start_page) + offset); /* * overflow may be triggered in case of zero page physical address * on 32bit arch, use queue's max segment size when that happens. */ return min_not_zero(mask - offset + 1, (unsigned long)queue_max_segment_size(q)); } /** * bvec_split_segs - verify whether or not a bvec should be split in the middle * @q: [in] request queue associated with the bio associated with @bv * @bv: [in] bvec to examine * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that * bio without exceeding @max_segs * @sectors: [in,out] Number of sectors in the bio being built. Incremented * by the number of sectors from @bv that may be appended to that * bio without exceeding @max_sectors * @max_segs: [in] upper bound for *@nsegs * @max_sectors: [in] upper bound for *@sectors * * When splitting a bio, it can happen that a bvec is encountered that is too * big to fit in a single segment and hence that it has to be split in the * middle. This function verifies whether or not that should happen. The value * %true is returned if and only if appending the entire @bv to a bio with * *@nsegs segments and *@sectors sectors would make that bio unacceptable for * the block driver. */ static bool bvec_split_segs(const struct request_queue *q, const struct bio_vec *bv, unsigned *nsegs, unsigned *sectors, unsigned max_segs, unsigned max_sectors) { unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9; unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; unsigned seg_size = 0; while (len && *nsegs < max_segs) { seg_size = get_max_segment_size(q, bv->bv_page, bv->bv_offset + total_len); seg_size = min(seg_size, len); (*nsegs)++; total_len += seg_size; len -= seg_size; if ((bv->bv_offset + total_len) & queue_virt_boundary(q)) break; } *sectors += total_len >> 9; /* tell the caller to split the bvec if it is too big to fit */ return len > 0 || bv->bv_len > max_len; } /** * blk_bio_segment_split - split a bio in two bios * @q: [in] request queue pointer * @bio: [in] bio to be split * @bs: [in] bio set to allocate the clone from * @segs: [out] number of segments in the bio with the first half of the sectors * * Clone @bio, update the bi_iter of the clone to represent the first sectors * of @bio and update @bio->bi_iter to represent the remaining sectors. The * following is guaranteed for the cloned bio: * - That it has at most get_max_io_size(@q, @bio) sectors. * - That it has at most queue_max_segments(@q) segments. * * Except for discard requests the cloned bio will point at the bi_io_vec of * the original bio. It is the responsibility of the caller to ensure that the * original bio is not freed before the cloned bio. The caller is also * responsible for ensuring that @bs is only destroyed after processing of the * split bio has finished. */ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *segs) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; unsigned nsegs = 0, sectors = 0; const unsigned max_sectors = get_max_io_size(q, bio); const unsigned max_segs = queue_max_segments(q); bio_for_each_bvec(bv, bio, iter) { /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; if (nsegs < max_segs && sectors + (bv.bv_len >> 9) <= max_sectors && bv.bv_offset + bv.bv_len <= PAGE_SIZE) { nsegs++; sectors += bv.bv_len >> 9; } else if (bvec_split_segs(q, &bv, &nsegs, §ors, max_segs, max_sectors)) { goto split; } bvprv = bv; bvprvp = &bvprv; } *segs = nsegs; return NULL; split: *segs = nsegs; return bio_split(bio, sectors, GFP_NOIO, bs); } /** * __blk_queue_split - split a bio and submit the second half * @bio: [in, out] bio to be split * @nr_segs: [out] number of segments in the first bio * * Split a bio into two bios, chain the two bios, submit the second half and * store a pointer to the first half in *@bio. If the second bio is still too * big it will be split by a recursive call to this function. Since this * function may allocate a new bio from @bio->bi_disk->queue->bio_split, it is * the responsibility of the caller to ensure that * @bio->bi_disk->queue->bio_split is only released after processing of the * split bio has finished. */ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs) { struct request_queue *q = (*bio)->bi_disk->queue; struct bio *split = NULL; switch (bio_op(*bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs); break; case REQ_OP_WRITE_ZEROES: split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, nr_segs); break; case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, &q->bio_split, nr_segs); break; default: /* * All drivers must accept single-segments bios that are <= * PAGE_SIZE. This is a quick and dirty check that relies on * the fact that bi_io_vec[0] is always valid if a bio has data. * The check might lead to occasional false negatives when bios * are cloned, but compared to the performance impact of cloned * bios themselves the loop below doesn't matter anyway. */ if (!q->limits.chunk_sectors && (*bio)->bi_vcnt == 1 && ((*bio)->bi_io_vec[0].bv_len + (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) { *nr_segs = 1; break; } split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs); break; } if (split) { /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); submit_bio_noacct(*bio); *bio = split; blk_throtl_charge_bio_split(*bio); } } /** * blk_queue_split - split a bio and submit the second half * @bio: [in, out] bio to be split * * Split a bio into two bios, chains the two bios, submit the second half and * store a pointer to the first half in *@bio. Since this function may allocate * a new bio from @bio->bi_disk->queue->bio_split, it is the responsibility of * the caller to ensure that @bio->bi_disk->queue->bio_split is only released * after processing of the split bio has finished. */ void blk_queue_split(struct bio **bio) { unsigned int nr_segs; __blk_queue_split(bio, &nr_segs); } EXPORT_SYMBOL(blk_queue_split); unsigned int blk_recalc_rq_segments(struct request *rq) { unsigned int nr_phys_segs = 0; unsigned int nr_sectors = 0; struct req_iterator iter; struct bio_vec bv; if (!rq->bio) return 0; switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: if (queue_max_discard_segments(rq->q) > 1) { struct bio *bio = rq->bio; for_each_bio(bio) nr_phys_segs++; return nr_phys_segs; } return 1; case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: return 1; } rq_for_each_bvec(bv, rq, iter) bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors, UINT_MAX, UINT_MAX); return nr_phys_segs; } static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) { if (!*sg) return sglist; /* * If the driver previously mapped a shorter list, we could see a * termination bit prematurely unless it fully inits the sg table * on each mapping. We KNOW that there must be more entries here * or the driver would be buggy, so force clear the termination bit * to avoid doing a full sg_init_table() in drivers for each command. */ sg_unmark_end(*sg); return sg_next(*sg); } static unsigned blk_bvec_map_sg(struct request_queue *q, struct bio_vec *bvec, struct scatterlist *sglist, struct scatterlist **sg) { unsigned nbytes = bvec->bv_len; unsigned nsegs = 0, total = 0; while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; unsigned len = min(get_max_segment_size(q, bvec->bv_page, offset), nbytes); struct page *page = bvec->bv_page; /* * Unfortunately a fair number of drivers barf on scatterlists * that have an offset larger than PAGE_SIZE, despite other * subsystems dealing with that invariant just fine. For now * stick to the legacy format where we never present those from * the block layer, but the code below should be removed once * these offenders (mostly MMC/SD drivers) are fixed. */ page += (offset >> PAGE_SHIFT); offset &= ~PAGE_MASK; *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, page, len, offset); total += len; nbytes -= len; nsegs++; } return nsegs; } static inline int __blk_bvec_map_sg(struct bio_vec bv, struct scatterlist *sglist, struct scatterlist **sg) { *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); return 1; } /* only try to merge bvecs into one sg if they are from two bios */ static inline bool __blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec, struct bio_vec *bvprv, struct scatterlist **sg) { int nbytes = bvec->bv_len; if (!*sg) return false; if ((*sg)->length + nbytes > queue_max_segment_size(q)) return false; if (!biovec_phys_mergeable(q, bvprv, bvec)) return false; (*sg)->length += nbytes; return true; } static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; int nsegs = 0; bool new_bio = false; for_each_bio(bio) { bio_for_each_bvec(bvec, bio, iter) { /* * Only try to merge bvecs from two bios given we * have done bio internal merge when adding pages * to bio */ if (new_bio && __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg)) goto next_bvec; if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE) nsegs += __blk_bvec_map_sg(bvec, sglist, sg); else nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg); next_bvec: new_bio = false; } if (likely(bio->bi_iter.bi_size)) { bvprv = bvec; new_bio = true; } } return nsegs; } /* * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg) { int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, last_sg); else if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); if (*last_sg) sg_mark_end(*last_sg); /* * Something must have been wrong if the figured number of * segment is bigger than number of req's physical segments */ WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); return nsegs; } EXPORT_SYMBOL(__blk_rq_map_sg); static inline unsigned int blk_rq_get_max_segments(struct request *rq) { if (req_op(rq) == REQ_OP_DISCARD) return queue_max_discard_segments(rq->q); return queue_max_segments(rq->q); } static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { if (!blk_cgroup_mergeable(req, bio)) goto no_merge; if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; /* discard request merge won't add new segment */ if (req_op(req) == REQ_OP_DISCARD) return 1; if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* * This will form the start of a new hw segment. Bump both * counters. */ req->nr_phys_segments += nr_phys_segs; return 1; no_merge: req_set_nomerge(req->q, req); return 0; } int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_back_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_back_merge(req, bio)) return 0; if (!bio_crypt_ctx_back_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_front_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_front_merge(req, bio)) return 0; if (!bio_crypt_ctx_front_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static bool req_attempt_discard_merge(struct request_queue *q, struct request *req, struct request *next) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(next->bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next); return true; no_merge: req_set_nomerge(q, req); return false; } static int ll_merge_requests_fn(struct request_queue *q, struct request *req, struct request *next) { int total_phys_segments; if (req_gap_back_merge(req, next->bio)) return 0; /* * Will it become too large? */ if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) return 0; total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; if (total_phys_segments > blk_rq_get_max_segments(req)) return 0; if (!blk_cgroup_mergeable(req, next->bio)) return 0; if (blk_integrity_merge_rq(q, req, next) == false) return 0; if (!bio_crypt_ctx_merge_rq(req, next)) return 0; /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; } /** * blk_rq_set_mixed_merge - mark a request as mixed merge * @rq: request to mark as mixed merge * * Description: * @rq is about to be mixed merged. Make sure the attributes * which can be mixed are set in each bio and mark @rq as mixed * merged. */ void blk_rq_set_mixed_merge(struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; if (rq->rq_flags & RQF_MIXED_MERGE) return; /* * @rq will no longer represent mixable attributes for all the * contained bios. It will just track those of the first one. * Distributes the attributs to each bio. */ for (bio = rq->bio; bio; bio = bio->bi_next) { WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) && (bio->bi_opf & REQ_FAILFAST_MASK) != ff); bio->bi_opf |= ff; } rq->rq_flags |= RQF_MIXED_MERGE; } static void blk_account_io_merge_request(struct request *req) { if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); hd_struct_put(req->part); } } static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { if (blk_discard_mergable(req)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) return ELEVATOR_BACK_MERGE; return ELEVATOR_NO_MERGE; } /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. */ static struct request *attempt_merge(struct request_queue *q, struct request *req, struct request *next) { if (!rq_mergeable(req) || !rq_mergeable(next)) return NULL; if (req_op(req) != req_op(next)) return NULL; if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk) return NULL; if (req_op(req) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(req->bio, next->bio)) return NULL; /* * Don't allow merge of different write hints, or for a hint with * non-hint IO. */ if (req->write_hint != next->write_hint) return NULL; if (req->ioprio != next->ioprio) return NULL; /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn * will have updated segment counts, update sector * counts here. Handle DISCARDs separately, as they * have separate settings. */ switch (blk_try_req_merge(req, next)) { case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; break; case ELEVATOR_BACK_MERGE: if (!ll_merge_requests_fn(q, req, next)) return NULL; break; default: return NULL; } /* * If failfast settings disagree or any of the two is already * a mixed merge, mark both as mixed before proceeding. This * makes sure that all involved bios have mixable attributes * set properly. */ if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) || (req->cmd_flags & REQ_FAILFAST_MASK) != (next->cmd_flags & REQ_FAILFAST_MASK)) { blk_rq_set_mixed_merge(req); blk_rq_set_mixed_merge(next); } /* * At this point we have either done a back merge or front merge. We * need the smaller start_time_ns of the merged requests to be the * current request for accounting purposes. */ if (next->start_time_ns < req->start_time_ns) req->start_time_ns = next->start_time_ns; req->biotail->bi_next = next->bio; req->biotail = next->biotail; req->__data_len += blk_rq_bytes(next); if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); blk_crypto_rq_put_keyslot(next); /* * 'next' is going away, so update stats accordingly */ blk_account_io_merge_request(next); trace_block_rq_merge(next); /* * ownership of bio passed from next to req, return 'next' for * the caller to free */ next->bio = NULL; return next; } static struct request *attempt_back_merge(struct request_queue *q, struct request *rq) { struct request *next = elv_latter_request(q, rq); if (next) return attempt_merge(q, rq, next); return NULL; } static struct request *attempt_front_merge(struct request_queue *q, struct request *rq) { struct request *prev = elv_former_request(q, rq); if (prev) return attempt_merge(q, prev, rq); return NULL; } int blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next) { struct request *free; free = attempt_merge(q, rq, next); if (free) { blk_put_request(free); return 1; } return 0; } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) { if (!rq_mergeable(rq) || !bio_mergeable(bio)) return false; if (req_op(rq) != bio_op(bio)) return false; /* different data direction or already started, don't merge */ if (bio_data_dir(bio) != rq_data_dir(rq)) return false; /* must be same device */ if (rq->rq_disk != bio->bi_disk) return false; /* don't merge across cgroup boundaries */ if (!blk_cgroup_mergeable(rq, bio)) return false; /* only merge integrity protected bio into ditto rq */ if (blk_integrity_merge_bio(rq->q, rq, bio) == false) return false; /* Only merge if the crypt contexts are compatible */ if (!bio_crypt_rq_ctx_compatible(rq, bio)) return false; /* must be using the same buffer */ if (req_op(rq) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(rq->bio, bio)) return false; /* * Don't allow merge of different write hints, or for a hint with * non-hint IO. */ if (rq->write_hint != bio->bi_write_hint) return false; if (rq->ioprio != bio_prio(bio)) return false; return true; } enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector) return ELEVATOR_FRONT_MERGE; return ELEVATOR_NO_MERGE; } static void blk_account_io_merge_bio(struct request *req) { if (!blk_do_io_stat(req)) return; part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); } enum bio_merge_status { BIO_MERGE_OK, BIO_MERGE_NONE, BIO_MERGE_FAILED, }; static enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_back_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_backmerge(req->q, req, bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_front_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_front_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_frontmerge(req->q, req, bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); bio->bi_next = req->bio; req->bio = bio; req->__sector = bio->bi_iter.bi_sector; req->__data_len += bio->bi_iter.bi_size; bio_crypt_do_front_merge(req, bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q, struct request *req, struct bio *bio) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; rq_qos_merge(q, req, bio); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; req->nr_phys_segments = segments + 1; blk_account_io_merge_bio(req); return BIO_MERGE_OK; no_merge: req_set_nomerge(q, req); return BIO_MERGE_FAILED; } static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q, struct request *rq, struct bio *bio, unsigned int nr_segs, bool sched_allow_merge) { if (!blk_rq_merge_ok(rq, bio)) return BIO_MERGE_NONE; switch (blk_try_merge(rq, bio)) { case ELEVATOR_BACK_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_back_merge(rq, bio, nr_segs); break; case ELEVATOR_FRONT_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_front_merge(rq, bio, nr_segs); break; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio); default: return BIO_MERGE_NONE; } return BIO_MERGE_FAILED; } /** * blk_attempt_plug_merge - try to merge with %current's plugged list * @q: request_queue new bio is being queued at * @bio: new bio being queued * @nr_segs: number of segments in @bio * @same_queue_rq: pointer to &struct request that gets filled in when * another request associated with @q is found on the plug list * (optional, may be %NULL) * * Determine whether @bio being queued on @q can be merged with a request * on %current's plugged list. Returns %true if merge was successful, * otherwise %false. * * Plugging coalesces IOs from the same issuer for the same purpose without * going through @q->queue_lock. As such it's more of an issuing mechanism * than scheduling, and the request, while may have elvpriv data, is not * added on the elevator at this point. In addition, we don't have * reliable access to the elevator outside queue lock. Only check basic * merging parameters without querying the elevator. * * Caller must ensure !blk_queue_nomerges(q) beforehand. */ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **same_queue_rq) { struct blk_plug *plug; struct request *rq; struct list_head *plug_list; plug = blk_mq_plug(q, bio); if (!plug) return false; plug_list = &plug->mq_list; list_for_each_entry_reverse(rq, plug_list, queuelist) { if (rq->q == q && same_queue_rq) { /* * Only blk-mq multiple hardware queues case checks the * rq in the same queue, there should be only one such * rq in a queue **/ *same_queue_rq = rq; } if (rq->q != q) continue; if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK) return true; } return false; } /* * Iterate list of requests and see if we can merge this bio with any * of them. */ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs) { struct request *rq; int checked = 8; list_for_each_entry_reverse(rq, list, queuelist) { if (!checked--) break; switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) { case BIO_MERGE_NONE: continue; case BIO_MERGE_OK: return true; case BIO_MERGE_FAILED: return false; } } return false; } EXPORT_SYMBOL_GPL(blk_bio_list_merge); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request) { struct request *rq; switch (elv_merge(q, &rq, bio)) { case ELEVATOR_BACK_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_back_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_BACK_MERGE); return true; case ELEVATOR_FRONT_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_front_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE); return true; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK; default: return false; } } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; static unsigned int mp_hash_shift __read_mostly; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static char * __initdata initramfs_options; static int __init initramfs_options_setup(char *str) { initramfs_options = str; return 1; } __setup("initramfs_options=", initramfs_options_setup); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); static struct hlist_head *mount_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (mnt->mnt_sb->s_readonly_remount) return 1; /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * __mnt_want_write - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, __mnt_drop_write() must be * called. This is effectively a refcount. */ int __mnt_want_write(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until * MNT_WRITE_HOLD is cleared. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = __mnt_want_write(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_clone_write - get write access to a mount * @mnt: the mount on which to take a write * * This is effectively like mnt_want_write, except * it must only be used to take an extra write reference * on a mountpoint that we already know has a write reference * on it. This allows some optimisation. * * After finished, mnt_drop_write must be called as usual to * drop the reference. */ int mnt_clone_write(struct vfsmount *mnt) { /* superblock may be r/o */ if (__mnt_is_readonly(mnt)) return -EROFS; preempt_disable(); mnt_inc_writers(real_mount(mnt)); preempt_enable(); return 0; } EXPORT_SYMBOL_GPL(mnt_clone_write); /** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like __mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int __mnt_want_write_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) return __mnt_want_write(file->f_path.mnt); else return mnt_clone_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = __mnt_want_write_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * __mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * __mnt_want_write() call above. */ void __mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { __mnt_drop_write(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { __mnt_drop_write_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); static int mnt_make_readonly(struct mount *mnt) { int ret = 0; lock_mount_hash(); mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) ret = -EBUSY; else mnt->mnt.mnt_flags |= MNT_READONLY; /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; unlock_mount_hash(); return ret; } static int __mnt_unmake_readonly(struct mount *mnt) { lock_mount_hash(); mnt->mnt.mnt_flags &= ~MNT_READONLY; unlock_mount_hash(); return 0; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; smp_mb(); if (mnt_get_writers(mnt) > 0) { err = -EBUSY; break; } } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) { sb->s_readonly_remount = 1; smp_wmb(); } list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; lock_mount_hash(); if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /* * find the first mount at @dentry on vfsmount @mnt. * call under rcu_read_lock() */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } static inline void lock_ns_list(struct mnt_namespace *ns) { spin_lock(&ns->ns_lock); } static inline void unlock_ns_list(struct mnt_namespace *ns) { spin_unlock(&ns->ns_lock); } static inline bool mnt_is_cursor(struct mount *mnt) { return mnt->mnt.mnt_flags & MNT_CURSOR; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; bool is_covered = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { if (mnt_is_cursor(mnt)) continue; is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } unlock_ns_list(ns); up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); __attach_mnt(mnt, parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; list_splice(&head, n->list.prev); n->mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ if (unlikely(m->mnt_expiry_mark)) m->mnt_expiry_mark = 0; mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* path_is_mountpoint() - Check if path is a mount in the current * namespace. * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } #ifdef CONFIG_PROC_FS static struct mount *mnt_list_next(struct mnt_namespace *ns, struct list_head *p) { struct mount *mnt, *ret = NULL; lock_ns_list(ns); list_for_each_continue(p, &ns->list) { mnt = list_entry(p, typeof(*mnt), mnt_list); if (!mnt_is_cursor(mnt)) { ret = mnt; break; } } unlock_ns_list(ns); return ret; } /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; struct list_head *prev; down_read(&namespace_sem); if (!*pos) { prev = &p->ns->list; } else { prev = &p->cursor.mnt_list; /* Read after we'd reached the end? */ if (list_empty(prev)) return NULL; } return mnt_list_next(p->ns, prev); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_mounts *p = m->private; struct mount *mnt = v; ++*pos; return mnt_list_next(p->ns, &mnt->mnt_list); } static void m_stop(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *mnt = v; lock_ns_list(p->ns); if (mnt) list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list); else list_del_init(&p->cursor.mnt_list); unlock_ns_list(p->ns); up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor) { down_read(&namespace_sem); lock_ns_list(ns); list_del(&cursor->mnt_list); unlock_ns_list(ns); up_read(&namespace_sem); } #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @mnt: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } #ifdef CONFIG_MANDATORY_FILE_LOCKING static bool may_mandlock(void) { pr_warn_once("======================================================\n" "WARNING: the mand mount option is being deprecated and\n" " will be removed in v5.15!\n" "======================================================\n"); return capable(CAP_SYS_ADMIN); } #else static inline bool may_mandlock(void) { pr_warn("VFS: \"mand\" mount option not supported"); return false; } #endif static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); struct super_block *sb = path->dentry->d_sb; if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { struct mount *res, *p, *q, *r, *parent; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { if (s->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ q = ERR_PTR(-EPERM); goto out; } else { s = skip_mnt_tree(s); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; parent = q; q = clone_mnt(p, p->mnt.mnt_root, flag); if (IS_ERR(q)) goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } static bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * * This creates a new vfsmount, which will be the clone of @path. The new will * not be attached anywhere in the namespace and will be private (i.e. changes * to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0, old, pending, sum; struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; old = ns->mounts; pending = ns->pending_mounts; sum = old + pending; if ((old > sum) || (pending > sum) || (max < sum) || (mounts > (max - sum))) return -ENOSPC; ns->pending_mounts = pending + mounts; return 0; } /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached * @parent_nd : if non-null, detach the source_mnt from its parent and * store the parent mount and mountpoint dentry. * (done when source_mnt is moved) * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *dest_mnt, struct mountpoint *dest_mp, bool moving) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; /* Preallocate a mountpoint in case the new mounts need * to be tucked under other mounts. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); lock_mount_hash(); if (err) goto out_cleanup_ids; for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } else { lock_mount_hash(); } if (moving) { unhash_mnt(source_mnt); attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } static struct mountpoint *lock_mount(struct path *path) { struct vfsmount *mnt; struct dentry *dentry = path->dentry; retry: inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); return ERR_PTR(-ENOENT); } namespace_lock(); mnt = lookup_mnt(path); if (likely(!mnt)) { struct mountpoint *mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); return mp; } return mp; } namespace_unlock(); inode_unlock(path->dentry->d_inode); path_put(path); path->mnt = mnt; dentry = path->dentry = dget(mnt->mnt_root); goto retry; } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, false); } static int may_change_propagation(const struct mount *m) { struct mnt_namespace *ns = m->mnt_ns; // it must be mounted in some namespace if (IS_ERR_OR_NULL(ns)) // is_mounted() return -EINVAL; // and the caller must be admin in userns of that namespace if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (path->dentry != path->mnt->mnt_root) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); err = may_change_propagation(mnt); if (err) goto out_unlock; if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt_ns = ns; ns->mounts++; } ns->root = mnt; list_add_tail(&ns->list, &mnt->mnt_list); mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); return __mnt_unmake_readonly(mnt); } /* * Update the user-settable attributes on a mount. The caller must hold * sb->s_umount for writing. */ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); unlock_mount_hash(); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf, *mntpath; buf = (char *)__get_free_page(GFP_KERNEL); if (buf) mntpath = d_path(mountpoint, buf, PAGE_SIZE); else mntpath = ERR_PTR(-ENOMEM); if (IS_ERR(mntpath)) mntpath = "(unknown)"; pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; if (buf) free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != mnt->mnt.mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; down_write(&sb->s_umount); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); up_write(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) set_mount_attributes(mnt, mnt_flags); } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_set_group(struct path *from_path, struct path *to_path) { struct mount *from, *to; int err; from = real_mount(from_path->mnt); to = real_mount(to_path->mnt); namespace_lock(); err = may_change_propagation(from); if (err) goto out; err = may_change_propagation(to); if (err) goto out; err = -EINVAL; /* To and From paths should be mount roots */ if (from_path->dentry != from_path->mnt->mnt_root) goto out; if (to_path->dentry != to_path->mnt->mnt_root) goto out; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) goto out; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) goto out; /* From mount should not have locked children in place of To's root */ if (has_locked_children(from, to->mnt.mnt_root)) goto out; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) goto out; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) goto out; if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; list_add(&to->mnt_slave, &m->mnt_slave_list); to->mnt_master = m; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); lock_mount_hash(); set_mnt_shared(to); unlock_mount_hash(); } err = 0; out: namespace_unlock(); return err; } static int do_move_mount(struct path *old_path, struct path *new_path) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; mp = lock_mount(new_path); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (old_path->dentry != old_path->mnt->mnt_root) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, attached); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path->mnt->mnt_root == path->dentry) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, dentry))) { rcu_read_unlock(); err = 0; goto discard_locked; } rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if ((flags & SB_MANDLOCK) && !may_mandlock()) return -EPERM; /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kfree(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); atomic_set(&new_ns->count, 1); INIT_LIST_HEAD(&new_ns->list); init_waitqueue_head(&new_ns->poll); spin_lock_init(&new_ns->ns_lock); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; list_add_tail(&new_ns->list, &new->mnt_list); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { q->mnt_ns = new_ns; new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(p, old); } namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } mnt->mnt_ns = ns; ns->root = mnt; ns->mounts++; list_add(&mnt->mnt_list, &ns->list); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~(MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME)) return -EINVAL; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; ret = -EPERM; if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock()) goto err_unlock; newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); mnt->mnt_ns = ns; ns->root = mnt; ns->mounts = 1; list_add(&mnt->mnt_list, &ns->list); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else ret = do_move_mount(&from_path, &to_path); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (root.mnt->mnt_root != root.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (new.mnt->mnt_root != new.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", initramfs_options); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); m->mnt_ns = ns; ns->root = m; ns->mounts = 1; list_add(&m->mnt_list, &ns->list); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!atomic_dec_and_test(&ns->count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { real_mount(mnt)->mnt_ns = NULL; synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) if (mnt[i]) real_mount(mnt[i])->mnt_ns = NULL; synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { struct mount *child; int mnt_flags; if (mnt_is_cursor(mnt)) continue; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: unlock_ns_list(ns); up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 | // SPDX-License-Identifier: GPL-2.0 /* * Detect hard lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) "NMI watchdog: " fmt #include <linux/nmi.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/sched/debug.h> #include <asm/irq_regs.h> #include <linux/perf_event.h> static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); static DEFINE_PER_CPU(struct perf_event *, dead_event); static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; static atomic_t watchdog_cpus = ATOMIC_INIT(0); notrace void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have * preemption enabled. If preemption is enabled * then interrupts should be enabled too, in which * case we shouldn't have to worry about the watchdog * going off. */ raw_cpu_write(watchdog_nmi_touch, true); } EXPORT_SYMBOL(arch_touch_nmi_watchdog); #ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP static DEFINE_PER_CPU(ktime_t, last_timestamp); static DEFINE_PER_CPU(unsigned int, nmi_rearmed); static ktime_t watchdog_hrtimer_sample_threshold __read_mostly; void watchdog_update_hrtimer_threshold(u64 period) { /* * The hrtimer runs with a period of (watchdog_threshold * 2) / 5 * * So it runs effectively with 2.5 times the rate of the NMI * watchdog. That means the hrtimer should fire 2-3 times before * the NMI watchdog expires. The NMI watchdog on x86 is based on * unhalted CPU cycles, so if Turbo-Mode is enabled the CPU cycles * might run way faster than expected and the NMI fires in a * smaller period than the one deduced from the nominal CPU * frequency. Depending on the Turbo-Mode factor this might be fast * enough to get the NMI period smaller than the hrtimer watchdog * period and trigger false positives. * * The sample threshold is used to check in the NMI handler whether * the minimum time between two NMI samples has elapsed. That * prevents false positives. * * Set this to 4/5 of the actual watchdog threshold period so the * hrtimer is guaranteed to fire at least once within the real * watchdog threshold. */ watchdog_hrtimer_sample_threshold = period * 2; } static bool watchdog_check_timestamp(void) { ktime_t delta, now = ktime_get_mono_fast_ns(); delta = now - __this_cpu_read(last_timestamp); if (delta < watchdog_hrtimer_sample_threshold) { /* * If ktime is jiffies based, a stalled timer would prevent * jiffies from being incremented and the filter would look * at a stale timestamp and never trigger. */ if (__this_cpu_inc_return(nmi_rearmed) < 10) return false; } __this_cpu_write(nmi_rearmed, 0); __this_cpu_write(last_timestamp, now); return true; } static void watchdog_init_timestamp(void) { __this_cpu_write(nmi_rearmed, 0); __this_cpu_write(last_timestamp, ktime_get_mono_fast_ns()); } #else static inline bool watchdog_check_timestamp(void) { return true; } static inline void watchdog_init_timestamp(void) { } #endif static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, .size = sizeof(struct perf_event_attr), .pinned = 1, .disabled = 1, }; /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; if (!watchdog_check_timestamp()) return; if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; } /* check for a hardlockup * This is done by making sure our timer interrupt * is incrementing. The timer interrupt should have * fired multiple times before we overflow'd. If it hasn't * then this is a good indication the cpu is stuck */ if (is_hardlockup()) { int this_cpu = smp_processor_id(); /* only print hardlockups once */ if (__this_cpu_read(hard_watchdog_warn) == true) return; pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", this_cpu); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); /* * Perform all-CPU dump only once to avoid multiple hardlockups * generating interleaving traces */ if (sysctl_hardlockup_all_cpu_backtrace && !test_and_set_bit(0, &hardlockup_allcpu_dumped)) trigger_allbutself_cpu_backtrace(); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); __this_cpu_write(hard_watchdog_warn, true); return; } __this_cpu_write(hard_watchdog_warn, false); return; } static int hardlockup_detector_event_create(void) { unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (IS_ERR(evt)) { pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, PTR_ERR(evt)); return PTR_ERR(evt); } this_cpu_write(watchdog_ev, evt); return 0; } /** * hardlockup_detector_perf_enable - Enable the local event */ void hardlockup_detector_perf_enable(void) { if (hardlockup_detector_event_create()) return; /* use original value for check */ if (!atomic_fetch_inc(&watchdog_cpus)) pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); watchdog_init_timestamp(); perf_event_enable(this_cpu_read(watchdog_ev)); } /** * hardlockup_detector_perf_disable - Disable the local event */ void hardlockup_detector_perf_disable(void) { struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); this_cpu_write(watchdog_ev, NULL); this_cpu_write(dead_event, event); cpumask_set_cpu(smp_processor_id(), &dead_events_mask); atomic_dec(&watchdog_cpus); } } /** * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them * * Called from lockup_detector_cleanup(). Serialized by the caller. */ void hardlockup_detector_perf_cleanup(void) { int cpu; for_each_cpu(cpu, &dead_events_mask) { struct perf_event *event = per_cpu(dead_event, cpu); /* * Required because for_each_cpu() reports unconditionally * CPU0 as set on UP kernels. Sigh. */ if (event) perf_event_release_kernel(event); per_cpu(dead_event, cpu) = NULL; } cpumask_clear(&dead_events_mask); } /** * hardlockup_detector_perf_stop - Globally stop watchdog events * * Special interface for x86 to handle the perf HT bug. */ void __init hardlockup_detector_perf_stop(void) { int cpu; lockdep_assert_cpus_held(); for_each_online_cpu(cpu) { struct perf_event *event = per_cpu(watchdog_ev, cpu); if (event) perf_event_disable(event); } } /** * hardlockup_detector_perf_restart - Globally restart watchdog events * * Special interface for x86 to handle the perf HT bug. */ void __init hardlockup_detector_perf_restart(void) { int cpu; lockdep_assert_cpus_held(); if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) return; for_each_online_cpu(cpu) { struct perf_event *event = per_cpu(watchdog_ev, cpu); if (event) perf_event_enable(event); } } /** * hardlockup_detector_perf_init - Probe whether NMI event is available at all */ int __init hardlockup_detector_perf_init(void) { int ret = hardlockup_detector_event_create(); if (ret) { pr_info("Perf NMI watchdog permanently disabled\n"); } else { perf_event_release_kernel(this_cpu_read(watchdog_ev)); this_cpu_write(watchdog_ev, NULL); } return ret; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef INT_BLK_MQ_TAG_H #define INT_BLK_MQ_TAG_H /* * Tag address space map. */ struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; atomic_t active_queues; struct sbitmap_queue *bitmap_tags; struct sbitmap_queue *breserved_tags; struct sbitmap_queue __bitmap_tags; struct sbitmap_queue __breserved_tags; struct request **rqs; struct request **static_rqs; struct list_head page_list; /* * used to clear request reference in rqs[] before freeing one * request pool */ spinlock_t lock; }; extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, unsigned int flags); extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags); extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size); extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv); void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt, struct blk_mq_hw_ctx *hctx) { if (!hctx) return &bt->ws[0]; return sbq_wait_ptr(bt, &hctx->wait_index); } enum { BLK_MQ_NO_TAG = -1U, BLK_MQ_TAG_MIN = 1, BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *); extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *); static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return false; return __blk_mq_tag_busy(hctx); } static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return; __blk_mq_tag_idle(hctx); } static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags, unsigned int tag) { return tag < tags->nr_reserved_tags; } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2001 Jens Axboe <axboe@suse.de> */ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H #include <linux/highmem.h> #include <linux/mempool.h> #include <linux/ioprio.h> /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include <linux/blk_types.h> #define BIO_DEBUG #ifdef BIO_DEBUG #define BIO_BUG_ON BUG_ON #else #define BIO_BUG_ON #endif #define BIO_MAX_PAGES 256 #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) #define bio_iter_page(bio, iter) \ bvec_iter_page((bio)->bi_io_vec, (iter)) #define bio_iter_len(bio, iter) \ bvec_iter_len((bio)->bi_io_vec, (iter)) #define bio_iter_offset(bio, iter) \ bvec_iter_offset((bio)->bi_io_vec, (iter)) #define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) #define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter) #define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter) /* * Return the data direction, READ or WRITE. */ #define bio_data_dir(bio) \ (op_is_write(bio_op(bio)) ? WRITE : READ) /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && bio_op(bio) != REQ_OP_SECURE_ERASE && bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; } static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || bio_op(bio) == REQ_OP_WRITE_SAME || bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline bool bio_mergeable(struct bio *bio) { if (bio->bi_opf & REQ_NOMERGE_FLAGS) return false; return true; } static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio_has_data(bio)) return bio_iovec(bio).bv_len; else /* dataless requests such as discard */ return bio->bi_iter.bi_size; } static inline void *bio_data(struct bio *bio) { if (bio_has_data(bio)) return page_address(bio_page(bio)) + bio_offset(bio); return NULL; } /** * bio_full - check if the bio is full * @bio: bio to check * @len: length of one segment to be added * * Return true if @bio is full and one segment with @len bytes can't be * added to the bio, otherwise return false */ static inline bool bio_full(struct bio *bio, unsigned len) { if (bio->bi_vcnt >= bio->bi_max_vecs) return true; if (bio->bi_iter.bi_size > UINT_MAX - len) return true; return false; } static inline bool bio_next_segment(const struct bio *bio, struct bvec_iter_all *iter) { if (iter->idx >= bio->bi_vcnt) return false; bvec_advance(&bio->bi_io_vec[iter->idx], iter); return true; } /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) static inline void bio_advance_iter(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ } #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bio_iter_iovec((bio), (iter))), 1); \ bio_advance_iter((bio), &(iter), (bvl).bv_len)) #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) #define __bio_for_each_bvec(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \ bio_advance_iter((bio), &(iter), (bvl).bv_len)) /* iterate over multi-page bvec */ #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) /* * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the * same reasons as bio_for_each_segment_all(). */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ i < (bio)->bi_vcnt; i++, bvl++) \ #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) { unsigned segs = 0; struct bio_vec bv; struct bvec_iter iter; /* * We special case discard/write same/write zeroes, because they * interpret bi_size differently: */ switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: return 1; default: break; } bio_for_each_segment(bv, bio, iter) segs++; return segs; } /* * get a reference to a bio, so it won't disappear. the intended use is * something like: * * bio_get(bio); * submit_bio(rw, bio); * if (bio->bi_flags ...) * do_something * bio_put(bio); * * without the bio_get(), it could potentially complete I/O before submit_bio * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ static inline void bio_get(struct bio *bio) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb__before_atomic(); atomic_inc(&bio->__bi_cnt); } static inline void bio_cnt_set(struct bio *bio, unsigned int count) { if (count != 1) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb(); } atomic_set(&bio->__bi_cnt, count); } static inline bool bio_flagged(struct bio *bio, unsigned int bit) { return (bio->bi_flags & (1U << bit)) != 0; } static inline void bio_set_flag(struct bio *bio, unsigned int bit) { bio->bi_flags |= (1U << bit); } static inline void bio_clear_flag(struct bio *bio, unsigned int bit) { bio->bi_flags &= ~(1U << bit); } static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) { struct bvec_iter iter = bio->bi_iter; int idx; bio_get_first_bvec(bio, bv); if (bv->bv_len == bio->bi_iter.bi_size) return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); if (!iter.bi_bvec_done) idx = iter.bi_idx - 1; else /* in the middle of bvec */ idx = iter.bi_idx; *bv = bio->bi_io_vec[idx]; /* * iter.bi_bvec_done records actual length of the last bvec * if this bio ends in the middle of one io vector */ if (iter.bi_bvec_done) bv->bv_len = iter.bi_bvec_done; } static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return bio->bi_io_vec; } static inline struct page *bio_first_page_all(struct bio *bio) { return bio_first_bvec_all(bio)->bv_page; } static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return &bio->bi_io_vec[bio->bi_vcnt - 1]; } enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ }; /* * bio integrity payload */ struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ struct bvec_iter bip_iter; unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ struct bvec_iter bio_iter; /* for rewinding parent bio */ struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; #if defined(CONFIG_BLK_DEV_INTEGRITY) static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip) return bip->bip_flags & flag; return false; } static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) { return bip->bip_iter.bi_sector; } static inline void bip_set_seed(struct bio_integrity_payload *bip, sector_t seed) { bip->bip_iter.bi_sector = seed; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ extern void bio_trim(struct bio *bio, int offset, int size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); /** * bio_next_split - get next @sectors from a bio, splitting if necessary * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Returns a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { if (sectors >= bio_sectors(bio)) return bio; return bio_split(bio, sectors, gfp, bs); } enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), }; extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); } extern blk_qc_t submit_bio(struct bio *); extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } static inline void bio_wouldblock_error(struct bio *bio) { bio_set_flag(bio, BIO_QUIET); bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } struct request_queue; extern int submit_bio_wait(struct bio *bio); extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs); extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool *same_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_list_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); void bio_truncate(struct bio *bio, unsigned new_size); void guard_bio_eod(struct bio *bio); static inline void zero_fill_bio(struct bio *bio) { zero_fill_bio_iter(bio, bio->bi_iter); } extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_set_dev(bio, bdev) \ do { \ if ((bio)->bi_disk != (bdev)->bd_disk) \ bio_clear_flag(bio, BIO_THROTTLED);\ (bio)->bi_disk = (bdev)->bd_disk; \ (bio)->bi_partno = (bdev)->bd_partno; \ bio_associate_blkg(bio); \ } while (0) #define bio_copy_dev(dst, src) \ do { \ (dst)->bi_disk = (src)->bi_disk; \ (dst)->bi_partno = (src)->bi_partno; \ bio_clone_blkg_association(dst, src); \ } while (0) #define bio_dev(bio) \ disk_devt((bio)->bi_disk) #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM /* * remember never ever reenable interrupts between a bvec_kmap_irq and * bvec_kunmap_irq! */ static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { unsigned long addr; /* * might not be a highmem page, but the preempt/irq count * balancing is a lot nicer this way */ local_irq_save(*flags); addr = (unsigned long) kmap_atomic(bvec->bv_page); BUG_ON(addr & ~PAGE_MASK); return (char *) addr + bvec->bv_offset; } static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { unsigned long ptr = (unsigned long) buffer & PAGE_MASK; kunmap_atomic((void *) ptr); local_irq_restore(*flags); } #else static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { return page_address(bvec->bv_page) + bvec->bv_offset; } static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { *flags = 0; } #endif /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * * A bio_list anchors a singly-linked list of bios chained through the bi_next * member of the bio. The bio_list also caches the last list member to allow * fast access to the tail. */ struct bio_list { struct bio *head; struct bio *tail; }; static inline int bio_list_empty(const struct bio_list *bl) { return bl->head == NULL; } static inline void bio_list_init(struct bio_list *bl) { bl->head = bl->tail = NULL; } #define BIO_EMPTY_LIST { NULL, NULL } #define bio_list_for_each(bio, bl) \ for (bio = (bl)->head; bio; bio = bio->bi_next) static inline unsigned bio_list_size(const struct bio_list *bl) { unsigned sz = 0; struct bio *bio; bio_list_for_each(bio, bl) sz++; return sz; } static inline void bio_list_add(struct bio_list *bl, struct bio *bio) { bio->bi_next = NULL; if (bl->tail) bl->tail->bi_next = bio; else bl->head = bio; bl->tail = bio; } static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) { bio->bi_next = bl->head; bl->head = bio; if (!bl->tail) bl->tail = bio; } static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->tail) bl->tail->bi_next = bl2->head; else bl->head = bl2->head; bl->tail = bl2->tail; } static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->head) bl2->tail->bi_next = bl->head; else bl->tail = bl2->tail; bl->head = bl2->head; } static inline struct bio *bio_list_peek(struct bio_list *bl) { return bl->head; } static inline struct bio *bio_list_pop(struct bio_list *bl) { struct bio *bio = bl->head; if (bio) { bl->head = bl->head->bi_next; if (!bl->head) bl->tail = NULL; bio->bi_next = NULL; } return bio; } static inline struct bio *bio_list_get(struct bio_list *bl) { struct bio *bio = bl->head; bl->head = bl->tail = NULL; return bio; } /* * Increment chain count for the bio. Make sure the CHAIN flag update * is visible before the raised count. */ static inline void bio_inc_remaining(struct bio *bio) { bio_set_flag(bio, BIO_CHAIN); smp_mb__before_atomic(); atomic_inc(&bio->__bi_remaining); } /* * bio_set is used to allow other portions of the IO system to * allocate their own private memory pools for bio and iovec structures. * These memory pools in turn all allocate from the bio_slab * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; mempool_t bio_pool; mempool_t bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) mempool_t bio_integrity_pool; mempool_t bvec_integrity_pool; #endif /* * Deadlock avoidance for stacking block drivers: see comments in * bio_alloc_bioset() for details */ spinlock_t rescue_lock; struct bio_list rescue_list; struct work_struct rescue_work; struct workqueue_struct *rescue_workqueue; }; struct biovec_slab { int nr_vecs; char *name; struct kmem_cache *slab; }; static inline bool bioset_initialized(struct bio_set *bs) { return bs->bio_slab != NULL; } /* * a small number of entries is fine, not going to be performance critical. * basically we just need to survive */ #define BIO_SPLIT_ENTRIES 2 #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_for_each_vec(bvl, bip, iter) \ for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) #define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ for_each_bio(_bio) \ bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); extern void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void *bio_integrity(struct bio *bio) { return NULL; } static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; } static inline void bioset_integrity_free (struct bio_set *bs) { return; } static inline bool bio_integrity_prep(struct bio *bio) { return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { return 0; } static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { return; } static inline void bio_integrity_trim(struct bio *bio) { return; } static inline void bio_integrity_init(void) { return; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { return false; } static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp, unsigned int nr) { return ERR_PTR(-EINVAL); } static inline int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { return 0; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ /* * Mark a bio as polled. Note that for async polled IO, the caller must * expect -EWOULDBLOCK if we cannot allocate a request (or other resources). * We cannot block waiting for requests on polled IO, as those completions * must be found by the caller. This is different than IRQ driven IO, where * it's safe to wait for IO to complete. */ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { bio->bi_opf |= REQ_HIPRI; if (!is_sync_kiocb(kiocb)) bio->bi_opf |= REQ_NOWAIT; } #endif /* __LINUX_BIO_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) #endif |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 | // SPDX-License-Identifier: GPL-2.0-or-later /* Filesystem parameter parser. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/namei.h> #include "internal.h" static const struct constant_table bool_names[] = { { "0", false }, { "1", true }, { "false", false }, { "no", false }, { "true", true }, { "yes", true }, { }, }; static const struct constant_table * __lookup_constant(const struct constant_table *tbl, const char *name) { for ( ; tbl->name; tbl++) if (strcmp(name, tbl->name) == 0) return tbl; return NULL; } /** * lookup_constant - Look up a constant by name in an ordered table * @tbl: The table of constants to search. * @name: The name to look up. * @not_found: The value to return if the name is not found. */ int lookup_constant(const struct constant_table *tbl, const char *name, int not_found) { const struct constant_table *p = __lookup_constant(tbl, name); return p ? p->value : not_found; } EXPORT_SYMBOL(lookup_constant); static inline bool is_flag(const struct fs_parameter_spec *p) { return p->type == NULL; } static const struct fs_parameter_spec *fs_lookup_key( const struct fs_parameter_spec *desc, struct fs_parameter *param, bool *negated) { const struct fs_parameter_spec *p, *other = NULL; const char *name = param->key; bool want_flag = param->type == fs_value_is_flag; *negated = false; for (p = desc; p->name; p++) { if (strcmp(p->name, name) != 0) continue; if (likely(is_flag(p) == want_flag)) return p; other = p; } if (want_flag) { if (name[0] == 'n' && name[1] == 'o' && name[2]) { for (p = desc; p->name; p++) { if (strcmp(p->name, name + 2) != 0) continue; if (!(p->flags & fs_param_neg_with_no)) continue; *negated = true; return p; } } } return other; } /* * fs_parse - Parse a filesystem configuration parameter * @fc: The filesystem context to log errors through. * @desc: The parameter description to use. * @param: The parameter. * @result: Where to place the result of the parse * * Parse a filesystem configuration parameter and attempt a conversion for a * simple parameter for which this is requested. If successful, the determined * parameter ID is placed into @result->key, the desired type is indicated in * @result->t and any converted value is placed into an appropriate member of * the union in @result. * * The function returns the parameter number if the parameter was matched, * -ENOPARAM if it wasn't matched and @desc->ignore_unknown indicated that * unknown parameters are okay and -EINVAL if there was a conversion issue or * the parameter wasn't recognised and unknowns aren't okay. */ int __fs_parse(struct p_log *log, const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { const struct fs_parameter_spec *p; result->uint_64 = 0; p = fs_lookup_key(desc, param, &result->negated); if (!p) return -ENOPARAM; if (p->flags & fs_param_deprecated) warn_plog(log, "Deprecated parameter '%s'", param->key); /* Try to turn the type we were given into the type desired by the * parameter and give an error if we can't. */ if (is_flag(p)) { if (param->type != fs_value_is_flag) return inval_plog(log, "Unexpected value for '%s'", param->key); result->boolean = !result->negated; } else { int ret = p->type(log, p, param, result); if (ret) return ret; } return p->opt; } EXPORT_SYMBOL(__fs_parse); /** * fs_lookup_param - Look up a path referred to by a parameter * @fc: The filesystem context to log errors through. * @param: The parameter. * @want_bdev: T if want a blockdev * @_path: The result of the lookup */ int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, struct path *_path) { struct filename *f; unsigned int flags = 0; bool put_f; int ret; switch (param->type) { case fs_value_is_string: f = getname_kernel(param->string); if (IS_ERR(f)) return PTR_ERR(f); put_f = true; break; case fs_value_is_filename: f = param->name; put_f = false; break; default: return invalf(fc, "%s: not usable as path", param->key); } f->refcnt++; /* filename_lookup() drops our ref. */ ret = filename_lookup(param->dirfd, f, flags, _path, NULL); if (ret < 0) { errorf(fc, "%s: Lookup failure for '%s'", param->key, f->name); goto out; } if (want_bdev && !S_ISBLK(d_backing_inode(_path->dentry)->i_mode)) { path_put(_path); _path->dentry = NULL; _path->mnt = NULL; errorf(fc, "%s: Non-blockdev passed as '%s'", param->key, f->name); ret = -ENOTBLK; } out: if (put_f) putname(f); return ret; } EXPORT_SYMBOL(fs_lookup_param); static int fs_param_bad_value(struct p_log *log, struct fs_parameter *param) { return inval_plog(log, "Bad value for '%s'", param->key); } int fs_param_is_bool(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { int b; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); b = lookup_constant(bool_names, param->string, -1); if (b == -1) return fs_param_bad_value(log, param); result->boolean = b; return 0; } EXPORT_SYMBOL(fs_param_is_bool); int fs_param_is_u32(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { int base = (unsigned long)p->data; if (param->type != fs_value_is_string || kstrtouint(param->string, base, &result->uint_32) < 0) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_u32); int fs_param_is_s32(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_string || kstrtoint(param->string, 0, &result->int_32) < 0) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_s32); int fs_param_is_u64(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_string || kstrtoull(param->string, 0, &result->uint_64) < 0) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_u64); int fs_param_is_enum(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { const struct constant_table *c; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); c = __lookup_constant(p->data, param->string); if (!c) return fs_param_bad_value(log, param); result->uint_32 = c->value; return 0; } EXPORT_SYMBOL(fs_param_is_enum); int fs_param_is_string(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_string || !*param->string) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_string); int fs_param_is_blob(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_blob) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_blob); int fs_param_is_fd(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { switch (param->type) { case fs_value_is_string: if (kstrtouint(param->string, 0, &result->uint_32) < 0) break; if (result->uint_32 <= INT_MAX) return 0; break; case fs_value_is_file: result->uint_32 = param->dirfd; if (result->uint_32 <= INT_MAX) return 0; break; default: break; } return fs_param_bad_value(log, param); } EXPORT_SYMBOL(fs_param_is_fd); int fs_param_is_blockdev(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { return 0; } EXPORT_SYMBOL(fs_param_is_blockdev); int fs_param_is_path(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { return 0; } EXPORT_SYMBOL(fs_param_is_path); #ifdef CONFIG_VALIDATE_FS_PARSER /** * validate_constant_table - Validate a constant table * @name: Name to use in reporting * @tbl: The constant table to validate. * @tbl_size: The size of the table. * @low: The lowest permissible value. * @high: The highest permissible value. * @special: One special permissible value outside of the range. */ bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { size_t i; bool good = true; if (tbl_size == 0) { pr_warn("VALIDATE C-TBL: Empty\n"); return true; } for (i = 0; i < tbl_size; i++) { if (!tbl[i].name) { pr_err("VALIDATE C-TBL[%zu]: Null\n", i); good = false; } else if (i > 0 && tbl[i - 1].name) { int c = strcmp(tbl[i-1].name, tbl[i].name); if (c == 0) { pr_err("VALIDATE C-TBL[%zu]: Duplicate %s\n", i, tbl[i].name); good = false; } if (c > 0) { pr_err("VALIDATE C-TBL[%zu]: Missorted %s>=%s\n", i, tbl[i-1].name, tbl[i].name); good = false; } } if (tbl[i].value != special && (tbl[i].value < low || tbl[i].value > high)) { pr_err("VALIDATE C-TBL[%zu]: %s->%d const out of range (%d-%d)\n", i, tbl[i].name, tbl[i].value, low, high); good = false; } } return good; } /** * fs_validate_description - Validate a parameter description * @desc: The parameter description to validate. */ bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { const struct fs_parameter_spec *param, *p2; bool good = true; for (param = desc; param->name; param++) { /* Check for duplicate parameter names */ for (p2 = desc; p2 < param; p2++) { if (strcmp(param->name, p2->name) == 0) { if (is_flag(param) != is_flag(p2)) continue; pr_err("VALIDATE %s: PARAM[%s]: Duplicate\n", name, param->name); good = false; } } } return good; } #endif /* CONFIG_VALIDATE_FS_PARSER */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/isofs/inode.c * * (C) 1991 Linus Torvalds - minix filesystem * 1992, 1993, 1994 Eric Youngdale Modified for ISO 9660 filesystem. * 1994 Eberhard Mönkeberg - multi session handling. * 1995 Mark Dobie - allow mounting of some weird VideoCDs and PhotoCDs. * 1997 Gordon Chaffee - Joliet CDs * 1998 Eric Lammerts - ISO 9660 Level 3 * 2004 Paul Serice - Inode Support pushed out from 4GB to 128GB * 2004 Paul Serice - NFS Export Operations */ #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/nls.h> #include <linux/ctype.h> #include <linux/statfs.h> #include <linux/cdrom.h> #include <linux/parser.h> #include <linux/mpage.h> #include <linux/user_namespace.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include "isofs.h" #include "zisofs.h" /* max tz offset is 13 hours */ #define MAX_TZ_OFFSET (52*15*60) #define BEQUIET static int isofs_hashi(const struct dentry *parent, struct qstr *qstr); static int isofs_dentry_cmpi(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); #ifdef CONFIG_JOLIET static int isofs_hashi_ms(const struct dentry *parent, struct qstr *qstr); static int isofs_hash_ms(const struct dentry *parent, struct qstr *qstr); static int isofs_dentry_cmpi_ms(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); static int isofs_dentry_cmp_ms(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); #endif static void isofs_put_super(struct super_block *sb) { struct isofs_sb_info *sbi = ISOFS_SB(sb); #ifdef CONFIG_JOLIET unload_nls(sbi->s_nls_iocharset); #endif kfree(sbi); sb->s_fs_info = NULL; return; } static int isofs_read_inode(struct inode *, int relocated); static int isofs_statfs (struct dentry *, struct kstatfs *); static int isofs_show_options(struct seq_file *, struct dentry *); static struct kmem_cache *isofs_inode_cachep; static struct inode *isofs_alloc_inode(struct super_block *sb) { struct iso_inode_info *ei; ei = kmem_cache_alloc(isofs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void isofs_free_inode(struct inode *inode) { kmem_cache_free(isofs_inode_cachep, ISOFS_I(inode)); } static void init_once(void *foo) { struct iso_inode_info *ei = foo; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { isofs_inode_cachep = kmem_cache_create("isofs_inode_cache", sizeof(struct iso_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (!isofs_inode_cachep) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(isofs_inode_cachep); } static int isofs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); if (!(*flags & SB_RDONLY)) return -EROFS; return 0; } static const struct super_operations isofs_sops = { .alloc_inode = isofs_alloc_inode, .free_inode = isofs_free_inode, .put_super = isofs_put_super, .statfs = isofs_statfs, .remount_fs = isofs_remount, .show_options = isofs_show_options, }; static const struct dentry_operations isofs_dentry_ops[] = { { .d_hash = isofs_hashi, .d_compare = isofs_dentry_cmpi, }, #ifdef CONFIG_JOLIET { .d_hash = isofs_hash_ms, .d_compare = isofs_dentry_cmp_ms, }, { .d_hash = isofs_hashi_ms, .d_compare = isofs_dentry_cmpi_ms, }, #endif }; struct iso9660_options{ unsigned int rock:1; unsigned int joliet:1; unsigned int cruft:1; unsigned int hide:1; unsigned int showassoc:1; unsigned int nocompress:1; unsigned int overriderockperm:1; unsigned int uid_set:1; unsigned int gid_set:1; unsigned char map; unsigned char check; unsigned int blocksize; umode_t fmode; umode_t dmode; kgid_t gid; kuid_t uid; char *iocharset; /* LVE */ s32 session; s32 sbsector; }; /* * Compute the hash for the isofs name corresponding to the dentry. */ static int isofs_hashi_common(const struct dentry *dentry, struct qstr *qstr, int ms) { const char *name; int len; char c; unsigned long hash; len = qstr->len; name = qstr->name; if (ms) { while (len && name[len-1] == '.') len--; } hash = init_name_hash(dentry); while (len--) { c = tolower(*name++); hash = partial_name_hash(c, hash); } qstr->hash = end_name_hash(hash); return 0; } /* * Compare of two isofs names. */ static int isofs_dentry_cmp_common( unsigned int len, const char *str, const struct qstr *name, int ms, int ci) { int alen, blen; /* A filename cannot end in '.' or we treat it like it has none */ alen = name->len; blen = len; if (ms) { while (alen && name->name[alen-1] == '.') alen--; while (blen && str[blen-1] == '.') blen--; } if (alen == blen) { if (ci) { if (strncasecmp(name->name, str, alen) == 0) return 0; } else { if (strncmp(name->name, str, alen) == 0) return 0; } } return 1; } static int isofs_hashi(const struct dentry *dentry, struct qstr *qstr) { return isofs_hashi_common(dentry, qstr, 0); } static int isofs_dentry_cmpi(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { return isofs_dentry_cmp_common(len, str, name, 0, 1); } #ifdef CONFIG_JOLIET /* * Compute the hash for the isofs name corresponding to the dentry. */ static int isofs_hash_common(const struct dentry *dentry, struct qstr *qstr, int ms) { const char *name; int len; len = qstr->len; name = qstr->name; if (ms) { while (len && name[len-1] == '.') len--; } qstr->hash = full_name_hash(dentry, name, len); return 0; } static int isofs_hash_ms(const struct dentry *dentry, struct qstr *qstr) { return isofs_hash_common(dentry, qstr, 1); } static int isofs_hashi_ms(const struct dentry *dentry, struct qstr *qstr) { return isofs_hashi_common(dentry, qstr, 1); } static int isofs_dentry_cmp_ms(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { return isofs_dentry_cmp_common(len, str, name, 1, 0); } static int isofs_dentry_cmpi_ms(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { return isofs_dentry_cmp_common(len, str, name, 1, 1); } #endif enum { Opt_block, Opt_check_r, Opt_check_s, Opt_cruft, Opt_gid, Opt_ignore, Opt_iocharset, Opt_map_a, Opt_map_n, Opt_map_o, Opt_mode, Opt_nojoliet, Opt_norock, Opt_sb, Opt_session, Opt_uid, Opt_unhide, Opt_utf8, Opt_err, Opt_nocompress, Opt_hide, Opt_showassoc, Opt_dmode, Opt_overriderockperm, }; static const match_table_t tokens = { {Opt_norock, "norock"}, {Opt_nojoliet, "nojoliet"}, {Opt_unhide, "unhide"}, {Opt_hide, "hide"}, {Opt_showassoc, "showassoc"}, {Opt_cruft, "cruft"}, {Opt_utf8, "utf8"}, {Opt_iocharset, "iocharset=%s"}, {Opt_map_a, "map=acorn"}, {Opt_map_a, "map=a"}, {Opt_map_n, "map=normal"}, {Opt_map_n, "map=n"}, {Opt_map_o, "map=off"}, {Opt_map_o, "map=o"}, {Opt_session, "session=%u"}, {Opt_sb, "sbsector=%u"}, {Opt_check_r, "check=relaxed"}, {Opt_check_r, "check=r"}, {Opt_check_s, "check=strict"}, {Opt_check_s, "check=s"}, {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, {Opt_mode, "mode=%u"}, {Opt_dmode, "dmode=%u"}, {Opt_overriderockperm, "overriderockperm"}, {Opt_block, "block=%u"}, {Opt_ignore, "conv=binary"}, {Opt_ignore, "conv=b"}, {Opt_ignore, "conv=text"}, {Opt_ignore, "conv=t"}, {Opt_ignore, "conv=mtext"}, {Opt_ignore, "conv=m"}, {Opt_ignore, "conv=auto"}, {Opt_ignore, "conv=a"}, {Opt_nocompress, "nocompress"}, {Opt_err, NULL} }; static int parse_options(char *options, struct iso9660_options *popt) { char *p; int option; popt->map = 'n'; popt->rock = 1; popt->joliet = 1; popt->cruft = 0; popt->hide = 0; popt->showassoc = 0; popt->check = 'u'; /* unset */ popt->nocompress = 0; popt->blocksize = 1024; popt->fmode = popt->dmode = ISOFS_INVALID_MODE; popt->uid_set = 0; popt->gid_set = 0; popt->gid = GLOBAL_ROOT_GID; popt->uid = GLOBAL_ROOT_UID; popt->iocharset = NULL; popt->overriderockperm = 0; popt->session=-1; popt->sbsector=-1; if (!options) return 1; while ((p = strsep(&options, ",")) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; unsigned n; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_norock: popt->rock = 0; break; case Opt_nojoliet: popt->joliet = 0; break; case Opt_hide: popt->hide = 1; break; case Opt_unhide: case Opt_showassoc: popt->showassoc = 1; break; case Opt_cruft: popt->cruft = 1; break; #ifdef CONFIG_JOLIET case Opt_utf8: kfree(popt->iocharset); popt->iocharset = kstrdup("utf8", GFP_KERNEL); if (!popt->iocharset) return 0; break; case Opt_iocharset: kfree(popt->iocharset); popt->iocharset = match_strdup(&args[0]); if (!popt->iocharset) return 0; break; #endif case Opt_map_a: popt->map = 'a'; break; case Opt_map_o: popt->map = 'o'; break; case Opt_map_n: popt->map = 'n'; break; case Opt_session: if (match_int(&args[0], &option)) return 0; n = option; /* * Track numbers are supposed to be in range 1-99, the * mount option starts indexing at 0. */ if (n >= 99) return 0; popt->session = n + 1; break; case Opt_sb: if (match_int(&args[0], &option)) return 0; popt->sbsector = option; break; case Opt_check_r: popt->check = 'r'; break; case Opt_check_s: popt->check = 's'; break; case Opt_ignore: break; case Opt_uid: if (match_int(&args[0], &option)) return 0; popt->uid = make_kuid(current_user_ns(), option); if (!uid_valid(popt->uid)) return 0; popt->uid_set = 1; break; case Opt_gid: if (match_int(&args[0], &option)) return 0; popt->gid = make_kgid(current_user_ns(), option); if (!gid_valid(popt->gid)) return 0; popt->gid_set = 1; break; case Opt_mode: if (match_int(&args[0], &option)) return 0; popt->fmode = option; break; case Opt_dmode: if (match_int(&args[0], &option)) return 0; popt->dmode = option; break; case Opt_overriderockperm: popt->overriderockperm = 1; break; case Opt_block: if (match_int(&args[0], &option)) return 0; n = option; if (n != 512 && n != 1024 && n != 2048) return 0; popt->blocksize = n; break; case Opt_nocompress: popt->nocompress = 1; break; default: return 0; } } return 1; } /* * Display the mount options in /proc/mounts. */ static int isofs_show_options(struct seq_file *m, struct dentry *root) { struct isofs_sb_info *sbi = ISOFS_SB(root->d_sb); if (!sbi->s_rock) seq_puts(m, ",norock"); else if (!sbi->s_joliet_level) seq_puts(m, ",nojoliet"); if (sbi->s_cruft) seq_puts(m, ",cruft"); if (sbi->s_hide) seq_puts(m, ",hide"); if (sbi->s_nocompress) seq_puts(m, ",nocompress"); if (sbi->s_overriderockperm) seq_puts(m, ",overriderockperm"); if (sbi->s_showassoc) seq_puts(m, ",showassoc"); if (sbi->s_check) seq_printf(m, ",check=%c", sbi->s_check); if (sbi->s_mapping) seq_printf(m, ",map=%c", sbi->s_mapping); if (sbi->s_session != 255) seq_printf(m, ",session=%u", sbi->s_session - 1); if (sbi->s_sbsector != -1) seq_printf(m, ",sbsector=%u", sbi->s_sbsector); if (root->d_sb->s_blocksize != 1024) seq_printf(m, ",blocksize=%lu", root->d_sb->s_blocksize); if (sbi->s_uid_set) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, sbi->s_uid)); if (sbi->s_gid_set) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, sbi->s_gid)); if (sbi->s_dmode != ISOFS_INVALID_MODE) seq_printf(m, ",dmode=%o", sbi->s_dmode); if (sbi->s_fmode != ISOFS_INVALID_MODE) seq_printf(m, ",fmode=%o", sbi->s_fmode); #ifdef CONFIG_JOLIET if (sbi->s_nls_iocharset) seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); else seq_puts(m, ",iocharset=utf8"); #endif return 0; } /* * look if the driver can tell the multi session redirection value * * don't change this if you don't know what you do, please! * Multisession is legal only with XA disks. * A non-XA disk with more than one volume descriptor may do it right, but * usually is written in a nowhere standardized "multi-partition" manner. * Multisession uses absolute addressing (solely the first frame of the whole * track is #0), multi-partition uses relative addressing (each first frame of * each track is #0), and a track is not a session. * * A broken CDwriter software or drive firmware does not set new standards, * at least not if conflicting with the existing ones. * * emoenke@gwdg.de */ #define WE_OBEY_THE_WRITTEN_STANDARDS 1 static unsigned int isofs_get_last_session(struct super_block *sb, s32 session) { struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); unsigned int vol_desc_start = 0; if (session > 0) { struct cdrom_tocentry te; if (!cdi) return 0; te.cdte_track = session; te.cdte_format = CDROM_LBA; if (cdrom_read_tocentry(cdi, &te) == 0) { printk(KERN_DEBUG "ISOFS: Session %d start %d type %d\n", session, te.cdte_addr.lba, te.cdte_ctrl & CDROM_DATA_TRACK); if ((te.cdte_ctrl & CDROM_DATA_TRACK) == 4) return te.cdte_addr.lba; } printk(KERN_ERR "ISOFS: Invalid session number or type of track\n"); } if (cdi) { struct cdrom_multisession ms_info; ms_info.addr_format = CDROM_LBA; if (cdrom_multisession(cdi, &ms_info) == 0) { #if WE_OBEY_THE_WRITTEN_STANDARDS /* necessary for a valid ms_info.addr */ if (ms_info.xa_flag) #endif vol_desc_start = ms_info.addr.lba; } } return vol_desc_start; } /* * Check if root directory is empty (has less than 3 files). * * Used to detect broken CDs where ISO root directory is empty but Joliet root * directory is OK. If such CD has Rock Ridge extensions, they will be disabled * (and Joliet used instead) or else no files would be visible. */ static bool rootdir_empty(struct super_block *sb, unsigned long block) { int offset = 0, files = 0, de_len; struct iso_directory_record *de; struct buffer_head *bh; bh = sb_bread(sb, block); if (!bh) return true; while (files < 3) { de = (struct iso_directory_record *) (bh->b_data + offset); de_len = *(unsigned char *) de; if (de_len == 0) break; files++; offset += de_len; } brelse(bh); return files < 3; } /* * Initialize the superblock and read the root inode. */ static int isofs_fill_super(struct super_block *s, void *data, int silent) { struct buffer_head *bh = NULL, *pri_bh = NULL; struct hs_primary_descriptor *h_pri = NULL; struct iso_primary_descriptor *pri = NULL; struct iso_supplementary_descriptor *sec = NULL; struct iso_directory_record *rootp; struct inode *inode; struct iso9660_options opt; struct isofs_sb_info *sbi; unsigned long first_data_zone; int joliet_level = 0; int iso_blknum, block; int orig_zonesize; int table, error = -EINVAL; unsigned int vol_desc_start; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; s->s_fs_info = sbi; if (!parse_options((char *)data, &opt)) goto out_freesbi; /* * First of all, get the hardware blocksize for this device. * If we don't know what it is, or the hardware blocksize is * larger than the blocksize the user specified, then use * that value. */ /* * What if bugger tells us to go beyond page size? */ if (bdev_logical_block_size(s->s_bdev) > 2048) { printk(KERN_WARNING "ISOFS: unsupported/invalid hardware sector size %d\n", bdev_logical_block_size(s->s_bdev)); goto out_freesbi; } opt.blocksize = sb_min_blocksize(s, opt.blocksize); sbi->s_high_sierra = 0; /* default is iso9660 */ sbi->s_session = opt.session; sbi->s_sbsector = opt.sbsector; vol_desc_start = (opt.sbsector != -1) ? opt.sbsector : isofs_get_last_session(s,opt.session); for (iso_blknum = vol_desc_start+16; iso_blknum < vol_desc_start+100; iso_blknum++) { struct hs_volume_descriptor *hdp; struct iso_volume_descriptor *vdp; block = iso_blknum << (ISOFS_BLOCK_BITS - s->s_blocksize_bits); if (!(bh = sb_bread(s, block))) goto out_no_read; vdp = (struct iso_volume_descriptor *)bh->b_data; hdp = (struct hs_volume_descriptor *)bh->b_data; /* * Due to the overlapping physical location of the descriptors, * ISO CDs can match hdp->id==HS_STANDARD_ID as well. To ensure * proper identification in this case, we first check for ISO. */ if (strncmp (vdp->id, ISO_STANDARD_ID, sizeof vdp->id) == 0) { if (isonum_711(vdp->type) == ISO_VD_END) break; if (isonum_711(vdp->type) == ISO_VD_PRIMARY) { if (!pri) { pri = (struct iso_primary_descriptor *)vdp; /* Save the buffer in case we need it ... */ pri_bh = bh; bh = NULL; } } #ifdef CONFIG_JOLIET else if (isonum_711(vdp->type) == ISO_VD_SUPPLEMENTARY) { sec = (struct iso_supplementary_descriptor *)vdp; if (sec->escape[0] == 0x25 && sec->escape[1] == 0x2f) { if (opt.joliet) { if (sec->escape[2] == 0x40) joliet_level = 1; else if (sec->escape[2] == 0x43) joliet_level = 2; else if (sec->escape[2] == 0x45) joliet_level = 3; printk(KERN_DEBUG "ISO 9660 Extensions: " "Microsoft Joliet Level %d\n", joliet_level); } goto root_found; } else { /* Unknown supplementary volume descriptor */ sec = NULL; } } #endif } else { if (strncmp (hdp->id, HS_STANDARD_ID, sizeof hdp->id) == 0) { if (isonum_711(hdp->type) != ISO_VD_PRIMARY) goto out_freebh; sbi->s_high_sierra = 1; opt.rock = 0; h_pri = (struct hs_primary_descriptor *)vdp; goto root_found; } } /* Just skip any volume descriptors we don't recognize */ brelse(bh); bh = NULL; } /* * If we fall through, either no volume descriptor was found, * or else we passed a primary descriptor looking for others. */ if (!pri) goto out_unknown_format; brelse(bh); bh = pri_bh; pri_bh = NULL; root_found: /* We don't support read-write mounts */ if (!sb_rdonly(s)) { error = -EACCES; goto out_freebh; } if (joliet_level && (!pri || !opt.rock)) { /* This is the case of Joliet with the norock mount flag. * A disc with both Joliet and Rock Ridge is handled later */ pri = (struct iso_primary_descriptor *) sec; } if(sbi->s_high_sierra){ rootp = (struct iso_directory_record *) h_pri->root_directory_record; sbi->s_nzones = isonum_733(h_pri->volume_space_size); sbi->s_log_zone_size = isonum_723(h_pri->logical_block_size); sbi->s_max_size = isonum_733(h_pri->volume_space_size); } else { if (!pri) goto out_freebh; rootp = (struct iso_directory_record *) pri->root_directory_record; sbi->s_nzones = isonum_733(pri->volume_space_size); sbi->s_log_zone_size = isonum_723(pri->logical_block_size); sbi->s_max_size = isonum_733(pri->volume_space_size); } sbi->s_ninodes = 0; /* No way to figure this out easily */ orig_zonesize = sbi->s_log_zone_size; /* * If the zone size is smaller than the hardware sector size, * this is a fatal error. This would occur if the disc drive * had sectors that were 2048 bytes, but the filesystem had * blocks that were 512 bytes (which should only very rarely * happen.) */ if (orig_zonesize < opt.blocksize) goto out_bad_size; /* RDE: convert log zone size to bit shift */ switch (sbi->s_log_zone_size) { case 512: sbi->s_log_zone_size = 9; break; case 1024: sbi->s_log_zone_size = 10; break; case 2048: sbi->s_log_zone_size = 11; break; default: goto out_bad_zone_size; } s->s_magic = ISOFS_SUPER_MAGIC; /* * With multi-extent files, file size is only limited by the maximum * size of a file system, which is 8 TB. */ s->s_maxbytes = 0x80000000000LL; /* ECMA-119 timestamp from 1900/1/1 with tz offset */ s->s_time_min = mktime64(1900, 1, 1, 0, 0, 0) - MAX_TZ_OFFSET; s->s_time_max = mktime64(U8_MAX+1900, 12, 31, 23, 59, 59) + MAX_TZ_OFFSET; /* Set this for reference. Its not currently used except on write which we don't have .. */ first_data_zone = isonum_733(rootp->extent) + isonum_711(rootp->ext_attr_length); sbi->s_firstdatazone = first_data_zone; #ifndef BEQUIET printk(KERN_DEBUG "ISOFS: Max size:%ld Log zone size:%ld\n", sbi->s_max_size, 1UL << sbi->s_log_zone_size); printk(KERN_DEBUG "ISOFS: First datazone:%ld\n", sbi->s_firstdatazone); if(sbi->s_high_sierra) printk(KERN_DEBUG "ISOFS: Disc in High Sierra format.\n"); #endif /* * If the Joliet level is set, we _may_ decide to use the * secondary descriptor, but can't be sure until after we * read the root inode. But before reading the root inode * we may need to change the device blocksize, and would * rather release the old buffer first. So, we cache the * first_data_zone value from the secondary descriptor. */ if (joliet_level) { pri = (struct iso_primary_descriptor *) sec; rootp = (struct iso_directory_record *) pri->root_directory_record; first_data_zone = isonum_733(rootp->extent) + isonum_711(rootp->ext_attr_length); } /* * We're all done using the volume descriptor, and may need * to change the device blocksize, so release the buffer now. */ brelse(pri_bh); brelse(bh); /* * Force the blocksize to 512 for 512 byte sectors. The file * read primitives really get it wrong in a bad way if we don't * do this. * * Note - we should never be setting the blocksize to something * less than the hardware sector size for the device. If we * do, we would end up having to read larger buffers and split * out portions to satisfy requests. * * Note2- the idea here is that we want to deal with the optimal * zonesize in the filesystem. If we have it set to something less, * then we have horrible problems with trying to piece together * bits of adjacent blocks in order to properly read directory * entries. By forcing the blocksize in this way, we ensure * that we will never be required to do this. */ sb_set_blocksize(s, orig_zonesize); sbi->s_nls_iocharset = NULL; #ifdef CONFIG_JOLIET if (joliet_level) { char *p = opt.iocharset ? opt.iocharset : CONFIG_NLS_DEFAULT; if (strcmp(p, "utf8") != 0) { sbi->s_nls_iocharset = opt.iocharset ? load_nls(opt.iocharset) : load_nls_default(); if (!sbi->s_nls_iocharset) goto out_freesbi; } } #endif s->s_op = &isofs_sops; s->s_export_op = &isofs_export_ops; sbi->s_mapping = opt.map; sbi->s_rock = (opt.rock ? 2 : 0); sbi->s_rock_offset = -1; /* initial offset, will guess until SP is found*/ sbi->s_cruft = opt.cruft; sbi->s_hide = opt.hide; sbi->s_showassoc = opt.showassoc; sbi->s_uid = opt.uid; sbi->s_gid = opt.gid; sbi->s_uid_set = opt.uid_set; sbi->s_gid_set = opt.gid_set; sbi->s_nocompress = opt.nocompress; sbi->s_overriderockperm = opt.overriderockperm; /* * It would be incredibly stupid to allow people to mark every file * on the disk as suid, so we merely allow them to set the default * permissions. */ if (opt.fmode != ISOFS_INVALID_MODE) sbi->s_fmode = opt.fmode & 0777; else sbi->s_fmode = ISOFS_INVALID_MODE; if (opt.dmode != ISOFS_INVALID_MODE) sbi->s_dmode = opt.dmode & 0777; else sbi->s_dmode = ISOFS_INVALID_MODE; /* * Read the root inode, which _may_ result in changing * the s_rock flag. Once we have the final s_rock value, * we then decide whether to use the Joliet descriptor. */ inode = isofs_iget(s, sbi->s_firstdatazone, 0); /* * Fix for broken CDs with a corrupt root inode but a correct Joliet * root directory. */ if (IS_ERR(inode)) { if (joliet_level && sbi->s_firstdatazone != first_data_zone) { printk(KERN_NOTICE "ISOFS: root inode is unusable. " "Disabling Rock Ridge and switching to Joliet."); sbi->s_rock = 0; inode = NULL; } else { goto out_no_root; } } /* * Fix for broken CDs with Rock Ridge and empty ISO root directory but * correct Joliet root directory. */ if (sbi->s_rock == 1 && joliet_level && rootdir_empty(s, sbi->s_firstdatazone)) { printk(KERN_NOTICE "ISOFS: primary root directory is empty. " "Disabling Rock Ridge and switching to Joliet."); sbi->s_rock = 0; } /* * If this disk has both Rock Ridge and Joliet on it, then we * want to use Rock Ridge by default. This can be overridden * by using the norock mount option. There is still one other * possibility that is not taken into account: a Rock Ridge * CD with Unicode names. Until someone sees such a beast, it * will not be supported. */ if (sbi->s_rock == 1) { joliet_level = 0; } else if (joliet_level) { sbi->s_rock = 0; if (sbi->s_firstdatazone != first_data_zone) { sbi->s_firstdatazone = first_data_zone; printk(KERN_DEBUG "ISOFS: changing to secondary root\n"); iput(inode); inode = isofs_iget(s, sbi->s_firstdatazone, 0); if (IS_ERR(inode)) goto out_no_root; } } if (opt.check == 'u') { /* Only Joliet is case insensitive by default */ if (joliet_level) opt.check = 'r'; else opt.check = 's'; } sbi->s_joliet_level = joliet_level; /* Make sure the root inode is a directory */ if (!S_ISDIR(inode->i_mode)) { printk(KERN_WARNING "isofs_fill_super: root inode is not a directory. " "Corrupted media?\n"); goto out_iput; } table = 0; if (joliet_level) table += 2; if (opt.check == 'r') table++; sbi->s_check = opt.check; if (table) s->s_d_op = &isofs_dentry_ops[table - 1]; /* get the root dentry */ s->s_root = d_make_root(inode); if (!(s->s_root)) { error = -ENOMEM; goto out_no_inode; } kfree(opt.iocharset); return 0; /* * Display error messages and free resources. */ out_iput: iput(inode); goto out_no_inode; out_no_root: error = PTR_ERR(inode); if (error != -ENOMEM) printk(KERN_WARNING "%s: get root inode failed\n", __func__); out_no_inode: #ifdef CONFIG_JOLIET unload_nls(sbi->s_nls_iocharset); #endif goto out_freesbi; out_no_read: printk(KERN_WARNING "%s: bread failed, dev=%s, iso_blknum=%d, block=%d\n", __func__, s->s_id, iso_blknum, block); goto out_freebh; out_bad_zone_size: printk(KERN_WARNING "ISOFS: Bad logical zone size %ld\n", sbi->s_log_zone_size); goto out_freebh; out_bad_size: printk(KERN_WARNING "ISOFS: Logical zone size(%d) < hardware blocksize(%u)\n", orig_zonesize, opt.blocksize); goto out_freebh; out_unknown_format: if (!silent) printk(KERN_WARNING "ISOFS: Unable to identify CD-ROM format.\n"); out_freebh: brelse(bh); brelse(pri_bh); out_freesbi: kfree(opt.iocharset); kfree(sbi); s->s_fs_info = NULL; return error; } static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = ISOFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = (ISOFS_SB(sb)->s_nzones << (ISOFS_SB(sb)->s_log_zone_size - sb->s_blocksize_bits)); buf->f_bfree = 0; buf->f_bavail = 0; buf->f_files = ISOFS_SB(sb)->s_ninodes; buf->f_ffree = 0; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = NAME_MAX; return 0; } /* * Get a set of blocks; filling in buffer_heads if already allocated * or getblk() if they are not. Returns the number of blocks inserted * (-ve == error.) */ int isofs_get_blocks(struct inode *inode, sector_t iblock, struct buffer_head **bh, unsigned long nblocks) { unsigned long b_off = iblock; unsigned offset, sect_size; unsigned int firstext; unsigned long nextblk, nextoff; int section, rv, error; struct iso_inode_info *ei = ISOFS_I(inode); error = -EIO; rv = 0; if (iblock != b_off) { printk(KERN_DEBUG "%s: block number too large\n", __func__); goto abort; } offset = 0; firstext = ei->i_first_extent; sect_size = ei->i_section_size >> ISOFS_BUFFER_BITS(inode); nextblk = ei->i_next_section_block; nextoff = ei->i_next_section_offset; section = 0; while (nblocks) { /* If we are *way* beyond the end of the file, print a message. * Access beyond the end of the file up to the next page boundary * is normal, however because of the way the page cache works. * In this case, we just return 0 so that we can properly fill * the page with useless information without generating any * I/O errors. */ if (b_off > ((inode->i_size + PAGE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) { printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n", __func__, b_off, (unsigned long long)inode->i_size); goto abort; } /* On the last section, nextblk == 0, section size is likely to * exceed sect_size by a partial block, and access beyond the * end of the file will reach beyond the section size, too. */ while (nextblk && (b_off >= (offset + sect_size))) { struct inode *ninode; offset += sect_size; ninode = isofs_iget(inode->i_sb, nextblk, nextoff); if (IS_ERR(ninode)) { error = PTR_ERR(ninode); goto abort; } firstext = ISOFS_I(ninode)->i_first_extent; sect_size = ISOFS_I(ninode)->i_section_size >> ISOFS_BUFFER_BITS(ninode); nextblk = ISOFS_I(ninode)->i_next_section_block; nextoff = ISOFS_I(ninode)->i_next_section_offset; iput(ninode); if (++section > 100) { printk(KERN_DEBUG "%s: More than 100 file sections ?!?" " aborting...\n", __func__); printk(KERN_DEBUG "%s: block=%lu firstext=%u sect_size=%u " "nextblk=%lu nextoff=%lu\n", __func__, b_off, firstext, (unsigned) sect_size, nextblk, nextoff); goto abort; } } if (*bh) { map_bh(*bh, inode->i_sb, firstext + b_off - offset); } else { *bh = sb_getblk(inode->i_sb, firstext+b_off-offset); if (!*bh) goto abort; } bh++; /* Next buffer head */ b_off++; /* Next buffer offset */ nblocks--; rv++; } error = 0; abort: return rv != 0 ? rv : error; } /* * Used by the standard interfaces. */ static int isofs_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret; if (create) { printk(KERN_DEBUG "%s: Kernel tries to allocate a block\n", __func__); return -EROFS; } ret = isofs_get_blocks(inode, iblock, &bh_result, 1); return ret < 0 ? ret : 0; } static int isofs_bmap(struct inode *inode, sector_t block) { struct buffer_head dummy; int error; dummy.b_state = 0; dummy.b_blocknr = -1000; error = isofs_get_block(inode, block, &dummy, 0); if (!error) return dummy.b_blocknr; return 0; } struct buffer_head *isofs_bread(struct inode *inode, sector_t block) { sector_t blknr = isofs_bmap(inode, block); if (!blknr) return NULL; return sb_bread(inode->i_sb, blknr); } static int isofs_readpage(struct file *file, struct page *page) { return mpage_readpage(page, isofs_get_block); } static void isofs_readahead(struct readahead_control *rac) { mpage_readahead(rac, isofs_get_block); } static sector_t _isofs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping,block,isofs_get_block); } static const struct address_space_operations isofs_aops = { .readpage = isofs_readpage, .readahead = isofs_readahead, .bmap = _isofs_bmap }; static int isofs_read_level3_size(struct inode *inode) { unsigned long bufsize = ISOFS_BUFFER_SIZE(inode); int high_sierra = ISOFS_SB(inode->i_sb)->s_high_sierra; struct buffer_head *bh = NULL; unsigned long block, offset, block_saved, offset_saved; int i = 0; int more_entries = 0; struct iso_directory_record *tmpde = NULL; struct iso_inode_info *ei = ISOFS_I(inode); inode->i_size = 0; /* The first 16 blocks are reserved as the System Area. Thus, * no inodes can appear in block 0. We use this to flag that * this is the last section. */ ei->i_next_section_block = 0; ei->i_next_section_offset = 0; block = ei->i_iget5_block; offset = ei->i_iget5_offset; do { struct iso_directory_record *de; unsigned int de_len; if (!bh) { bh = sb_bread(inode->i_sb, block); if (!bh) goto out_noread; } de = (struct iso_directory_record *) (bh->b_data + offset); de_len = *(unsigned char *) de; if (de_len == 0) { brelse(bh); bh = NULL; ++block; offset = 0; continue; } block_saved = block; offset_saved = offset; offset += de_len; /* Make sure we have a full directory entry */ if (offset >= bufsize) { int slop = bufsize - offset + de_len; if (!tmpde) { tmpde = kmalloc(256, GFP_KERNEL); if (!tmpde) goto out_nomem; } memcpy(tmpde, de, slop); offset &= bufsize - 1; block++; brelse(bh); bh = NULL; if (offset) { bh = sb_bread(inode->i_sb, block); if (!bh) goto out_noread; memcpy((void *)tmpde+slop, bh->b_data, offset); } de = tmpde; } inode->i_size += isonum_733(de->size); if (i == 1) { ei->i_next_section_block = block_saved; ei->i_next_section_offset = offset_saved; } more_entries = de->flags[-high_sierra] & 0x80; i++; if (i > 100) goto out_toomany; } while (more_entries); out: kfree(tmpde); if (bh) brelse(bh); return 0; out_nomem: if (bh) brelse(bh); return -ENOMEM; out_noread: printk(KERN_INFO "ISOFS: unable to read i-node block %lu\n", block); kfree(tmpde); return -EIO; out_toomany: printk(KERN_INFO "%s: More than 100 file sections ?!?, aborting...\n" "isofs_read_level3_size: inode=%lu\n", __func__, inode->i_ino); goto out; } static int isofs_read_inode(struct inode *inode, int relocated) { struct super_block *sb = inode->i_sb; struct isofs_sb_info *sbi = ISOFS_SB(sb); unsigned long bufsize = ISOFS_BUFFER_SIZE(inode); unsigned long block; int high_sierra = sbi->s_high_sierra; struct buffer_head *bh; struct iso_directory_record *de; struct iso_directory_record *tmpde = NULL; unsigned int de_len; unsigned long offset; struct iso_inode_info *ei = ISOFS_I(inode); int ret = -EIO; block = ei->i_iget5_block; bh = sb_bread(inode->i_sb, block); if (!bh) goto out_badread; offset = ei->i_iget5_offset; de = (struct iso_directory_record *) (bh->b_data + offset); de_len = *(unsigned char *) de; if (de_len < sizeof(struct iso_directory_record)) goto fail; if (offset + de_len > bufsize) { int frag1 = bufsize - offset; tmpde = kmalloc(de_len, GFP_KERNEL); if (!tmpde) { ret = -ENOMEM; goto fail; } memcpy(tmpde, bh->b_data + offset, frag1); brelse(bh); bh = sb_bread(inode->i_sb, ++block); if (!bh) goto out_badread; memcpy((char *)tmpde+frag1, bh->b_data, de_len - frag1); de = tmpde; } inode->i_ino = isofs_get_ino(ei->i_iget5_block, ei->i_iget5_offset, ISOFS_BUFFER_BITS(inode)); /* Assume it is a normal-format file unless told otherwise */ ei->i_file_format = isofs_file_normal; if (de->flags[-high_sierra] & 2) { if (sbi->s_dmode != ISOFS_INVALID_MODE) inode->i_mode = S_IFDIR | sbi->s_dmode; else inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; set_nlink(inode, 1); /* * Set to 1. We know there are 2, but * the find utility tries to optimize * if it is 2, and it screws up. It is * easier to give 1 which tells find to * do it the hard way. */ } else { if (sbi->s_fmode != ISOFS_INVALID_MODE) { inode->i_mode = S_IFREG | sbi->s_fmode; } else { /* * Set default permissions: r-x for all. The disc * could be shared with DOS machines so virtually * anything could be a valid executable. */ inode->i_mode = S_IFREG | S_IRUGO | S_IXUGO; } set_nlink(inode, 1); } inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; inode->i_blocks = 0; ei->i_format_parm[0] = 0; ei->i_format_parm[1] = 0; ei->i_format_parm[2] = 0; ei->i_section_size = isonum_733(de->size); if (de->flags[-high_sierra] & 0x80) { ret = isofs_read_level3_size(inode); if (ret < 0) goto fail; ret = -EIO; } else { ei->i_next_section_block = 0; ei->i_next_section_offset = 0; inode->i_size = isonum_733(de->size); } /* * Some dipshit decided to store some other bit of information * in the high byte of the file length. Truncate size in case * this CDROM was mounted with the cruft option. */ if (sbi->s_cruft) inode->i_size &= 0x00ffffff; if (de->interleave[0]) { printk(KERN_DEBUG "ISOFS: Interleaved files not (yet) supported.\n"); inode->i_size = 0; } /* I have no idea what file_unit_size is used for, so we will flag it for now */ if (de->file_unit_size[0] != 0) { printk(KERN_DEBUG "ISOFS: File unit size != 0 for ISO file (%ld).\n", inode->i_ino); } /* I have no idea what other flag bits are used for, so we will flag it for now */ #ifdef DEBUG if((de->flags[-high_sierra] & ~2)!= 0){ printk(KERN_DEBUG "ISOFS: Unusual flag settings for ISO file " "(%ld %x).\n", inode->i_ino, de->flags[-high_sierra]); } #endif inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = iso_date(de->date, high_sierra); inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0; ei->i_first_extent = (isonum_733(de->extent) + isonum_711(de->ext_attr_length)); /* Set the number of blocks for stat() - should be done before RR */ inode->i_blocks = (inode->i_size + 511) >> 9; /* * Now test for possible Rock Ridge extensions which will override * some of these numbers in the inode structure. */ if (!high_sierra) { parse_rock_ridge_inode(de, inode, relocated); /* if we want uid/gid set, override the rock ridge setting */ if (sbi->s_uid_set) inode->i_uid = sbi->s_uid; if (sbi->s_gid_set) inode->i_gid = sbi->s_gid; } /* Now set final access rights if overriding rock ridge setting */ if (S_ISDIR(inode->i_mode) && sbi->s_overriderockperm && sbi->s_dmode != ISOFS_INVALID_MODE) inode->i_mode = S_IFDIR | sbi->s_dmode; if (S_ISREG(inode->i_mode) && sbi->s_overriderockperm && sbi->s_fmode != ISOFS_INVALID_MODE) inode->i_mode = S_IFREG | sbi->s_fmode; /* Install the inode operations vector */ if (S_ISREG(inode->i_mode)) { inode->i_fop = &generic_ro_fops; switch (ei->i_file_format) { #ifdef CONFIG_ZISOFS case isofs_file_compressed: inode->i_data.a_ops = &zisofs_aops; break; #endif default: inode->i_data.a_ops = &isofs_aops; break; } } else if (S_ISDIR(inode->i_mode)) { inode->i_op = &isofs_dir_inode_operations; inode->i_fop = &isofs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ init_special_inode(inode, inode->i_mode, inode->i_rdev); } else { printk(KERN_DEBUG "ISOFS: Invalid file type 0%04o for inode %lu.\n", inode->i_mode, inode->i_ino); ret = -EIO; goto fail; } ret = 0; out: kfree(tmpde); if (bh) brelse(bh); return ret; out_badread: printk(KERN_WARNING "ISOFS: unable to read i-node block\n"); fail: goto out; } struct isofs_iget5_callback_data { unsigned long block; unsigned long offset; }; static int isofs_iget5_test(struct inode *ino, void *data) { struct iso_inode_info *i = ISOFS_I(ino); struct isofs_iget5_callback_data *d = (struct isofs_iget5_callback_data*)data; return (i->i_iget5_block == d->block) && (i->i_iget5_offset == d->offset); } static int isofs_iget5_set(struct inode *ino, void *data) { struct iso_inode_info *i = ISOFS_I(ino); struct isofs_iget5_callback_data *d = (struct isofs_iget5_callback_data*)data; i->i_iget5_block = d->block; i->i_iget5_offset = d->offset; return 0; } /* Store, in the inode's containing structure, the block and block * offset that point to the underlying meta-data for the inode. The * code below is otherwise similar to the iget() code in * include/linux/fs.h */ struct inode *__isofs_iget(struct super_block *sb, unsigned long block, unsigned long offset, int relocated) { unsigned long hashval; struct inode *inode; struct isofs_iget5_callback_data data; long ret; if (offset >= 1ul << sb->s_blocksize_bits) return ERR_PTR(-EINVAL); data.block = block; data.offset = offset; hashval = (block << sb->s_blocksize_bits) | offset; inode = iget5_locked(sb, hashval, &isofs_iget5_test, &isofs_iget5_set, &data); if (!inode) return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { ret = isofs_read_inode(inode, relocated); if (ret < 0) { iget_failed(inode); inode = ERR_PTR(ret); } else { unlock_new_inode(inode); } } return inode; } static struct dentry *isofs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super); } static struct file_system_type iso9660_fs_type = { .owner = THIS_MODULE, .name = "iso9660", .mount = isofs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("iso9660"); MODULE_ALIAS("iso9660"); static int __init init_iso9660_fs(void) { int err = init_inodecache(); if (err) goto out; #ifdef CONFIG_ZISOFS err = zisofs_init(); if (err) goto out1; #endif err = register_filesystem(&iso9660_fs_type); if (err) goto out2; return 0; out2: #ifdef CONFIG_ZISOFS zisofs_cleanup(); out1: #endif destroy_inodecache(); out: return err; } static void __exit exit_iso9660_fs(void) { unregister_filesystem(&iso9660_fs_type); #ifdef CONFIG_ZISOFS zisofs_cleanup(); #endif destroy_inodecache(); } module_init(init_iso9660_fs) module_exit(exit_iso9660_fs) MODULE_LICENSE("GPL"); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> #include <linux/cleanup.h> struct file; extern void fput(struct file *); extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { if (fput_needed) fput(file); } struct fd { struct file *file; unsigned int flags; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 static inline void fdput(struct fd fd) { if (fd.flags & FDPUT_FPUT) fput(fd.file); } extern struct file *fget(unsigned int fd); extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); extern unsigned long __fdget_pos(unsigned int fd); extern void __f_unlock_pos(struct file *); static inline struct fd __to_fd(unsigned long v) { return (struct fd){(struct file *)(v & ~3),v & 3}; } static inline struct fd fdget(unsigned int fd) { return __to_fd(__fdget(fd)); } static inline struct fd fdget_raw(unsigned int fd) { return __to_fd(__fdget_raw(fd)); } static inline struct fd fdget_pos(int fd) { return __to_fd(__fdget_pos(fd)); } static inline void fdput_pos(struct fd f) { if (f.flags & FDPUT_POS_UNLOCK) __f_unlock_pos(f.file); fdput(f); } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; return __receive_fd(-1, file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { return __receive_fd(-1, file, NULL, o_flags); } static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) { return __receive_fd(fd, file, NULL, o_flags); } extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; #endif /* __LINUX_FILE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/core.c - core driver model code (device registration, etc) * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2006 Novell, Inc. */ #include <linux/acpi.h> #include <linux/cpufreq.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fwnode.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/notifier.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/genhd.h> #include <linux/mutex.h> #include <linux/pm_runtime.h> #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/sysfs.h> #include "base.h" #include "power/power.h" #ifdef CONFIG_SYSFS_DEPRECATED #ifdef CONFIG_SYSFS_DEPRECATED_V2 long sysfs_deprecated = 1; #else long sysfs_deprecated = 0; #endif static int __init sysfs_deprecated_setup(char *arg) { return kstrtol(arg, 10, &sysfs_deprecated); } early_param("sysfs.deprecated", sysfs_deprecated_setup); #endif /* Device links support. */ static LIST_HEAD(wait_for_suppliers); static DEFINE_MUTEX(wfs_lock); static LIST_HEAD(deferred_sync); static unsigned int defer_sync_state_count = 1; static unsigned int defer_fw_devlink_count; static LIST_HEAD(deferred_fw_devlink); static DEFINE_MUTEX(defer_fw_devlink_lock); static struct workqueue_struct *device_link_wq; static bool fw_devlink_is_permissive(void); #ifdef CONFIG_SRCU static DEFINE_MUTEX(device_links_lock); DEFINE_STATIC_SRCU(device_links_srcu); static inline void device_links_write_lock(void) { mutex_lock(&device_links_lock); } static inline void device_links_write_unlock(void) { mutex_unlock(&device_links_lock); } int device_links_read_lock(void) __acquires(&device_links_srcu) { return srcu_read_lock(&device_links_srcu); } void device_links_read_unlock(int idx) __releases(&device_links_srcu) { srcu_read_unlock(&device_links_srcu, idx); } int device_links_read_lock_held(void) { return srcu_read_lock_held(&device_links_srcu); } static void device_link_synchronize_removal(void) { synchronize_srcu(&device_links_srcu); } #else /* !CONFIG_SRCU */ static DECLARE_RWSEM(device_links_lock); static inline void device_links_write_lock(void) { down_write(&device_links_lock); } static inline void device_links_write_unlock(void) { up_write(&device_links_lock); } int device_links_read_lock(void) { down_read(&device_links_lock); return 0; } void device_links_read_unlock(int not_used) { up_read(&device_links_lock); } #ifdef CONFIG_DEBUG_LOCK_ALLOC int device_links_read_lock_held(void) { return lockdep_is_held(&device_links_lock); } #endif static inline void device_link_synchronize_removal(void) { } #endif /* !CONFIG_SRCU */ static bool device_is_ancestor(struct device *dev, struct device *target) { while (target->parent) { target = target->parent; if (dev == target) return true; } return false; } /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. * @target: Device to check against. * * Check if @target depends on @dev or any device dependent on it (its child or * its consumer etc). Return 1 if that is the case or 0 otherwise. */ int device_is_dependent(struct device *dev, void *target) { struct device_link *link; int ret; /* * The "ancestors" check is needed to catch the case when the target * device has not been completely initialized yet and it is still * missing from the list of children of its parent device. */ if (dev == target || device_is_ancestor(dev, target)) return 1; ret = device_for_each_child(dev, target, device_is_dependent); if (ret) return ret; list_for_each_entry(link, &dev->links.consumers, s_node) { if (link->flags == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; if (link->consumer == target) return 1; ret = device_is_dependent(link->consumer, target); if (ret) break; } return ret; } static void device_link_init_status(struct device_link *link, struct device *consumer, struct device *supplier) { switch (supplier->links.status) { case DL_DEV_PROBING: switch (consumer->links.status) { case DL_DEV_PROBING: /* * A consumer driver can create a link to a supplier * that has not completed its probing yet as long as it * knows that the supplier is already functional (for * example, it has just acquired some resources from the * supplier). */ link->status = DL_STATE_CONSUMER_PROBE; break; default: link->status = DL_STATE_DORMANT; break; } break; case DL_DEV_DRIVER_BOUND: switch (consumer->links.status) { case DL_DEV_PROBING: link->status = DL_STATE_CONSUMER_PROBE; break; case DL_DEV_DRIVER_BOUND: link->status = DL_STATE_ACTIVE; break; default: link->status = DL_STATE_AVAILABLE; break; } break; case DL_DEV_UNBINDING: link->status = DL_STATE_SUPPLIER_UNBIND; break; default: link->status = DL_STATE_DORMANT; break; } } static int device_reorder_to_tail(struct device *dev, void *not_used) { struct device_link *link; /* * Devices that have not been registered yet will be put to the ends * of the lists during the registration, so skip them here. */ if (device_is_registered(dev)) devices_kset_move_last(dev); if (device_pm_initialized(dev)) device_pm_move_last(dev); device_for_each_child(dev, NULL, device_reorder_to_tail); list_for_each_entry(link, &dev->links.consumers, s_node) { if (link->flags == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; device_reorder_to_tail(link->consumer, NULL); } return 0; } /** * device_pm_move_to_tail - Move set of devices to the end of device lists * @dev: Device to move * * This is a device_reorder_to_tail() wrapper taking the requisite locks. * * It moves the @dev along with all of its children and all of its consumers * to the ends of the device_kset and dpm_list, recursively. */ void device_pm_move_to_tail(struct device *dev) { int idx; idx = device_links_read_lock(); device_pm_lock(); device_reorder_to_tail(dev, NULL); device_pm_unlock(); device_links_read_unlock(idx); } #define to_devlink(dev) container_of((dev), struct device_link, link_dev) static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; switch (to_devlink(dev)->status) { case DL_STATE_NONE: output = "not tracked"; break; case DL_STATE_DORMANT: output = "dormant"; break; case DL_STATE_AVAILABLE: output = "available"; break; case DL_STATE_CONSUMER_PROBE: output = "consumer probing"; break; case DL_STATE_ACTIVE: output = "active"; break; case DL_STATE_SUPPLIER_UNBIND: output = "supplier unbinding"; break; default: output = "unknown"; break; } return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(status); static ssize_t auto_remove_on_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); const char *output; if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) output = "supplier unbind"; else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) output = "consumer unbind"; else output = "never"; return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(auto_remove_on); static ssize_t runtime_pm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME)); } static DEVICE_ATTR_RO(runtime_pm); static ssize_t sync_state_only_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); } static DEVICE_ATTR_RO(sync_state_only); static struct attribute *devlink_attrs[] = { &dev_attr_status.attr, &dev_attr_auto_remove_on.attr, &dev_attr_runtime_pm.attr, &dev_attr_sync_state_only.attr, NULL, }; ATTRIBUTE_GROUPS(devlink); static void device_link_release_fn(struct work_struct *work) { struct device_link *link = container_of(work, struct device_link, rm_work); /* Ensure that all references to the link object have been dropped. */ device_link_synchronize_removal(); pm_runtime_release_supplier(link); pm_request_idle(link->supplier); put_device(link->consumer); put_device(link->supplier); kfree(link); } static void devlink_dev_release(struct device *dev) { struct device_link *link = to_devlink(dev); INIT_WORK(&link->rm_work, device_link_release_fn); /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or * supplier devices get deleted when it runs, so put it into the * dedicated workqueue. */ queue_work(device_link_wq, &link->rm_work); } /** * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate */ void device_link_wait_removal(void) { /* * devlink removal jobs are queued in the dedicated work queue. * To be sure that all removal jobs are terminated, ensure that any * scheduled work has run to completion. */ flush_workqueue(device_link_wq); } EXPORT_SYMBOL_GPL(device_link_wait_removal); static struct class devlink_class = { .name = "devlink", .owner = THIS_MODULE, .dev_groups = devlink_groups, .dev_release = devlink_dev_release, }; static int devlink_add_symlinks(struct device *dev, struct class_interface *class_intf) { int ret; size_t len; struct device_link *link = to_devlink(dev); struct device *sup = link->supplier; struct device *con = link->consumer; char *buf; len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), strlen(dev_bus_name(con)) + strlen(dev_name(con))); len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier"); if (ret) goto out; ret = sysfs_create_link(&link->link_dev.kobj, &con->kobj, "consumer"); if (ret) goto err_con; snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); if (ret) goto err_con_dev; snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); if (ret) goto err_sup_dev; goto out; err_sup_dev: snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); err_con: sysfs_remove_link(&link->link_dev.kobj, "supplier"); out: kfree(buf); return ret; } static void devlink_remove_symlinks(struct device *dev, struct class_interface *class_intf) { struct device_link *link = to_devlink(dev); size_t len; struct device *sup = link->supplier; struct device *con = link->consumer; char *buf; sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), strlen(dev_bus_name(con)) + strlen(dev_name(con))); len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) { WARN(1, "Unable to properly free device link symlinks!\n"); return; } if (device_is_registered(con)) { snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); sysfs_remove_link(&con->kobj, buf); } snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); kfree(buf); } static struct class_interface devlink_class_intf = { .class = &devlink_class, .add_dev = devlink_add_symlinks, .remove_dev = devlink_remove_symlinks, }; static int __init devlink_class_init(void) { int ret; ret = class_register(&devlink_class); if (ret) return ret; ret = class_interface_register(&devlink_class_intf); if (ret) class_unregister(&devlink_class); return ret; } postcore_initcall(devlink_class_init); #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ DL_FLAG_AUTOREMOVE_SUPPLIER | \ DL_FLAG_AUTOPROBE_CONSUMER | \ DL_FLAG_SYNC_STATE_ONLY) #define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE) /** * device_link_add - Create a link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * @flags: Link flags. * * The caller is responsible for the proper synchronization of the link creation * with runtime PM. First, setting the DL_FLAG_PM_RUNTIME flag will cause the * runtime PM framework to take the link into account. Second, if the * DL_FLAG_RPM_ACTIVE flag is set in addition to it, the supplier devices will * be forced into the active metastate and reference-counted upon the creation * of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be * ignored. * * If DL_FLAG_STATELESS is set in @flags, the caller of this function is * expected to release the link returned by it directly with the help of either * device_link_del() or device_link_remove(). * * If that flag is not set, however, the caller of this function is handing the * management of the link over to the driver core entirely and its return value * can only be used to check whether or not the link is present. In that case, * the DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_AUTOREMOVE_SUPPLIER device link * flags can be used to indicate to the driver core when the link can be safely * deleted. Namely, setting one of them in @flags indicates to the driver core * that the link is not going to be used (by the given caller of this function) * after unbinding the consumer or supplier driver, respectively, from its * device, so the link can be deleted at that point. If none of them is set, * the link will be maintained until one of the devices pointed to by it (either * the consumer or the supplier) is unregistered. * * Also, if DL_FLAG_STATELESS, DL_FLAG_AUTOREMOVE_CONSUMER and * DL_FLAG_AUTOREMOVE_SUPPLIER are not set in @flags (that is, a persistent * managed device link is being added), the DL_FLAG_AUTOPROBE_CONSUMER flag can * be used to request the driver core to automaticall probe for a consmer * driver after successfully binding a driver to the supplier device. * * The combination of DL_FLAG_STATELESS and one of DL_FLAG_AUTOREMOVE_CONSUMER, * DL_FLAG_AUTOREMOVE_SUPPLIER, or DL_FLAG_AUTOPROBE_CONSUMER set in @flags at * the same time is invalid and will cause NULL to be returned upfront. * However, if a device link between the given @consumer and @supplier pair * exists already when this function is called for them, the existing link will * be returned regardless of its current type and status (the link's flags may * be modified then). The caller of this function is then expected to treat * the link as though it has just been created, so (in particular) if * DL_FLAG_STATELESS was passed in @flags, the link needs to be released * explicitly when not needed any more (as stated above). * * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). * * The supplier device is required to be registered when this function is called * and NULL will be returned if that is not the case. The consumer device need * not be registered, however. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags) { struct device_link *link; if (!consumer || !supplier || consumer == supplier || flags & ~DL_ADD_VALID_FLAGS || (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || (flags & DL_FLAG_SYNC_STATE_ONLY && flags != DL_FLAG_SYNC_STATE_ONLY) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) return NULL; if (flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) { if (pm_runtime_get_sync(supplier) < 0) { pm_runtime_put_noidle(supplier); return NULL; } } if (!(flags & DL_FLAG_STATELESS)) flags |= DL_FLAG_MANAGED; device_links_write_lock(); device_pm_lock(); /* * If the supplier has not been fully registered yet or there is a * reverse (non-SYNC_STATE_ONLY) dependency between the consumer and * the supplier already in the graph, return NULL. If the link is a * SYNC_STATE_ONLY link, we don't check for reverse dependencies * because it only affects sync_state() callbacks. */ if (!device_pm_initialized(supplier) || (!(flags & DL_FLAG_SYNC_STATE_ONLY) && device_is_dependent(consumer, supplier))) { link = NULL; goto out; } /* * DL_FLAG_AUTOREMOVE_SUPPLIER indicates that the link will be needed * longer than for DL_FLAG_AUTOREMOVE_CONSUMER and setting them both * together doesn't make sense, so prefer DL_FLAG_AUTOREMOVE_SUPPLIER. */ if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer != consumer) continue; if (flags & DL_FLAG_PM_RUNTIME) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) { pm_runtime_new_link(consumer); link->flags |= DL_FLAG_PM_RUNTIME; } if (flags & DL_FLAG_RPM_ACTIVE) refcount_inc(&link->rpm_active); } if (flags & DL_FLAG_STATELESS) { kref_get(&link->kref); if (link->flags & DL_FLAG_SYNC_STATE_ONLY && !(link->flags & DL_FLAG_STATELESS)) { link->flags |= DL_FLAG_STATELESS; goto reorder; } else { link->flags |= DL_FLAG_STATELESS; goto out; } } /* * If the life time of the link following from the new flags is * longer than indicated by the flags of the existing link, * update the existing link to stay around longer. */ if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) { if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { link->flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER; } } else if (!(flags & DL_FLAG_AUTOREMOVE_CONSUMER)) { link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER); } if (!(link->flags & DL_FLAG_MANAGED)) { kref_get(&link->kref); link->flags |= DL_FLAG_MANAGED; device_link_init_status(link, consumer, supplier); } if (link->flags & DL_FLAG_SYNC_STATE_ONLY && !(flags & DL_FLAG_SYNC_STATE_ONLY)) { link->flags &= ~DL_FLAG_SYNC_STATE_ONLY; goto reorder; } goto out; } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) goto out; refcount_set(&link->rpm_active, 1); get_device(supplier); link->supplier = supplier; INIT_LIST_HEAD(&link->s_node); get_device(consumer); link->consumer = consumer; INIT_LIST_HEAD(&link->c_node); link->flags = flags; kref_init(&link->kref); link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); dev_set_name(&link->link_dev, "%s:%s--%s:%s", dev_bus_name(supplier), dev_name(supplier), dev_bus_name(consumer), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(&link->link_dev); link = NULL; goto out; } if (flags & DL_FLAG_PM_RUNTIME) { if (flags & DL_FLAG_RPM_ACTIVE) refcount_inc(&link->rpm_active); pm_runtime_new_link(consumer); } /* Determine the initial link state. */ if (flags & DL_FLAG_STATELESS) link->status = DL_STATE_NONE; else device_link_init_status(link, consumer, supplier); /* * Some callers expect the link creation during consumer driver probe to * resume the supplier even without DL_FLAG_RPM_ACTIVE. */ if (link->status == DL_STATE_CONSUMER_PROBE && flags & DL_FLAG_PM_RUNTIME) pm_runtime_resume(supplier); list_add_tail_rcu(&link->s_node, &supplier->links.consumers); list_add_tail_rcu(&link->c_node, &consumer->links.suppliers); if (flags & DL_FLAG_SYNC_STATE_ONLY) { dev_dbg(consumer, "Linked as a sync state only consumer to %s\n", dev_name(supplier)); goto out; } reorder: /* * Move the consumer and all of the devices depending on it to the end * of dpm_list and the devices_kset list. * * It is necessary to hold dpm_list locked throughout all that or else * we may end up suspending with a wrong ordering of it. */ device_reorder_to_tail(consumer, NULL); dev_dbg(consumer, "Linked as a consumer to %s\n", dev_name(supplier)); out: device_pm_unlock(); device_links_write_unlock(); if ((flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) && !link) pm_runtime_put(supplier); return link; } EXPORT_SYMBOL_GPL(device_link_add); /** * device_link_wait_for_supplier - Add device to wait_for_suppliers list * @consumer: Consumer device * * Marks the @consumer device as waiting for suppliers to become available by * adding it to the wait_for_suppliers list. The consumer device will never be * probed until it's removed from the wait_for_suppliers list. * * The caller is responsible for adding the links to the supplier devices once * they are available and removing the @consumer device from the * wait_for_suppliers list once links to all the suppliers have been created. * * This function is NOT meant to be called from the probe function of the * consumer but rather from code that creates/adds the consumer device. */ static void device_link_wait_for_supplier(struct device *consumer, bool need_for_probe) { mutex_lock(&wfs_lock); list_add_tail(&consumer->links.needs_suppliers, &wait_for_suppliers); consumer->links.need_for_probe = need_for_probe; mutex_unlock(&wfs_lock); } static void device_link_wait_for_mandatory_supplier(struct device *consumer) { device_link_wait_for_supplier(consumer, true); } static void device_link_wait_for_optional_supplier(struct device *consumer) { device_link_wait_for_supplier(consumer, false); } /** * device_link_add_missing_supplier_links - Add links from consumer devices to * supplier devices, leaving any * consumer with inactive suppliers on * the wait_for_suppliers list * * Loops through all consumers waiting on suppliers and tries to add all their * supplier links. If that succeeds, the consumer device is removed from * wait_for_suppliers list. Otherwise, they are left in the wait_for_suppliers * list. Devices left on the wait_for_suppliers list will not be probed. * * The fwnode add_links callback is expected to return 0 if it has found and * added all the supplier links for the consumer device. It should return an * error if it isn't able to do so. * * The caller of device_link_wait_for_supplier() is expected to call this once * it's aware of potential suppliers becoming available. */ static void device_link_add_missing_supplier_links(void) { struct device *dev, *tmp; mutex_lock(&wfs_lock); list_for_each_entry_safe(dev, tmp, &wait_for_suppliers, links.needs_suppliers) { int ret = fwnode_call_int_op(dev->fwnode, add_links, dev); if (!ret) list_del_init(&dev->links.needs_suppliers); else if (ret != -ENODEV || fw_devlink_is_permissive()) dev->links.need_for_probe = false; } mutex_unlock(&wfs_lock); } #ifdef CONFIG_SRCU static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); dev_dbg(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); pm_runtime_drop_link(link); list_del_rcu(&link->s_node); list_del_rcu(&link->c_node); device_unregister(&link->link_dev); } #else /* !CONFIG_SRCU */ static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); dev_info(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); pm_runtime_drop_link(link); list_del(&link->s_node); list_del(&link->c_node); device_unregister(&link->link_dev); } #endif /* !CONFIG_SRCU */ static void device_link_put_kref(struct device_link *link) { if (link->flags & DL_FLAG_STATELESS) kref_put(&link->kref, __device_link_del); else WARN(1, "Unable to drop a managed device link reference\n"); } /** * device_link_del - Delete a stateless link between two devices. * @link: Device link to delete. * * The caller must ensure proper synchronization of this function with runtime * PM. If the link was added multiple times, it needs to be deleted as often. * Care is required for hotplugged devices: Their links are purged on removal * and calling device_link_del() is then no longer allowed. */ void device_link_del(struct device_link *link) { device_links_write_lock(); device_link_put_kref(link); device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_del); /** * device_link_remove - Delete a stateless link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * * The caller must ensure proper synchronization of this function with runtime * PM. */ void device_link_remove(void *consumer, struct device *supplier) { struct device_link *link; if (WARN_ON(consumer == supplier)) return; device_links_write_lock(); list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer == consumer) { device_link_put_kref(link); break; } } device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_remove); static void device_links_missing_supplier(struct device *dev) { struct device_link *link; list_for_each_entry(link, &dev->links.suppliers, c_node) { if (link->status != DL_STATE_CONSUMER_PROBE) continue; if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) { WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } else { WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); WRITE_ONCE(link->status, DL_STATE_DORMANT); } } } /** * device_links_check_suppliers - Check presence of supplier drivers. * @dev: Consumer device. * * Check links from this device to any suppliers. Walk the list of the device's * links to suppliers and see if all of them are available. If not, simply * return -EPROBE_DEFER. * * We need to guarantee that the supplier will not go away after the check has * been positive here. It only can go away in __device_release_driver() and * that function checks the device's links to consumers. This means we need to * mark the link as "consumer probe in progress" to make the supplier removal * wait for us to complete (or bad things may happen). * * Links without the DL_FLAG_MANAGED flag set are ignored. */ int device_links_check_suppliers(struct device *dev) { struct device_link *link; int ret = 0; /* * Device waiting for supplier to become available is not allowed to * probe. */ mutex_lock(&wfs_lock); if (!list_empty(&dev->links.needs_suppliers) && dev->links.need_for_probe) { mutex_unlock(&wfs_lock); return -EPROBE_DEFER; } mutex_unlock(&wfs_lock); device_links_write_lock(); list_for_each_entry(link, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_AVAILABLE && !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) { device_links_missing_supplier(dev); ret = -EPROBE_DEFER; break; } WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE); } dev->links.status = DL_DEV_PROBING; device_links_write_unlock(); return ret; } /** * __device_links_queue_sync_state - Queue a device for sync_state() callback * @dev: Device to call sync_state() on * @list: List head to queue the @dev on * * Queues a device for a sync_state() callback when the device links write lock * isn't held. This allows the sync_state() execution flow to use device links * APIs. The caller must ensure this function is called with * device_links_write_lock() held. * * This function does a get_device() to make sure the device is not freed while * on this list. * * So the caller must also ensure that device_links_flush_sync_list() is called * as soon as the caller releases device_links_write_lock(). This is necessary * to make sure the sync_state() is called in a timely fashion and the * put_device() is called on this device. */ static void __device_links_queue_sync_state(struct device *dev, struct list_head *list) { struct device_link *link; if (!dev_has_sync_state(dev)) return; if (dev->state_synced) return; list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_ACTIVE) return; } /* * Set the flag here to avoid adding the same device to a list more * than once. This can happen if new consumers get added to the device * and probed before the list is flushed. */ dev->state_synced = true; if (WARN_ON(!list_empty(&dev->links.defer_hook))) return; get_device(dev); list_add_tail(&dev->links.defer_hook, list); } /** * device_links_flush_sync_list - Call sync_state() on a list of devices * @list: List of devices to call sync_state() on * @dont_lock_dev: Device for which lock is already held by the caller * * Calls sync_state() on all the devices that have been queued for it. This * function is used in conjunction with __device_links_queue_sync_state(). The * @dont_lock_dev parameter is useful when this function is called from a * context where a device lock is already held. */ static void device_links_flush_sync_list(struct list_head *list, struct device *dont_lock_dev) { struct device *dev, *tmp; list_for_each_entry_safe(dev, tmp, list, links.defer_hook) { list_del_init(&dev->links.defer_hook); if (dev != dont_lock_dev) device_lock(dev); if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); if (dev != dont_lock_dev) device_unlock(dev); put_device(dev); } } void device_links_supplier_sync_state_pause(void) { device_links_write_lock(); defer_sync_state_count++; device_links_write_unlock(); } void device_links_supplier_sync_state_resume(void) { struct device *dev, *tmp; LIST_HEAD(sync_list); device_links_write_lock(); if (!defer_sync_state_count) { WARN(true, "Unmatched sync_state pause/resume!"); goto out; } defer_sync_state_count--; if (defer_sync_state_count) goto out; list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_hook) { /* * Delete from deferred_sync list before queuing it to * sync_list because defer_hook is used for both lists. */ list_del_init(&dev->links.defer_hook); __device_links_queue_sync_state(dev, &sync_list); } out: device_links_write_unlock(); device_links_flush_sync_list(&sync_list, NULL); } static int sync_state_resume_initcall(void) { device_links_supplier_sync_state_resume(); return 0; } late_initcall(sync_state_resume_initcall); static void __device_links_supplier_defer_sync(struct device *sup) { if (list_empty(&sup->links.defer_hook) && dev_has_sync_state(sup)) list_add_tail(&sup->links.defer_hook, &deferred_sync); } static void device_link_drop_managed(struct device_link *link) { link->flags &= ~DL_FLAG_MANAGED; WRITE_ONCE(link->status, DL_STATE_NONE); kref_put(&link->kref, __device_link_del); } static ssize_t waiting_for_supplier_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); mutex_lock(&wfs_lock); val = !list_empty(&dev->links.needs_suppliers) && dev->links.need_for_probe; mutex_unlock(&wfs_lock); device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RO(waiting_for_supplier); /** * device_links_driver_bound - Update device links after probing its driver. * @dev: Device to update the links for. * * The probe has been successful, so update links from this device to any * consumers by changing their status to "available". * * Also change the status of @dev's links to suppliers to "active". * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_bound(struct device *dev) { struct device_link *link, *ln; LIST_HEAD(sync_list); /* * If a device probes successfully, it's expected to have created all * the device links it needs to or make new device links as it needs * them. So, it no longer needs to wait on any suppliers. */ mutex_lock(&wfs_lock); list_del_init(&dev->links.needs_suppliers); mutex_unlock(&wfs_lock); device_remove_file(dev, &dev_attr_waiting_for_supplier); device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; /* * Links created during consumer probe may be in the "consumer * probe" state to start with if the supplier is still probing * when they are created and they may become "active" if the * consumer probe returns first. Skip them here. */ if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) continue; WARN_ON(link->status != DL_STATE_DORMANT); WRITE_ONCE(link->status, DL_STATE_AVAILABLE); if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER) driver_deferred_probe_add(link->consumer); } if (defer_sync_state_count) __device_links_supplier_defer_sync(dev); else __device_links_queue_sync_state(dev, &sync_list); list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) { struct device *supplier; if (!(link->flags & DL_FLAG_MANAGED)) continue; supplier = link->supplier; if (link->flags & DL_FLAG_SYNC_STATE_ONLY) { /* * When DL_FLAG_SYNC_STATE_ONLY is set, it means no * other DL_MANAGED_LINK_FLAGS have been set. So, it's * save to drop the managed link completely. */ device_link_drop_managed(link); } else { WARN_ON(link->status != DL_STATE_CONSUMER_PROBE); WRITE_ONCE(link->status, DL_STATE_ACTIVE); } /* * This needs to be done even for the deleted * DL_FLAG_SYNC_STATE_ONLY device link in case it was the last * device link that was preventing the supplier from getting a * sync_state() call. */ if (defer_sync_state_count) __device_links_supplier_defer_sync(supplier); else __device_links_queue_sync_state(supplier, &sync_list); } dev->links.status = DL_DEV_DRIVER_BOUND; device_links_write_unlock(); device_links_flush_sync_list(&sync_list, dev); } /** * __device_links_no_driver - Update links of a device without a driver. * @dev: Device without a drvier. * * Delete all non-persistent links from this device to any suppliers. * * Persistent links stay around, but their status is changed to "available", * unless they already are in the "supplier unbind in progress" state in which * case they need not be updated. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ static void __device_links_no_driver(struct device *dev) { struct device_link *link, *ln; list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { device_link_drop_managed(link); continue; } if (link->status != DL_STATE_CONSUMER_PROBE && link->status != DL_STATE_ACTIVE) continue; if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) { WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } else { WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); WRITE_ONCE(link->status, DL_STATE_DORMANT); } } dev->links.status = DL_DEV_NO_DRIVER; } /** * device_links_no_driver - Update links after failing driver probe. * @dev: Device whose driver has just failed to probe. * * Clean up leftover links to consumers for @dev and invoke * %__device_links_no_driver() to update links to suppliers for it as * appropriate. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_no_driver(struct device *dev) { struct device_link *link; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; /* * The probe has failed, so if the status of the link is * "consumer probe" or "active", it must have been added by * a probing consumer while this device was still probing. * Change its state to "dormant", as it represents a valid * relationship, but it is not functionally meaningful. */ if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) WRITE_ONCE(link->status, DL_STATE_DORMANT); } __device_links_no_driver(dev); device_links_write_unlock(); } /** * device_links_driver_cleanup - Update links after driver removal. * @dev: Device whose driver has just gone away. * * Update links to consumers for @dev by changing their status to "dormant" and * invoke %__device_links_no_driver() to update links to suppliers for it as * appropriate. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_cleanup(struct device *dev) { struct device_link *link, *ln; device_links_write_lock(); list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER); WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND); /* * autoremove the links between this @dev and its consumer * devices that are not active, i.e. where the link state * has moved to DL_STATE_SUPPLIER_UNBIND. */ if (link->status == DL_STATE_SUPPLIER_UNBIND && link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) device_link_drop_managed(link); WRITE_ONCE(link->status, DL_STATE_DORMANT); } list_del_init(&dev->links.defer_hook); __device_links_no_driver(dev); device_links_write_unlock(); } /** * device_links_busy - Check if there are any busy links to consumers. * @dev: Device to check. * * Check each consumer of the device and return 'true' if its link's status * is one of "consumer probe" or "active" (meaning that the given consumer is * probing right now or its driver is present). Otherwise, change the link * state to "supplier unbind" to prevent the consumer from being probed * successfully going forward. * * Return 'false' if there are no probing or active consumers. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ bool device_links_busy(struct device *dev) { struct device_link *link; bool ret = false; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) { ret = true; break; } WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND); } dev->links.status = DL_DEV_UNBINDING; device_links_write_unlock(); return ret; } /** * device_links_unbind_consumers - Force unbind consumers of the given device. * @dev: Device to unbind the consumers of. * * Walk the list of links to consumers for @dev and if any of them is in the * "consumer probe" state, wait for all device probes in progress to complete * and start over. * * If that's not the case, change the status of the link to "supplier unbind" * and check if the link was in the "active" state. If so, force the consumer * driver to unbind and start over (the consumer will not re-probe as we have * changed the state of the link already). * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_unbind_consumers(struct device *dev) { struct device_link *link; start: device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { enum device_link_state status; if (!(link->flags & DL_FLAG_MANAGED) || link->flags & DL_FLAG_SYNC_STATE_ONLY) continue; status = link->status; if (status == DL_STATE_CONSUMER_PROBE) { device_links_write_unlock(); wait_for_device_probe(); goto start; } WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND); if (status == DL_STATE_ACTIVE) { struct device *consumer = link->consumer; get_device(consumer); device_links_write_unlock(); device_release_driver_internal(consumer, NULL, consumer->parent); put_device(consumer); goto start; } } device_links_write_unlock(); } /** * device_links_purge - Delete existing links to other devices. * @dev: Target device. */ static void device_links_purge(struct device *dev) { struct device_link *link, *ln; if (dev->class == &devlink_class) return; mutex_lock(&wfs_lock); list_del_init(&dev->links.needs_suppliers); mutex_unlock(&wfs_lock); /* * Delete all of the remaining links from this device to any other * devices (either consumers or suppliers). */ device_links_write_lock(); list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { WARN_ON(link->status == DL_STATE_ACTIVE); __device_link_del(&link->kref); } list_for_each_entry_safe_reverse(link, ln, &dev->links.consumers, s_node) { WARN_ON(link->status != DL_STATE_DORMANT && link->status != DL_STATE_NONE); __device_link_del(&link->kref); } device_links_write_unlock(); } static u32 fw_devlink_flags = DL_FLAG_SYNC_STATE_ONLY; static int __init fw_devlink_setup(char *arg) { if (!arg) return -EINVAL; if (strcmp(arg, "off") == 0) { fw_devlink_flags = 0; } else if (strcmp(arg, "permissive") == 0) { fw_devlink_flags = DL_FLAG_SYNC_STATE_ONLY; } else if (strcmp(arg, "on") == 0) { fw_devlink_flags = DL_FLAG_AUTOPROBE_CONSUMER; } else if (strcmp(arg, "rpm") == 0) { fw_devlink_flags = DL_FLAG_AUTOPROBE_CONSUMER | DL_FLAG_PM_RUNTIME; } return 0; } early_param("fw_devlink", fw_devlink_setup); u32 fw_devlink_get_flags(void) { return fw_devlink_flags; } static bool fw_devlink_is_permissive(void) { return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY; } static void fw_devlink_link_device(struct device *dev) { int fw_ret; if (!fw_devlink_flags) return; mutex_lock(&defer_fw_devlink_lock); if (!defer_fw_devlink_count) device_link_add_missing_supplier_links(); /* * The device's fwnode not having add_links() doesn't affect if other * consumers can find this device as a supplier. So, this check is * intentionally placed after device_link_add_missing_supplier_links(). */ if (!fwnode_has_op(dev->fwnode, add_links)) goto out; /* * If fw_devlink is being deferred, assume all devices have mandatory * suppliers they need to link to later. Then, when the fw_devlink is * resumed, all these devices will get a chance to try and link to any * suppliers they have. */ if (!defer_fw_devlink_count) { fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); if (fw_ret == -ENODEV && fw_devlink_is_permissive()) fw_ret = -EAGAIN; } else { fw_ret = -ENODEV; /* * defer_hook is not used to add device to deferred_sync list * until device is bound. Since deferred fw devlink also blocks * probing, same list hook can be used for deferred_fw_devlink. */ list_add_tail(&dev->links.defer_hook, &deferred_fw_devlink); } if (fw_ret == -ENODEV) device_link_wait_for_mandatory_supplier(dev); else if (fw_ret) device_link_wait_for_optional_supplier(dev); out: mutex_unlock(&defer_fw_devlink_lock); } /** * fw_devlink_pause - Pause parsing of fwnode to create device links * * Calling this function defers any fwnode parsing to create device links until * fw_devlink_resume() is called. Both these functions are ref counted and the * caller needs to match the calls. * * While fw_devlink is paused: * - Any device that is added won't have its fwnode parsed to create device * links. * - The probe of the device will also be deferred during this period. * - Any devices that were already added, but waiting for suppliers won't be * able to link to newly added devices. * * Once fw_devlink_resume(): * - All the fwnodes that was not parsed will be parsed. * - All the devices that were deferred probing will be reattempted if they * aren't waiting for any more suppliers. * * This pair of functions, is mainly meant to optimize the parsing of fwnodes * when a lot of devices that need to link to each other are added in a short * interval of time. For example, adding all the top level devices in a system. * * For example, if N devices are added and: * - All the consumers are added before their suppliers * - All the suppliers of the N devices are part of the N devices * * Then: * * - With the use of fw_devlink_pause() and fw_devlink_resume(), each device * will only need one parsing of its fwnode because it is guaranteed to find * all the supplier devices already registered and ready to link to. It won't * have to do another pass later to find one or more suppliers it couldn't * find in the first parse of the fwnode. So, we'll only need O(N) fwnode * parses. * * - Without the use of fw_devlink_pause() and fw_devlink_resume(), we would * end up doing O(N^2) parses of fwnodes because every device that's added is * guaranteed to trigger a parse of the fwnode of every device added before * it. This O(N^2) parse is made worse by the fact that when a fwnode of a * device is parsed, all it descendant devices might need to have their * fwnodes parsed too (even if the devices themselves aren't added). */ void fw_devlink_pause(void) { mutex_lock(&defer_fw_devlink_lock); defer_fw_devlink_count++; mutex_unlock(&defer_fw_devlink_lock); } /** fw_devlink_resume - Resume parsing of fwnode to create device links * * This function is used in conjunction with fw_devlink_pause() and is ref * counted. See documentation for fw_devlink_pause() for more details. */ void fw_devlink_resume(void) { struct device *dev, *tmp; LIST_HEAD(probe_list); mutex_lock(&defer_fw_devlink_lock); if (!defer_fw_devlink_count) { WARN(true, "Unmatched fw_devlink pause/resume!"); goto out; } defer_fw_devlink_count--; if (defer_fw_devlink_count) goto out; device_link_add_missing_supplier_links(); list_splice_tail_init(&deferred_fw_devlink, &probe_list); out: mutex_unlock(&defer_fw_devlink_lock); /* * bus_probe_device() can cause new devices to get added and they'll * try to grab defer_fw_devlink_lock. So, this needs to be done outside * the defer_fw_devlink_lock. */ list_for_each_entry_safe(dev, tmp, &probe_list, links.defer_hook) { list_del_init(&dev->links.defer_hook); bus_probe_device(dev); } } /* Device links support end. */ int (*platform_notify)(struct device *dev) = NULL; int (*platform_notify_remove)(struct device *dev) = NULL; static struct kobject *dev_kobj; struct kobject *sysfs_dev_char_kobj; struct kobject *sysfs_dev_block_kobj; static DEFINE_MUTEX(device_hotplug_lock); void lock_device_hotplug(void) { mutex_lock(&device_hotplug_lock); } void unlock_device_hotplug(void) { mutex_unlock(&device_hotplug_lock); } int lock_device_hotplug_sysfs(void) { if (mutex_trylock(&device_hotplug_lock)) return 0; /* Avoid busy looping (5 ms of sleep should do). */ msleep(5); return restart_syscall(); } #ifdef CONFIG_BLOCK static inline int device_is_not_partition(struct device *dev) { return !(dev->type == &part_type); } #else static inline int device_is_not_partition(struct device *dev) { return 1; } #endif static int device_platform_notify(struct device *dev, enum kobject_action action) { int ret; ret = acpi_platform_notify(dev, action); if (ret) return ret; ret = software_node_notify(dev, action); if (ret) return ret; if (platform_notify && action == KOBJ_ADD) platform_notify(dev); else if (platform_notify_remove && action == KOBJ_REMOVE) platform_notify_remove(dev); return 0; } /** * dev_driver_string - Return a device's driver name, if at all possible * @dev: struct device to get the name of * * Will return the device's driver's name if it is bound to a device. If * the device is not bound to a driver, it will return the name of the bus * it is attached to. If it is not attached to a bus either, an empty * string will be returned. */ const char *dev_driver_string(const struct device *dev) { struct device_driver *drv; /* dev->driver can change to NULL underneath us because of unbinding, * so be careful about accessing it. dev->bus and dev->class should * never change once they are set, so they don't need special care. */ drv = READ_ONCE(dev->driver); return drv ? drv->name : dev_bus_name(dev); } EXPORT_SYMBOL(dev_driver_string); #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct device_attribute *dev_attr = to_dev_attr(attr); struct device *dev = kobj_to_dev(kobj); ssize_t ret = -EIO; if (dev_attr->show) ret = dev_attr->show(dev, dev_attr, buf); if (ret >= (ssize_t)PAGE_SIZE) { printk("dev_attr_show: %pS returned bad count\n", dev_attr->show); } return ret; } static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct device_attribute *dev_attr = to_dev_attr(attr); struct device *dev = kobj_to_dev(kobj); ssize_t ret = -EIO; if (dev_attr->store) ret = dev_attr->store(dev, dev_attr, buf, count); return ret; } static const struct sysfs_ops dev_sysfs_ops = { .show = dev_attr_show, .store = dev_attr_store, }; #define to_ext_attr(x) container_of(x, struct dev_ext_attribute, attr) ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); int ret; unsigned long new; ret = kstrtoul(buf, 0, &new); if (ret) return ret; *(unsigned long *)(ea->var) = new; /* Always return full write size even if we didn't consume all */ return size; } EXPORT_SYMBOL_GPL(device_store_ulong); ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%lx\n", *(unsigned long *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_ulong); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); int ret; long new; ret = kstrtol(buf, 0, &new); if (ret) return ret; if (new > INT_MAX || new < INT_MIN) return -EINVAL; *(int *)(ea->var) = new; /* Always return full write size even if we didn't consume all */ return size; } EXPORT_SYMBOL_GPL(device_store_int); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%d\n", *(int *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_int); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); if (strtobool(buf, ea->var) < 0) return -EINVAL; return size; } EXPORT_SYMBOL_GPL(device_store_bool); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%d\n", *(bool *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_bool); /** * device_release - free device structure. * @kobj: device's kobject. * * This is called once the reference count for the object * reaches 0. We forward the call to the device's release * method, which should handle actually freeing the structure. */ static void device_release(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); struct device_private *p = dev->p; /* * Some platform devices are driven without driver attached * and managed resources may have been acquired. Make sure * all resources are released. * * Drivers still can add resources into device after device * is deleted but alive, so release devres here to avoid * possible memory leak. */ devres_release_all(dev); kfree(dev->dma_range_map); if (dev->release) dev->release(dev); else if (dev->type && dev->type->release) dev->type->release(dev); else if (dev->class && dev->class->dev_release) dev->class->dev_release(dev); else WARN(1, KERN_ERR "Device '%s' does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", dev_name(dev)); kfree(p); } static const void *device_namespace(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); const void *ns = NULL; if (dev->class && dev->class->ns_type) ns = dev->class->namespace(dev); return ns; } static void device_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { struct device *dev = kobj_to_dev(kobj); if (dev->class && dev->class->get_ownership) dev->class->get_ownership(dev, uid, gid); } static struct kobj_type device_ktype = { .release = device_release, .sysfs_ops = &dev_sysfs_ops, .namespace = device_namespace, .get_ownership = device_get_ownership, }; static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) { struct kobj_type *ktype = get_ktype(kobj); if (ktype == &device_ktype) { struct device *dev = kobj_to_dev(kobj); if (dev->bus) return 1; if (dev->class) return 1; } return 0; } static const char *dev_uevent_name(struct kset *kset, struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); if (dev->bus) return dev->bus->name; if (dev->class) return dev->class->name; return NULL; } static int dev_uevent(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env) { struct device *dev = kobj_to_dev(kobj); int retval = 0; /* add device node properties if present */ if (MAJOR(dev->devt)) { const char *tmp; const char *name; umode_t mode = 0; kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; add_uevent_var(env, "MAJOR=%u", MAJOR(dev->devt)); add_uevent_var(env, "MINOR=%u", MINOR(dev->devt)); name = device_get_devnode(dev, &mode, &uid, &gid, &tmp); if (name) { add_uevent_var(env, "DEVNAME=%s", name); if (mode) add_uevent_var(env, "DEVMODE=%#o", mode & 0777); if (!uid_eq(uid, GLOBAL_ROOT_UID)) add_uevent_var(env, "DEVUID=%u", from_kuid(&init_user_ns, uid)); if (!gid_eq(gid, GLOBAL_ROOT_GID)) add_uevent_var(env, "DEVGID=%u", from_kgid(&init_user_ns, gid)); kfree(tmp); } } if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); if (dev->driver) add_uevent_var(env, "DRIVER=%s", dev->driver->name); /* Add common DT information about the device */ of_device_uevent(dev, env); /* have the bus specific function add its stuff */ if (dev->bus && dev->bus->uevent) { retval = dev->bus->uevent(dev, env); if (retval) pr_debug("device: '%s': %s: bus uevent() returned %d\n", dev_name(dev), __func__, retval); } /* have the class specific function add its stuff */ if (dev->class && dev->class->dev_uevent) { retval = dev->class->dev_uevent(dev, env); if (retval) pr_debug("device: '%s': %s: class uevent() " "returned %d\n", dev_name(dev), __func__, retval); } /* have the device type specific function add its stuff */ if (dev->type && dev->type->uevent) { retval = dev->type->uevent(dev, env); if (retval) pr_debug("device: '%s': %s: dev_type uevent() " "returned %d\n", dev_name(dev), __func__, retval); } return retval; } static const struct kset_uevent_ops device_uevent_ops = { .filter = dev_uevent_filter, .name = dev_uevent_name, .uevent = dev_uevent, }; static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, char *buf) { struct kobject *top_kobj; struct kset *kset; struct kobj_uevent_env *env = NULL; int i; int len = 0; int retval; /* search the kset, the device belongs to */ top_kobj = &dev->kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) goto out; kset = top_kobj->kset; if (!kset->uevent_ops || !kset->uevent_ops->uevent) goto out; /* respect filter */ if (kset->uevent_ops && kset->uevent_ops->filter) if (!kset->uevent_ops->filter(kset, &dev->kobj)) goto out; env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* Synchronize with really_probe() */ device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(kset, &dev->kobj, env); device_unlock(dev); if (retval) goto out; /* copy keys to file */ for (i = 0; i < env->envp_idx; i++) len += sysfs_emit_at(buf, len, "%s\n", env->envp[i]); out: kfree(env); return len; } static ssize_t uevent_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; rc = kobject_synth_uevent(&dev->kobj, buf, count); if (rc) { dev_err(dev, "uevent: failed to send synthetic uevent\n"); return rc; } return count; } static DEVICE_ATTR_RW(uevent); static ssize_t online_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = !dev->offline; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { bool val; int ret; ret = strtobool(buf, &val); if (ret < 0) return ret; ret = lock_device_hotplug_sysfs(); if (ret) return ret; ret = val ? device_online(dev) : device_offline(dev); unlock_device_hotplug(); return ret < 0 ? ret : count; } static DEVICE_ATTR_RW(online); static ssize_t removable_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *loc; switch (dev->removable) { case DEVICE_REMOVABLE: loc = "removable"; break; case DEVICE_FIXED: loc = "fixed"; break; default: loc = "unknown"; } return sysfs_emit(buf, "%s\n", loc); } static DEVICE_ATTR_RO(removable); int device_add_groups(struct device *dev, const struct attribute_group **groups) { return sysfs_create_groups(&dev->kobj, groups); } EXPORT_SYMBOL_GPL(device_add_groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups) { sysfs_remove_groups(&dev->kobj, groups); } EXPORT_SYMBOL_GPL(device_remove_groups); union device_attr_group_devres { const struct attribute_group *group; const struct attribute_group **groups; }; static int devm_attr_group_match(struct device *dev, void *res, void *data) { return ((union device_attr_group_devres *)res)->group == data; } static void devm_attr_group_remove(struct device *dev, void *res) { union device_attr_group_devres *devres = res; const struct attribute_group *group = devres->group; dev_dbg(dev, "%s: removing group %p\n", __func__, group); sysfs_remove_group(&dev->kobj, group); } static void devm_attr_groups_remove(struct device *dev, void *res) { union device_attr_group_devres *devres = res; const struct attribute_group **groups = devres->groups; dev_dbg(dev, "%s: removing groups %p\n", __func__, groups); sysfs_remove_groups(&dev->kobj, groups); } /** * devm_device_add_group - given a device, create a managed attribute group * @dev: The device to create the group for * @grp: The attribute group to create * * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * * Returns 0 on success or error code on failure. */ int devm_device_add_group(struct device *dev, const struct attribute_group *grp) { union device_attr_group_devres *devres; int error; devres = devres_alloc(devm_attr_group_remove, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; error = sysfs_create_group(&dev->kobj, grp); if (error) { devres_free(devres); return error; } devres->group = grp; devres_add(dev, devres); return 0; } EXPORT_SYMBOL_GPL(devm_device_add_group); /** * devm_device_remove_group: remove a managed group from a device * @dev: device to remove the group from * @grp: group to remove * * This function removes a group of attributes from a device. The attributes * previously have to have been created for this group, otherwise it will fail. */ void devm_device_remove_group(struct device *dev, const struct attribute_group *grp) { WARN_ON(devres_release(dev, devm_attr_group_remove, devm_attr_group_match, /* cast away const */ (void *)grp)); } EXPORT_SYMBOL_GPL(devm_device_remove_group); /** * devm_device_add_groups - create a bunch of managed attribute groups * @dev: The device to create the group for * @groups: The attribute groups to create, NULL terminated * * This function creates a bunch of managed attribute groups. If an error * occurs when creating a group, all previously created groups will be * removed, unwinding everything back to the original state when this * function was called. It will explicitly warn and error if any of the * attribute files being created already exist. * * Returns 0 on success or error code from sysfs_create_group on failure. */ int devm_device_add_groups(struct device *dev, const struct attribute_group **groups) { union device_attr_group_devres *devres; int error; devres = devres_alloc(devm_attr_groups_remove, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; error = sysfs_create_groups(&dev->kobj, groups); if (error) { devres_free(devres); return error; } devres->groups = groups; devres_add(dev, devres); return 0; } EXPORT_SYMBOL_GPL(devm_device_add_groups); /** * devm_device_remove_groups - remove a list of managed groups * * @dev: The device for the groups to be removed from * @groups: NULL terminated list of groups to be removed * * If groups is not NULL, remove the specified groups from the device. */ void devm_device_remove_groups(struct device *dev, const struct attribute_group **groups) { WARN_ON(devres_release(dev, devm_attr_groups_remove, devm_attr_group_match, /* cast away const */ (void *)groups)); } EXPORT_SYMBOL_GPL(devm_device_remove_groups); static int device_add_attrs(struct device *dev) { struct class *class = dev->class; const struct device_type *type = dev->type; int error; if (class) { error = device_add_groups(dev, class->dev_groups); if (error) return error; } if (type) { error = device_add_groups(dev, type->groups); if (error) goto err_remove_class_groups; } error = device_add_groups(dev, dev->groups); if (error) goto err_remove_type_groups; if (device_supports_offline(dev) && !dev->offline_disabled) { error = device_create_file(dev, &dev_attr_online); if (error) goto err_remove_dev_groups; } if (fw_devlink_flags && !fw_devlink_is_permissive()) { error = device_create_file(dev, &dev_attr_waiting_for_supplier); if (error) goto err_remove_dev_online; } if (dev_removable_is_valid(dev)) { error = device_create_file(dev, &dev_attr_removable); if (error) goto err_remove_dev_waiting_for_supplier; } return 0; err_remove_dev_waiting_for_supplier: device_remove_file(dev, &dev_attr_waiting_for_supplier); err_remove_dev_online: device_remove_file(dev, &dev_attr_online); err_remove_dev_groups: device_remove_groups(dev, dev->groups); err_remove_type_groups: if (type) device_remove_groups(dev, type->groups); err_remove_class_groups: if (class) device_remove_groups(dev, class->dev_groups); return error; } static void device_remove_attrs(struct device *dev) { struct class *class = dev->class; const struct device_type *type = dev->type; device_remove_file(dev, &dev_attr_removable); device_remove_file(dev, &dev_attr_waiting_for_supplier); device_remove_file(dev, &dev_attr_online); device_remove_groups(dev, dev->groups); if (type) device_remove_groups(dev, type->groups); if (class) device_remove_groups(dev, class->dev_groups); } static ssize_t dev_show(struct device *dev, struct device_attribute *attr, char *buf) { return print_dev_t(buf, dev->devt); } static DEVICE_ATTR_RO(dev); /* /sys/devices/ */ struct kset *devices_kset; /** * devices_kset_move_before - Move device in the devices_kset's list. * @deva: Device to move. * @devb: Device @deva should come before. */ static void devices_kset_move_before(struct device *deva, struct device *devb) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s before %s\n", dev_name(deva), dev_name(devb)); spin_lock(&devices_kset->list_lock); list_move_tail(&deva->kobj.entry, &devb->kobj.entry); spin_unlock(&devices_kset->list_lock); } /** * devices_kset_move_after - Move device in the devices_kset's list. * @deva: Device to move * @devb: Device @deva should come after. */ static void devices_kset_move_after(struct device *deva, struct device *devb) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s after %s\n", dev_name(deva), dev_name(devb)); spin_lock(&devices_kset->list_lock); list_move(&deva->kobj.entry, &devb->kobj.entry); spin_unlock(&devices_kset->list_lock); } /** * devices_kset_move_last - move the device to the end of devices_kset's list. * @dev: device to move */ void devices_kset_move_last(struct device *dev) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s to end of list\n", dev_name(dev)); spin_lock(&devices_kset->list_lock); list_move_tail(&dev->kobj.entry, &devices_kset->list); spin_unlock(&devices_kset->list_lock); } /** * device_create_file - create sysfs attribute file for device. * @dev: device. * @attr: device attribute descriptor. */ int device_create_file(struct device *dev, const struct device_attribute *attr) { int error = 0; if (dev) { WARN(((attr->attr.mode & S_IWUGO) && !attr->store), "Attribute %s: write permission without 'store'\n", attr->attr.name); WARN(((attr->attr.mode & S_IRUGO) && !attr->show), "Attribute %s: read permission without 'show'\n", attr->attr.name); error = sysfs_create_file(&dev->kobj, &attr->attr); } return error; } EXPORT_SYMBOL_GPL(device_create_file); /** * device_remove_file - remove sysfs attribute file. * @dev: device. * @attr: device attribute descriptor. */ void device_remove_file(struct device *dev, const struct device_attribute *attr) { if (dev) sysfs_remove_file(&dev->kobj, &attr->attr); } EXPORT_SYMBOL_GPL(device_remove_file); /** * device_remove_file_self - remove sysfs attribute file from its own method. * @dev: device. * @attr: device attribute descriptor. * * See kernfs_remove_self() for details. */ bool device_remove_file_self(struct device *dev, const struct device_attribute *attr) { if (dev) return sysfs_remove_file_self(&dev->kobj, &attr->attr); else return false; } EXPORT_SYMBOL_GPL(device_remove_file_self); /** * device_create_bin_file - create sysfs binary attribute file for device. * @dev: device. * @attr: device binary attribute descriptor. */ int device_create_bin_file(struct device *dev, const struct bin_attribute *attr) { int error = -EINVAL; if (dev) error = sysfs_create_bin_file(&dev->kobj, attr); return error; } EXPORT_SYMBOL_GPL(device_create_bin_file); /** * device_remove_bin_file - remove sysfs binary attribute file * @dev: device. * @attr: device binary attribute descriptor. */ void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr) { if (dev) sysfs_remove_bin_file(&dev->kobj, attr); } EXPORT_SYMBOL_GPL(device_remove_bin_file); static void klist_children_get(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); struct device *dev = p->device; get_device(dev); } static void klist_children_put(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); struct device *dev = p->device; put_device(dev); } /** * device_initialize - init device structure. * @dev: device. * * This prepares the device for use by other layers by initializing * its fields. * It is the first half of device_register(), if called by * that function, though it can also be called separately, so one * may use @dev's fields. In particular, get_device()/put_device() * may be used for reference counting of @dev after calling this * function. * * All fields in @dev must be initialized by the caller to 0, except * for those explicitly set to some other value. The simplest * approach is to use kzalloc() to allocate the structure containing * @dev. * * NOTE: Use put_device() to give up your reference instead of freeing * @dev directly once you have called this function. */ void device_initialize(struct device *dev) { dev->kobj.kset = devices_kset; kobject_init(&dev->kobj, &device_ktype); INIT_LIST_HEAD(&dev->dma_pools); mutex_init(&dev->mutex); #ifdef CONFIG_PROVE_LOCKING mutex_init(&dev->lockdep_mutex); #endif lockdep_set_novalidate_class(&dev->mutex); spin_lock_init(&dev->devres_lock); INIT_LIST_HEAD(&dev->devres_head); device_pm_init(dev); set_dev_node(dev, -1); #ifdef CONFIG_GENERIC_MSI_IRQ raw_spin_lock_init(&dev->msi_lock); INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); INIT_LIST_HEAD(&dev->links.needs_suppliers); INIT_LIST_HEAD(&dev->links.defer_hook); dev->links.status = DL_DEV_NO_DRIVER; } EXPORT_SYMBOL_GPL(device_initialize); struct kobject *virtual_device_parent(struct device *dev) { static struct kobject *virtual_dir = NULL; if (!virtual_dir) virtual_dir = kobject_create_and_add("virtual", &devices_kset->kobj); return virtual_dir; } struct class_dir { struct kobject kobj; struct class *class; }; #define to_class_dir(obj) container_of(obj, struct class_dir, kobj) static void class_dir_release(struct kobject *kobj) { struct class_dir *dir = to_class_dir(kobj); kfree(dir); } static const struct kobj_ns_type_operations *class_dir_child_ns_type(struct kobject *kobj) { struct class_dir *dir = to_class_dir(kobj); return dir->class->ns_type; } static struct kobj_type class_dir_ktype = { .release = class_dir_release, .sysfs_ops = &kobj_sysfs_ops, .child_ns_type = class_dir_child_ns_type }; static struct kobject * class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) { struct class_dir *dir; int retval; dir = kzalloc(sizeof(*dir), GFP_KERNEL); if (!dir) return ERR_PTR(-ENOMEM); dir->class = class; kobject_init(&dir->kobj, &class_dir_ktype); dir->kobj.kset = &class->p->glue_dirs; retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name); if (retval < 0) { kobject_put(&dir->kobj); return ERR_PTR(retval); } return &dir->kobj; } static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { if (dev->class) { struct kobject *kobj = NULL; struct kobject *parent_kobj; struct kobject *k; #ifdef CONFIG_BLOCK /* block disks show up in /sys/block */ if (sysfs_deprecated && dev->class == &block_class) { if (parent && parent->class == &block_class) return &parent->kobj; return &block_class.p->subsys.kobj; } #endif /* * If we have no parent, we live in "virtual". * Class-devices with a non class-device as parent, live * in a "glue" directory to prevent namespace collisions. */ if (parent == NULL) parent_kobj = virtual_device_parent(dev); else if (parent->class && !dev->class->ns_type) return &parent->kobj; else parent_kobj = &parent->kobj; mutex_lock(&gdp_mutex); /* find our class-directory at the parent and reference it */ spin_lock(&dev->class->p->glue_dirs.list_lock); list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } spin_unlock(&dev->class->p->glue_dirs.list_lock); if (kobj) { mutex_unlock(&gdp_mutex); return kobj; } /* or create a new class-directory at the parent device */ k = class_dir_create_and_add(dev->class, parent_kobj); /* do not emit an uevent for this simple "glue" directory */ mutex_unlock(&gdp_mutex); return k; } /* subsystems can specify a default root directory for their devices */ if (!parent && dev->bus && dev->bus->dev_root) return &dev->bus->dev_root->kobj; if (parent) return &parent->kobj; return NULL; } static inline bool live_in_glue_dir(struct kobject *kobj, struct device *dev) { if (!kobj || !dev->class || kobj->kset != &dev->class->p->glue_dirs) return false; return true; } static inline struct kobject *get_glue_dir(struct device *dev) { return dev->kobj.parent; } /* * make sure cleaning up dir as the last step, we need to make * sure .release handler of kobject is run with holding the * global lock */ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) { unsigned int ref; /* see if we live in a "glue" directory */ if (!live_in_glue_dir(glue_dir, dev)) return; mutex_lock(&gdp_mutex); /** * There is a race condition between removing glue directory * and adding a new device under the glue directory. * * CPU1: CPU2: * * device_add() * get_device_parent() * class_dir_create_and_add() * kobject_add_internal() * create_dir() // create glue_dir * * device_add() * get_device_parent() * kobject_get() // get glue_dir * * device_del() * cleanup_glue_dir() * kobject_del(glue_dir) * * kobject_add() * kobject_add_internal() * create_dir() // in glue_dir * sysfs_create_dir_ns() * kernfs_create_dir_ns(sd) * * sysfs_remove_dir() // glue_dir->sd=NULL * sysfs_put() // free glue_dir->sd * * // sd is freed * kernfs_new_node(sd) * kernfs_get(glue_dir) * kernfs_add_one() * kernfs_put() * * Before CPU1 remove last child device under glue dir, if CPU2 add * a new device under glue dir, the glue_dir kobject reference count * will be increase to 2 in kobject_get(k). And CPU2 has been called * kernfs_create_dir_ns(). Meanwhile, CPU1 call sysfs_remove_dir() * and sysfs_put(). This result in glue_dir->sd is freed. * * Then the CPU2 will see a stale "empty" but still potentially used * glue dir around in kernfs_new_node(). * * In order to avoid this happening, we also should make sure that * kernfs_node for glue_dir is released in CPU1 only when refcount * for glue_dir kobj is 1. */ ref = kref_read(&glue_dir->kref); if (!kobject_has_children(glue_dir) && !--ref) kobject_del(glue_dir); kobject_put(glue_dir); mutex_unlock(&gdp_mutex); } static int device_add_class_symlinks(struct device *dev) { struct device_node *of_node = dev_of_node(dev); int error; if (of_node) { error = sysfs_create_link(&dev->kobj, of_node_kobj(of_node), "of_node"); if (error) dev_warn(dev, "Error %d creating of_node link\n",error); /* An error here doesn't warrant bringing down the device */ } if (!dev->class) return 0; error = sysfs_create_link(&dev->kobj, &dev->class->p->subsys.kobj, "subsystem"); if (error) goto out_devnode; if (dev->parent && device_is_not_partition(dev)) { error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device"); if (error) goto out_subsys; } #ifdef CONFIG_BLOCK /* /sys/block has directories and does not need symlinks */ if (sysfs_deprecated && dev->class == &block_class) return 0; #endif /* link in the class directory pointing to the device */ error = sysfs_create_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); if (error) goto out_device; return 0; out_device: sysfs_remove_link(&dev->kobj, "device"); out_subsys: sysfs_remove_link(&dev->kobj, "subsystem"); out_devnode: sysfs_remove_link(&dev->kobj, "of_node"); return error; } static void device_remove_class_symlinks(struct device *dev) { if (dev_of_node(dev)) sysfs_remove_link(&dev->kobj, "of_node"); if (!dev->class) return; if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(&dev->kobj, "subsystem"); #ifdef CONFIG_BLOCK if (sysfs_deprecated && dev->class == &block_class) return; #endif sysfs_delete_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); } /** * dev_set_name - set a device name * @dev: device * @fmt: format string for the device's name */ int dev_set_name(struct device *dev, const char *fmt, ...) { va_list vargs; int err; va_start(vargs, fmt); err = kobject_set_name_vargs(&dev->kobj, fmt, vargs); va_end(vargs); return err; } EXPORT_SYMBOL_GPL(dev_set_name); /** * device_to_dev_kobj - select a /sys/dev/ directory for the device * @dev: device * * By default we select char/ for new entries. Setting class->dev_obj * to NULL prevents an entry from being created. class->dev_kobj must * be set (or cleared) before any devices are registered to the class * otherwise device_create_sys_dev_entry() and * device_remove_sys_dev_entry() will disagree about the presence of * the link. */ static struct kobject *device_to_dev_kobj(struct device *dev) { struct kobject *kobj; if (dev->class) kobj = dev->class->dev_kobj; else kobj = sysfs_dev_char_kobj; return kobj; } static int device_create_sys_dev_entry(struct device *dev) { struct kobject *kobj = device_to_dev_kobj(dev); int error = 0; char devt_str[15]; if (kobj) { format_dev_t(devt_str, dev->devt); error = sysfs_create_link(kobj, &dev->kobj, devt_str); } return error; } static void device_remove_sys_dev_entry(struct device *dev) { struct kobject *kobj = device_to_dev_kobj(dev); char devt_str[15]; if (kobj) { format_dev_t(devt_str, dev->devt); sysfs_remove_link(kobj, devt_str); } } static int device_private_init(struct device *dev) { dev->p = kzalloc(sizeof(*dev->p), GFP_KERNEL); if (!dev->p) return -ENOMEM; dev->p->device = dev; klist_init(&dev->p->klist_children, klist_children_get, klist_children_put); INIT_LIST_HEAD(&dev->p->deferred_probe); return 0; } /** * device_add - add device to device hierarchy. * @dev: device. * * This is part 2 of device_register(), though may be called * separately _iff_ device_initialize() has been called separately. * * This adds @dev to the kobject hierarchy via kobject_add(), adds it * to the global and sibling lists for the device, then * adds it to the other relevant subsystems of the driver model. * * Do not call this routine or device_register() more than once for * any device structure. The driver model core is not designed to work * with devices that get unregistered and then spring back to life. * (Among other things, it's very hard to guarantee that all references * to the previous incarnation of @dev have been dropped.) Allocate * and register a fresh new struct device instead. * * NOTE: _Never_ directly free @dev after calling this function, even * if it returned an error! Always use put_device() to give up your * reference instead. * * Rule of thumb is: if device_add() succeeds, you should call * device_del() when you want to get rid of it. If device_add() has * *not* succeeded, use *only* put_device() to drop the reference * count. */ int device_add(struct device *dev) { struct device *parent; struct kobject *kobj; struct class_interface *class_intf; int error = -EINVAL; struct kobject *glue_dir = NULL; dev = get_device(dev); if (!dev) goto done; if (!dev->p) { error = device_private_init(dev); if (error) goto done; } /* * for statically allocated devices, which should all be converted * some day, we need to initialize the name. We prevent reading back * the name, and force the use of dev_name() */ if (dev->init_name) { dev_set_name(dev, "%s", dev->init_name); dev->init_name = NULL; } /* subsystems can specify simple device enumeration */ if (!dev_name(dev) && dev->bus && dev->bus->dev_name) dev_set_name(dev, "%s%u", dev->bus->dev_name, dev->id); if (!dev_name(dev)) { error = -EINVAL; goto name_error; } pr_debug("device: '%s': %s\n", dev_name(dev), __func__); parent = get_device(dev->parent); kobj = get_device_parent(dev, parent); if (IS_ERR(kobj)) { error = PTR_ERR(kobj); goto parent_error; } if (kobj) dev->kobj.parent = kobj; /* use parent numa_node */ if (parent && (dev_to_node(dev) == NUMA_NO_NODE)) set_dev_node(dev, dev_to_node(parent)); /* first, register with generic layer. */ /* we require the name to be set before, and pass NULL */ error = kobject_add(&dev->kobj, dev->kobj.parent, NULL); if (error) { glue_dir = get_glue_dir(dev); goto Error; } /* notify platform of device entry */ error = device_platform_notify(dev, KOBJ_ADD); if (error) goto platform_error; error = device_create_file(dev, &dev_attr_uevent); if (error) goto attrError; error = device_add_class_symlinks(dev); if (error) goto SymlinkError; error = device_add_attrs(dev); if (error) goto AttrsError; error = bus_add_device(dev); if (error) goto BusError; error = dpm_sysfs_add(dev); if (error) goto DPMError; device_pm_add(dev); if (MAJOR(dev->devt)) { error = device_create_file(dev, &dev_attr_dev); if (error) goto DevAttrError; error = device_create_sys_dev_entry(dev); if (error) goto SysEntryError; devtmpfs_create_node(dev); } /* Notify clients of device addition. This call must come * after dpm_sysfs_add() and before kobject_uevent(). */ if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_ADD_DEVICE, dev); kobject_uevent(&dev->kobj, KOBJ_ADD); /* * Check if any of the other devices (consumers) have been waiting for * this device (supplier) to be added so that they can create a device * link to it. * * This needs to happen after device_pm_add() because device_link_add() * requires the supplier be registered before it's called. * * But this also needs to happen before bus_probe_device() to make sure * waiting consumers can link to it before the driver is bound to the * device and the driver sync_state callback is called for this device. */ if (dev->fwnode && !dev->fwnode->dev) { dev->fwnode->dev = dev; fw_devlink_link_device(dev); } bus_probe_device(dev); if (parent) klist_add_tail(&dev->p->knode_parent, &parent->p->klist_children); if (dev->class) { mutex_lock(&dev->class->p->mutex); /* tie the class to the device */ klist_add_tail(&dev->p->knode_class, &dev->class->p->klist_devices); /* notify any interfaces that the device is here */ list_for_each_entry(class_intf, &dev->class->p->interfaces, node) if (class_intf->add_dev) class_intf->add_dev(dev, class_intf); mutex_unlock(&dev->class->p->mutex); } done: put_device(dev); return error; SysEntryError: if (MAJOR(dev->devt)) device_remove_file(dev, &dev_attr_dev); DevAttrError: device_pm_remove(dev); dpm_sysfs_remove(dev); DPMError: dev->driver = NULL; bus_remove_device(dev); BusError: device_remove_attrs(dev); AttrsError: device_remove_class_symlinks(dev); SymlinkError: device_remove_file(dev, &dev_attr_uevent); attrError: device_platform_notify(dev, KOBJ_REMOVE); platform_error: kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); Error: cleanup_glue_dir(dev, glue_dir); parent_error: put_device(parent); name_error: kfree(dev->p); dev->p = NULL; goto done; } EXPORT_SYMBOL_GPL(device_add); /** * device_register - register a device with the system. * @dev: pointer to the device structure * * This happens in two clean steps - initialize the device * and add it to the system. The two steps can be called * separately, but this is the easiest and most common. * I.e. you should only call the two helpers separately if * have a clearly defined need to use and refcount the device * before it is added to the hierarchy. * * For more information, see the kerneldoc for device_initialize() * and device_add(). * * NOTE: _Never_ directly free @dev after calling this function, even * if it returned an error! Always use put_device() to give up the * reference initialized in this function instead. */ int device_register(struct device *dev) { device_initialize(dev); return device_add(dev); } EXPORT_SYMBOL_GPL(device_register); /** * get_device - increment reference count for device. * @dev: device. * * This simply forwards the call to kobject_get(), though * we do take care to provide for the case that we get a NULL * pointer passed in. */ struct device *get_device(struct device *dev) { return dev ? kobj_to_dev(kobject_get(&dev->kobj)) : NULL; } EXPORT_SYMBOL_GPL(get_device); /** * put_device - decrement reference count. * @dev: device in question. */ void put_device(struct device *dev) { /* might_sleep(); */ if (dev) kobject_put(&dev->kobj); } EXPORT_SYMBOL_GPL(put_device); bool kill_device(struct device *dev) { /* * Require the device lock and set the "dead" flag to guarantee that * the update behavior is consistent with the other bitfields near * it and that we cannot have an asynchronous probe routine trying * to run while we are tearing out the bus/class/sysfs from * underneath the device. */ lockdep_assert_held(&dev->mutex); if (dev->p->dead) return false; dev->p->dead = true; return true; } EXPORT_SYMBOL_GPL(kill_device); /** * device_del - delete device from system. * @dev: device. * * This is the first part of the device unregistration * sequence. This removes the device from the lists we control * from here, has it removed from the other driver model * subsystems it was added to in device_add(), and removes it * from the kobject hierarchy. * * NOTE: this should be called manually _iff_ device_add() was * also called manually. */ void device_del(struct device *dev) { struct device *parent = dev->parent; struct kobject *glue_dir = NULL; struct class_interface *class_intf; unsigned int noio_flag; device_lock(dev); kill_device(dev); device_unlock(dev); if (dev->fwnode && dev->fwnode->dev == dev) dev->fwnode->dev = NULL; /* Notify clients of device removal. This call must come * before dpm_sysfs_remove(). */ noio_flag = memalloc_noio_save(); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DEL_DEVICE, dev); dpm_sysfs_remove(dev); if (parent) klist_del(&dev->p->knode_parent); if (MAJOR(dev->devt)) { devtmpfs_delete_node(dev); device_remove_sys_dev_entry(dev); device_remove_file(dev, &dev_attr_dev); } if (dev->class) { device_remove_class_symlinks(dev); mutex_lock(&dev->class->p->mutex); /* notify any interfaces that the device is now gone */ list_for_each_entry(class_intf, &dev->class->p->interfaces, node) if (class_intf->remove_dev) class_intf->remove_dev(dev, class_intf); /* remove the device from the class list */ klist_del(&dev->p->knode_class); mutex_unlock(&dev->class->p->mutex); } device_remove_file(dev, &dev_attr_uevent); device_remove_attrs(dev); bus_remove_device(dev); device_pm_remove(dev); driver_deferred_probe_del(dev); device_platform_notify(dev, KOBJ_REMOVE); device_remove_properties(dev); device_links_purge(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_REMOVED_DEVICE, dev); kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); cleanup_glue_dir(dev, glue_dir); memalloc_noio_restore(noio_flag); put_device(parent); } EXPORT_SYMBOL_GPL(device_del); /** * device_unregister - unregister device from system. * @dev: device going away. * * We do this in two parts, like we do device_register(). First, * we remove it from all the subsystems with device_del(), then * we decrement the reference count via put_device(). If that * is the final reference count, the device will be cleaned up * via device_release() above. Otherwise, the structure will * stick around until the final reference to the device is dropped. */ void device_unregister(struct device *dev) { pr_debug("device: '%s': %s\n", dev_name(dev), __func__); device_del(dev); put_device(dev); } EXPORT_SYMBOL_GPL(device_unregister); static struct device *prev_device(struct klist_iter *i) { struct klist_node *n = klist_prev(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; } static struct device *next_device(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; } /** * device_get_devnode - path of device node file * @dev: device * @mode: returned file access mode * @uid: returned file owner * @gid: returned file group * @tmp: possibly allocated string * * Return the relative path of a possible device node. * Non-default names may need to allocate a memory to compose * a name. This memory is returned in tmp and needs to be * freed by the caller. */ const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp) { char *s; *tmp = NULL; /* the device type may provide a specific name */ if (dev->type && dev->type->devnode) *tmp = dev->type->devnode(dev, mode, uid, gid); if (*tmp) return *tmp; /* the class may provide a specific name */ if (dev->class && dev->class->devnode) *tmp = dev->class->devnode(dev, mode); if (*tmp) return *tmp; /* return name without allocation, tmp == NULL */ if (strchr(dev_name(dev), '!') == NULL) return dev_name(dev); /* replace '!' in the name with '/' */ s = kstrdup(dev_name(dev), GFP_KERNEL); if (!s) return NULL; strreplace(s, '!', '/'); return *tmp = s; } /** * device_for_each_child - device child iterator. * @parent: parent struct device. * @fn: function to be called for each device. * @data: data for the callback. * * Iterate over @parent's child devices, and call @fn for each, * passing it @data. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. */ int device_for_each_child(struct device *parent, void *data, int (*fn)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; int error = 0; if (!parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); while (!error && (child = next_device(&i))) error = fn(child, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(device_for_each_child); /** * device_for_each_child_reverse - device child iterator in reversed order. * @parent: parent struct device. * @fn: function to be called for each device. * @data: data for the callback. * * Iterate over @parent's child devices, and call @fn for each, * passing it @data. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. */ int device_for_each_child_reverse(struct device *parent, void *data, int (*fn)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; int error = 0; if (!parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); while ((child = prev_device(&i)) && !error) error = fn(child, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(device_for_each_child_reverse); /** * device_find_child - device iterator for locating a particular device. * @parent: parent struct device * @match: Callback function to check device * @data: Data to pass to match function * * This is similar to the device_for_each_child() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero and a reference to the * current device can be obtained, this function will return to the caller * and not iterate over any more devices. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_child(struct device *parent, void *data, int (*match)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; if (!parent) return NULL; klist_iter_init(&parent->p->klist_children, &i); while ((child = next_device(&i))) if (match(child, data) && get_device(child)) break; klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child); /** * device_find_child_by_name - device iterator for locating a child device. * @parent: parent struct device * @name: name of the child device * * This is similar to the device_find_child() function above, but it * returns a reference to a device that has the name @name. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_child_by_name(struct device *parent, const char *name) { struct klist_iter i; struct device *child; if (!parent) return NULL; klist_iter_init(&parent->p->klist_children, &i); while ((child = next_device(&i))) if (sysfs_streq(dev_name(child), name) && get_device(child)) break; klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child_by_name); static int match_any(struct device *dev, void *unused) { return 1; } /** * device_find_any_child - device iterator for locating a child device, if any. * @parent: parent struct device * * This is similar to the device_find_child() function above, but it * returns a reference to a child device, if any. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_any_child(struct device *parent) { return device_find_child(parent, NULL, match_any); } EXPORT_SYMBOL_GPL(device_find_any_child); int __init devices_init(void) { devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL); if (!devices_kset) return -ENOMEM; dev_kobj = kobject_create_and_add("dev", NULL); if (!dev_kobj) goto dev_kobj_err; sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj); if (!sysfs_dev_block_kobj) goto block_kobj_err; sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; device_link_wq = alloc_workqueue("device_link_wq", 0, 0); if (!device_link_wq) goto wq_err; return 0; wq_err: kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: kobject_put(dev_kobj); dev_kobj_err: kset_unregister(devices_kset); return -ENOMEM; } static int device_check_offline(struct device *dev, void *not_used) { int ret; ret = device_for_each_child(dev, NULL, device_check_offline); if (ret) return ret; return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0; } /** * device_offline - Prepare the device for hot-removal. * @dev: Device to be put offline. * * Execute the device bus type's .offline() callback, if present, to prepare * the device for a subsequent hot-removal. If that succeeds, the device must * not be used until either it is removed or its bus type's .online() callback * is executed. * * Call under device_hotplug_lock. */ int device_offline(struct device *dev) { int ret; if (dev->offline_disabled) return -EPERM; ret = device_for_each_child(dev, NULL, device_check_offline); if (ret) return ret; device_lock(dev); if (device_supports_offline(dev)) { if (dev->offline) { ret = 1; } else { ret = dev->bus->offline(dev); if (!ret) { kobject_uevent(&dev->kobj, KOBJ_OFFLINE); dev->offline = true; } } } device_unlock(dev); return ret; } /** * device_online - Put the device back online after successful device_offline(). * @dev: Device to be put back online. * * If device_offline() has been successfully executed for @dev, but the device * has not been removed subsequently, execute its bus type's .online() callback * to indicate that the device can be used again. * * Call under device_hotplug_lock. */ int device_online(struct device *dev) { int ret = 0; device_lock(dev); if (device_supports_offline(dev)) { if (dev->offline) { ret = dev->bus->online(dev); if (!ret) { kobject_uevent(&dev->kobj, KOBJ_ONLINE); dev->offline = false; } } else { ret = 1; } } device_unlock(dev); return ret; } struct root_device { struct device dev; struct module *owner; }; static inline struct root_device *to_root_device(struct device *d) { return container_of(d, struct root_device, dev); } static void root_device_release(struct device *dev) { kfree(to_root_device(dev)); } /** * __root_device_register - allocate and register a root device * @name: root device name * @owner: owner module of the root device, usually THIS_MODULE * * This function allocates a root device and registers it * using device_register(). In order to free the returned * device, use root_device_unregister(). * * Root devices are dummy devices which allow other devices * to be grouped under /sys/devices. Use this function to * allocate a root device and then use it as the parent of * any device which should appear under /sys/devices/{name} * * The /sys/devices/{name} directory will also contain a * 'module' symlink which points to the @owner directory * in sysfs. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: You probably want to use root_device_register(). */ struct device *__root_device_register(const char *name, struct module *owner) { struct root_device *root; int err = -ENOMEM; root = kzalloc(sizeof(struct root_device), GFP_KERNEL); if (!root) return ERR_PTR(err); err = dev_set_name(&root->dev, "%s", name); if (err) { kfree(root); return ERR_PTR(err); } root->dev.release = root_device_release; err = device_register(&root->dev); if (err) { put_device(&root->dev); return ERR_PTR(err); } #ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */ if (owner) { struct module_kobject *mk = &owner->mkobj; err = sysfs_create_link(&root->dev.kobj, &mk->kobj, "module"); if (err) { device_unregister(&root->dev); return ERR_PTR(err); } root->owner = owner; } #endif return &root->dev; } EXPORT_SYMBOL_GPL(__root_device_register); /** * root_device_unregister - unregister and free a root device * @dev: device going away * * This function unregisters and cleans up a device that was created by * root_device_register(). */ void root_device_unregister(struct device *dev) { struct root_device *root = to_root_device(dev); if (root->owner) sysfs_remove_link(&root->dev.kobj, "module"); device_unregister(dev); } EXPORT_SYMBOL_GPL(root_device_unregister); static void device_create_release(struct device *dev) { pr_debug("device: '%s': %s\n", dev_name(dev), __func__); kfree(dev); } static __printf(6, 0) struct device * device_create_groups_vargs(struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, va_list args) { struct device *dev = NULL; int retval = -ENODEV; if (class == NULL || IS_ERR(class)) goto error; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) { retval = -ENOMEM; goto error; } device_initialize(dev); dev->devt = devt; dev->class = class; dev->parent = parent; dev->groups = groups; dev->release = device_create_release; dev_set_drvdata(dev, drvdata); retval = kobject_set_name_vargs(&dev->kobj, fmt, args); if (retval) goto error; retval = device_add(dev); if (retval) goto error; return dev; error: put_device(dev); return ERR_PTR(retval); } /** * device_create - creates a device and registers it with sysfs * @class: pointer to the struct class that this device should be registered to * @parent: pointer to the parent struct device of this new device, if any * @devt: the dev_t for the char device to be added * @drvdata: the data to be added to the device for callbacks * @fmt: string for the device's name * * This function can be used by char device classes. A struct device * will be created in sysfs, registered to the specified class. * * A "dev" file will be created, showing the dev_t for the device, if * the dev_t is not 0,0. * If a pointer to a parent struct device is passed in, the newly created * struct device will be a child of that device in sysfs. * The pointer to the struct device will be returned from the call. * Any further sysfs files that might be required can be created using this * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: the struct class passed to this function must have previously * been created with a call to class_create(). */ struct device *device_create(struct class *class, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...) { va_list vargs; struct device *dev; va_start(vargs, fmt); dev = device_create_groups_vargs(class, parent, devt, drvdata, NULL, fmt, vargs); va_end(vargs); return dev; } EXPORT_SYMBOL_GPL(device_create); /** * device_create_with_groups - creates a device and registers it with sysfs * @class: pointer to the struct class that this device should be registered to * @parent: pointer to the parent struct device of this new device, if any * @devt: the dev_t for the char device to be added * @drvdata: the data to be added to the device for callbacks * @groups: NULL-terminated list of attribute groups to be created * @fmt: string for the device's name * * This function can be used by char device classes. A struct device * will be created in sysfs, registered to the specified class. * Additional attributes specified in the groups parameter will also * be created automatically. * * A "dev" file will be created, showing the dev_t for the device, if * the dev_t is not 0,0. * If a pointer to a parent struct device is passed in, the newly created * struct device will be a child of that device in sysfs. * The pointer to the struct device will be returned from the call. * Any further sysfs files that might be required can be created using this * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: the struct class passed to this function must have previously * been created with a call to class_create(). */ struct device *device_create_with_groups(struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...) { va_list vargs; struct device *dev; va_start(vargs, fmt); dev = device_create_groups_vargs(class, parent, devt, drvdata, groups, fmt, vargs); va_end(vargs); return dev; } EXPORT_SYMBOL_GPL(device_create_with_groups); /** * device_destroy - removes a device that was created with device_create() * @class: pointer to the struct class that this device was registered with * @devt: the dev_t of the device that was previously registered * * This call unregisters and cleans up a device that was created with a * call to device_create(). */ void device_destroy(struct class *class, dev_t devt) { struct device *dev; dev = class_find_device_by_devt(class, devt); if (dev) { put_device(dev); device_unregister(dev); } } EXPORT_SYMBOL_GPL(device_destroy); /** * device_rename - renames a device * @dev: the pointer to the struct device to be renamed * @new_name: the new name of the device * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of device_rename * on the same device to ensure that new_name is valid and * won't conflict with other devices. * * Note: Don't call this function. Currently, the networking layer calls this * function, but that will change. The following text from Kay Sievers offers * some insight: * * Renaming devices is racy at many levels, symlinks and other stuff are not * replaced atomically, and you get a "move" uevent, but it's not easy to * connect the event to the old and new device. Device nodes are not renamed at * all, there isn't even support for that in the kernel now. * * In the meantime, during renaming, your target name might be taken by another * driver, creating conflicts. Or the old name is taken directly after you * renamed it -- then you get events for the same DEVPATH, before you even see * the "move" event. It's just a mess, and nothing new should ever rely on * kernel device renaming. Besides that, it's not even implemented now for * other things than (driver-core wise very simple) network devices. * * We are currently about to change network renaming in udev to completely * disallow renaming of devices in the same namespace as the kernel uses, * because we can't solve the problems properly, that arise with swapping names * of multiple interfaces without races. Means, renaming of eth[0-9]* will only * be allowed to some other name than eth[0-9]*, for the aforementioned * reasons. * * Make up a "real" name in the driver before you register anything, or add * some other attributes for userspace to find the device, or use udev to add * symlinks -- but never rename kernel devices later, it's a complete mess. We * don't even want to get into that and try to implement the missing pieces in * the core. We really have other pieces to fix in the driver core mess. :) */ int device_rename(struct device *dev, const char *new_name) { struct kobject *kobj = &dev->kobj; char *old_device_name = NULL; int error; dev = get_device(dev); if (!dev) return -EINVAL; dev_dbg(dev, "renaming to %s\n", new_name); old_device_name = kstrdup(dev_name(dev), GFP_KERNEL); if (!old_device_name) { error = -ENOMEM; goto out; } if (dev->class) { error = sysfs_rename_link_ns(&dev->class->p->subsys.kobj, kobj, old_device_name, new_name, kobject_namespace(kobj)); if (error) goto out; } error = kobject_rename(kobj, new_name); if (error) goto out; out: put_device(dev); kfree(old_device_name); return error; } EXPORT_SYMBOL_GPL(device_rename); static int device_move_class_links(struct device *dev, struct device *old_parent, struct device *new_parent) { int error = 0; if (old_parent) sysfs_remove_link(&dev->kobj, "device"); if (new_parent) error = sysfs_create_link(&dev->kobj, &new_parent->kobj, "device"); return error; } /** * device_move - moves a device to a new parent * @dev: the pointer to the struct device to be moved * @new_parent: the new parent of the device (can be NULL) * @dpm_order: how to reorder the dpm_list */ int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order) { int error; struct device *old_parent; struct kobject *new_parent_kobj; dev = get_device(dev); if (!dev) return -EINVAL; device_pm_lock(); new_parent = get_device(new_parent); new_parent_kobj = get_device_parent(dev, new_parent); if (IS_ERR(new_parent_kobj)) { error = PTR_ERR(new_parent_kobj); put_device(new_parent); goto out; } pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev), __func__, new_parent ? dev_name(new_parent) : "<NULL>"); error = kobject_move(&dev->kobj, new_parent_kobj); if (error) { cleanup_glue_dir(dev, new_parent_kobj); put_device(new_parent); goto out; } old_parent = dev->parent; dev->parent = new_parent; if (old_parent) klist_remove(&dev->p->knode_parent); if (new_parent) { klist_add_tail(&dev->p->knode_parent, &new_parent->p->klist_children); set_dev_node(dev, dev_to_node(new_parent)); } if (dev->class) { error = device_move_class_links(dev, old_parent, new_parent); if (error) { /* We ignore errors on cleanup since we're hosed anyway... */ device_move_class_links(dev, new_parent, old_parent); if (!kobject_move(&dev->kobj, &old_parent->kobj)) { if (new_parent) klist_remove(&dev->p->knode_parent); dev->parent = old_parent; if (old_parent) { klist_add_tail(&dev->p->knode_parent, &old_parent->p->klist_children); set_dev_node(dev, dev_to_node(old_parent)); } } cleanup_glue_dir(dev, new_parent_kobj); put_device(new_parent); goto out; } } switch (dpm_order) { case DPM_ORDER_NONE: break; case DPM_ORDER_DEV_AFTER_PARENT: device_pm_move_after(dev, new_parent); devices_kset_move_after(dev, new_parent); break; case DPM_ORDER_PARENT_BEFORE_DEV: device_pm_move_before(new_parent, dev); devices_kset_move_before(new_parent, dev); break; case DPM_ORDER_DEV_LAST: device_pm_move_last(dev); devices_kset_move_last(dev); break; } put_device(old_parent); out: device_pm_unlock(); put_device(dev); return error; } EXPORT_SYMBOL_GPL(device_move); static int device_attrs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { struct kobject *kobj = &dev->kobj; struct class *class = dev->class; const struct device_type *type = dev->type; int error; if (class) { /* * Change the device groups of the device class for @dev to * @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, class->dev_groups, kuid, kgid); if (error) return error; } if (type) { /* * Change the device groups of the device type for @dev to * @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, type->groups, kuid, kgid); if (error) return error; } /* Change the device groups of @dev to @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, dev->groups, kuid, kgid); if (error) return error; if (device_supports_offline(dev) && !dev->offline_disabled) { /* Change online device attributes of @dev to @kuid/@kgid. */ error = sysfs_file_change_owner(kobj, dev_attr_online.attr.name, kuid, kgid); if (error) return error; } return 0; } /** * device_change_owner - change the owner of an existing device. * @dev: device. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This changes the owner of @dev and its corresponding sysfs entries to * @kuid/@kgid. This function closely mirrors how @dev was added via driver * core. * * Returns 0 on success or error code on failure. */ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { int error; struct kobject *kobj = &dev->kobj; dev = get_device(dev); if (!dev) return -EINVAL; /* * Change the kobject and the default attributes and groups of the * ktype associated with it to @kuid/@kgid. */ error = sysfs_change_owner(kobj, kuid, kgid); if (error) goto out; /* * Change the uevent file for @dev to the new owner. The uevent file * was created in a separate step when @dev got added and we mirror * that step here. */ error = sysfs_file_change_owner(kobj, dev_attr_uevent.attr.name, kuid, kgid); if (error) goto out; /* * Change the device groups, the device groups associated with the * device class, and the groups associated with the device type of @dev * to @kuid/@kgid. */ error = device_attrs_change_owner(dev, kuid, kgid); if (error) goto out; error = dpm_sysfs_change_owner(dev, kuid, kgid); if (error) goto out; #ifdef CONFIG_BLOCK if (sysfs_deprecated && dev->class == &block_class) goto out; #endif /* * Change the owner of the symlink located in the class directory of * the device class associated with @dev which points to the actual * directory entry for @dev to @kuid/@kgid. This ensures that the * symlink shows the same permissions as its target. */ error = sysfs_link_change_owner(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev), kuid, kgid); if (error) goto out; out: put_device(dev); return error; } EXPORT_SYMBOL_GPL(device_change_owner); /** * device_shutdown - call ->shutdown() on each device to shutdown. */ void device_shutdown(void) { struct device *dev, *parent; wait_for_device_probe(); device_block_probing(); cpufreq_suspend(); spin_lock(&devices_kset->list_lock); /* * Walk the devices list backward, shutting down each in turn. * Beware that device unplug events may also start pulling * devices offline, even as the system is shutting down. */ while (!list_empty(&devices_kset->list)) { dev = list_entry(devices_kset->list.prev, struct device, kobj.entry); /* * hold reference count of device's parent to * prevent it from being freed because parent's * lock is to be held */ parent = get_device(dev->parent); get_device(dev); /* * Make sure the device is off the kset list, in the * event that dev->*->shutdown() doesn't remove it. */ list_del_init(&dev->kobj.entry); spin_unlock(&devices_kset->list_lock); /* hold lock to avoid race with probe/release */ if (parent) device_lock(parent); device_lock(dev); /* Don't allow any more runtime suspends */ pm_runtime_get_noresume(dev); pm_runtime_barrier(dev); if (dev->class && dev->class->shutdown_pre) { if (initcall_debug) dev_info(dev, "shutdown_pre\n"); dev->class->shutdown_pre(dev); } if (dev->bus && dev->bus->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->bus->shutdown(dev); } else if (dev->driver && dev->driver->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->driver->shutdown(dev); } device_unlock(dev); if (parent) device_unlock(parent); put_device(dev); put_device(parent); spin_lock(&devices_kset->list_lock); } spin_unlock(&devices_kset->list_lock); } /* * Device logging functions */ #ifdef CONFIG_PRINTK static void set_dev_info(const struct device *dev, struct dev_printk_info *dev_info) { const char *subsys; memset(dev_info, 0, sizeof(*dev_info)); if (dev->class) subsys = dev->class->name; else if (dev->bus) subsys = dev->bus->name; else return; strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem)); /* * Add device identifier DEVICE=: * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname */ if (MAJOR(dev->devt)) { char c; if (strcmp(subsys, "block") == 0) c = 'b'; else c = 'c'; snprintf(dev_info->device, sizeof(dev_info->device), "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt)); } else if (strcmp(subsys, "net") == 0) { struct net_device *net = to_net_dev(dev); snprintf(dev_info->device, sizeof(dev_info->device), "n%u", net->ifindex); } else { snprintf(dev_info->device, sizeof(dev_info->device), "+%s:%s", subsys, dev_name(dev)); } } int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args) { struct dev_printk_info dev_info; set_dev_info(dev, &dev_info); return vprintk_emit(0, level, &dev_info, fmt, args); } EXPORT_SYMBOL(dev_vprintk_emit); int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = dev_vprintk_emit(level, dev, fmt, args); va_end(args); return r; } EXPORT_SYMBOL(dev_printk_emit); static void __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) { if (dev) dev_printk_emit(level[1] - '0', dev, "%s %s: %pV", dev_driver_string(dev), dev_name(dev), vaf); else printk("%s(NULL device *): %pV", level, vaf); } void dev_printk(const char *level, const struct device *dev, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; __dev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(dev_printk); #define define_dev_printk_level(func, kern_level) \ void func(const struct device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __dev_printk(kern_level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_dev_printk_level(_dev_emerg, KERN_EMERG); define_dev_printk_level(_dev_alert, KERN_ALERT); define_dev_printk_level(_dev_crit, KERN_CRIT); define_dev_printk_level(_dev_err, KERN_ERR); define_dev_printk_level(_dev_warn, KERN_WARNING); define_dev_printk_level(_dev_notice, KERN_NOTICE); define_dev_printk_level(_dev_info, KERN_INFO); #endif /** * dev_err_probe - probe error check and log helper * @dev: the pointer to the struct device * @err: error value to test * @fmt: printf-style format string * @...: arguments as specified in the format string * * This helper implements common pattern present in probe functions for error * checking: print debug or error message depending if the error value is * -EPROBE_DEFER and propagate error upwards. * In case of -EPROBE_DEFER it sets also defer probe reason, which can be * checked later by reading devices_deferred debugfs attribute. * It replaces code sequence:: * * if (err != -EPROBE_DEFER) * dev_err(dev, ...); * else * dev_dbg(dev, ...); * return err; * * with:: * * return dev_err_probe(dev, err, ...); * * Returns @err. * */ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (err != -EPROBE_DEFER) { dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf); } else { device_set_deferred_probe_reason(dev, &vaf); dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf); } va_end(args); return err; } EXPORT_SYMBOL_GPL(dev_err_probe); static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) { return fwnode && !IS_ERR(fwnode->secondary); } /** * set_primary_fwnode - Change the primary firmware node of a given device. * @dev: Device to handle. * @fwnode: New primary firmware node of the device. * * Set the device's firmware node pointer to @fwnode, but if a secondary * firmware node of the device is present, preserve it. */ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { struct device *parent = dev->parent; struct fwnode_handle *fn = dev->fwnode; if (fwnode) { if (fwnode_is_primary(fn)) fn = fn->secondary; if (fn) { WARN_ON(fwnode->secondary); fwnode->secondary = fn; } dev->fwnode = fwnode; } else { if (fwnode_is_primary(fn)) { dev->fwnode = fn->secondary; if (!(parent && fn == parent->fwnode)) fn->secondary = NULL; } else { dev->fwnode = NULL; } } } EXPORT_SYMBOL_GPL(set_primary_fwnode); /** * set_secondary_fwnode - Change the secondary firmware node of a given device. * @dev: Device to handle. * @fwnode: New secondary firmware node of the device. * * If a primary firmware node of the device is present, set its secondary * pointer to @fwnode. Otherwise, set the device's firmware node pointer to * @fwnode. */ void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { if (fwnode) fwnode->secondary = ERR_PTR(-ENODEV); if (fwnode_is_primary(dev->fwnode)) dev->fwnode->secondary = fwnode; else dev->fwnode = fwnode; } EXPORT_SYMBOL_GPL(set_secondary_fwnode); /** * device_set_of_node_from_dev - reuse device-tree node of another device * @dev: device whose device-tree node is being set * @dev2: device whose device-tree node is being reused * * Takes another reference to the new device-tree node after first dropping * any reference held to the old node. */ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) { of_node_put(dev->of_node); dev->of_node = of_node_get(dev2->of_node); dev->of_node_reused = true; } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); void device_set_node(struct device *dev, struct fwnode_handle *fwnode) { dev->fwnode = fwnode; dev->of_node = to_of_node(fwnode); } EXPORT_SYMBOL_GPL(device_set_node); int device_match_name(struct device *dev, const void *name) { return sysfs_streq(dev_name(dev), name); } EXPORT_SYMBOL_GPL(device_match_name); int device_match_of_node(struct device *dev, const void *np) { return dev->of_node == np; } EXPORT_SYMBOL_GPL(device_match_of_node); int device_match_fwnode(struct device *dev, const void *fwnode) { return dev_fwnode(dev) == fwnode; } EXPORT_SYMBOL_GPL(device_match_fwnode); int device_match_devt(struct device *dev, const void *pdevt) { return dev->devt == *(dev_t *)pdevt; } EXPORT_SYMBOL_GPL(device_match_devt); int device_match_acpi_dev(struct device *dev, const void *adev) { return ACPI_COMPANION(dev) == adev; } EXPORT_SYMBOL(device_match_acpi_dev); int device_match_any(struct device *dev, const void *unused) { return 1; } EXPORT_SYMBOL_GPL(device_match_any); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE 5 #ifdef CONFIG_X86_64 # define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC #else # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t" "2:\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } #else /* __ASSEMBLY__ */ .macro STATIC_JUMP_IF_TRUE target, key, def .Lstatic_jump_\@: .if \def /* Equivalent to "jmp.d32 \target" */ .byte 0xe9 .long \target - .Lstatic_jump_after_\@ .Lstatic_jump_after_\@: .else .byte STATIC_KEY_INIT_NOP .endif .pushsection __jump_table, "aw" _ASM_ALIGN .long .Lstatic_jump_\@ - ., \target - . _ASM_PTR \key - . .popsection .endm .macro STATIC_JUMP_IF_FALSE target, key, def .Lstatic_jump_\@: .if \def .byte STATIC_KEY_INIT_NOP .else /* Equivalent to "jmp.d32 \target" */ .byte 0xe9 .long \target - .Lstatic_jump_after_\@ .Lstatic_jump_after_\@: .endif .pushsection __jump_table, "aw" _ASM_ALIGN .long .Lstatic_jump_\@ - ., \target - . _ASM_PTR \key + 1 - . .popsection .endm #endif /* __ASSEMBLY__ */ #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EMe(WB_REASON_FORKER_THREAD, "forker_thread") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_page_template, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = page->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_page_template, writeback_dirty_page, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DEFINE_EVENT(writeback_page_template, wait_on_page_writeback, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct page *page, struct bdi_writeback *wb), TP_ARGS(page, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_congest_waited_template, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed), TP_STRUCT__entry( __field( unsigned int, usec_timeout ) __field( unsigned int, usec_delayed ) ), TP_fast_assign( __entry->usec_timeout = usec_timeout; __entry->usec_delayed = usec_delayed; ), TP_printk("usec_timeout=%u usec_delayed=%u", __entry->usec_timeout, __entry->usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2014 Davidlohr Bueso. */ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/mm.h> #include <linux/vmacache.h> /* * Hash based on the pmd of addr if configured with MMU, which provides a good * hit rate for workloads with spatial locality. Otherwise, use pages. */ #ifdef CONFIG_MMU #define VMACACHE_SHIFT PMD_SHIFT #else #define VMACACHE_SHIFT PAGE_SHIFT #endif #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) /* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this * task's vmacache pertains to a different mm (ie, its own). There is * nothing we can do here. * * Also handle the case where a kernel thread has adopted this mm via * kthread_use_mm(). That kernel thread's vmacache is not applicable to this mm. */ static inline bool vmacache_valid_mm(struct mm_struct *mm) { return current->mm == mm && !(current->flags & PF_KTHREAD); } void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) { if (vmacache_valid_mm(newvma->vm_mm)) current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma; } static bool vmacache_valid(struct mm_struct *mm) { struct task_struct *curr; if (!vmacache_valid_mm(mm)) return false; curr = current; if (mm->vmacache_seqnum != curr->vmacache.seqnum) { /* * First attempt will always be invalid, initialize * the new cache for this task here. */ curr->vmacache.seqnum = mm->vmacache_seqnum; vmacache_flush(curr); return false; } return true; } struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) { int idx = VMACACHE_HASH(addr); int i; count_vm_vmacache_event(VMACACHE_FIND_CALLS); if (!vmacache_valid(mm)) return NULL; for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache.vmas[idx]; if (vma) { #ifdef CONFIG_DEBUG_VM_VMACACHE if (WARN_ON_ONCE(vma->vm_mm != mm)) break; #endif if (vma->vm_start <= addr && vma->vm_end > addr) { count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; } } if (++idx == VMACACHE_SIZE) idx = 0; } return NULL; } #ifndef CONFIG_MMU struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, unsigned long start, unsigned long end) { int idx = VMACACHE_HASH(start); int i; count_vm_vmacache_event(VMACACHE_FIND_CALLS); if (!vmacache_valid(mm)) return NULL; for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache.vmas[idx]; if (vma && vma->vm_start == start && vma->vm_end == end) { count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; } if (++idx == VMACACHE_SIZE) idx = 0; } return NULL; } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set. */ unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next); /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set in both. */ int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next_and); /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Returns >= nr_cpu_ids if no cpus set. */ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } EXPORT_SYMBOL(cpumask_any_but); /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Returns >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>) * Returns TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(zalloc_cpumask_var_node); /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. */ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } EXPORT_SYMBOL(alloc_cpumask_var); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } EXPORT_SYMBOL(zalloc_cpumask_var); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); if (!*mask) panic("%s: Failed to allocate %u bytes\n", __func__, cpumask_size()); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free_early(__pa(mask), cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number * @node: local numa_node * * This function selects an online CPU according to a numa aware policy; * local cpus are returned first, followed by non-local ones, then it * wraps around. * * It's not very efficient, but useful for setup. */ unsigned int cpumask_local_spread(unsigned int i, int node) { int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; } else { /* NUMA first. */ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) if (i-- == 0) return cpu; for_each_cpu(cpu, cpu_online_mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; if (i-- == 0) return cpu; } } BUG(); } EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** * Returns an arbitrary cpu within srcp1 & srcp2. * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * * Returns >= nr_cpu_ids if the intersection is empty. */ int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = cpumask_next_and(prev, src1p, src2p); if (next >= nr_cpu_ids) next = cpumask_first_and(src1p, src2p); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_and_distribute); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RATELIMIT_H #define _LINUX_RATELIMIT_H #include <linux/ratelimit_types.h> #include <linux/sched.h> #include <linux/spinlock.h> static inline void ratelimit_state_init(struct ratelimit_state *rs, int interval, int burst) { memset(rs, 0, sizeof(*rs)); raw_spin_lock_init(&rs->lock); rs->interval = interval; rs->burst = burst; } static inline void ratelimit_default_init(struct ratelimit_state *rs) { return ratelimit_state_init(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); } static inline void ratelimit_state_exit(struct ratelimit_state *rs) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) return; if (rs->missed) { pr_warn("%s: %d output lines suppressed due to ratelimiting\n", current->comm, rs->missed); rs->missed = 0; } } static inline void ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags) { rs->flags = flags; } extern struct ratelimit_state printk_ratelimit_state; #ifdef CONFIG_PRINTK #define WARN_ON_RATELIMIT(condition, state) ({ \ bool __rtn_cond = !!(condition); \ WARN_ON(__rtn_cond && __ratelimit(state)); \ __rtn_cond; \ }) #define WARN_RATELIMIT(condition, format, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ int rtn = !!(condition); \ \ if (unlikely(rtn && __ratelimit(&_rs))) \ WARN(rtn, format, ##__VA_ARGS__); \ \ rtn; \ }) #else #define WARN_ON_RATELIMIT(condition, state) \ WARN_ON(condition) #define WARN_RATELIMIT(condition, format, ...) \ ({ \ int rtn = WARN(condition, format, ##__VA_ARGS__); \ rtn; \ }) #endif #endif /* _LINUX_RATELIMIT_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; DEFINE_RAW_SPINLOCK(timekeeper_lock); /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the timekeeper_lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) { u64 max_cycles = tk->tkr_mono.clock->max_cycles; const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", offset, name, max_cycles); printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } } if (tk->underflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->underflow_seen = 0; } if (tk->overflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->overflow_seen = 0; } } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; unsigned int seq; /* * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; } while (read_seqcount_retry(&tk_core.seq, seq)); delta = clocksource_delta(now, last, mask); /* * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) { tk->underflow_seen = 1; delta = 0; } /* Cap delta value to the max_cycles values to avoid mult overflows */ if (unlikely(delta > max)) { tk->overflow_seen = 1; delta = tkr->clock->max_cycles; } return delta; } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; /* read clocksource */ cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); return delta; } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET static u32 default_arch_gettimeoffset(void) { return 0; } u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; #else static inline u32 arch_gettimeoffset(void) { return 0; } #endif static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; nsec = delta * tkr->mult + tkr->xtime_nsec; nsec >>= tkr->shift; /* If arch requires, add in get_arch_timeoffset() */ return nsec + arch_gettimeoffset(); } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; delta = timekeeping_get_delta(tkr); return timekeeping_delta_to_ns(tkr, delta); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); return timekeeping_delta_to_ns(tkr, delta); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_delta_to_ns(tkr, clocksource_delta( tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } u64 ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); u64 ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update(tk, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; u64 basem, baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_delta_to_ns(tkr, clocksource_delta(tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) *mono = basem + delta; return baser + delta; } /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. */ u64 ktime_get_real_fast_ns(void) { return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * ktime_get_fast_timestamps: - NMI safe timestamps * @snapshot: Pointer to timestamp storage * * Stores clock monotonic, boottime and realtime timestamps. * * Boot time is a racy access on 32bit systems if the sleep time injection * happens late during resume and not in timekeeping_resume(). That could * be avoided by expanding struct tk_read_base with boot offset for 32bit * and adding more overhead to the update. As this is a hard to observe * once per resume event which can be filtered with reasonable effort using * the accurate mono/real timestamps, it's probably not worth the trouble. * * Aside of that it might be possible on 32 and 64 bit to observe the * following when the sleep time injection happens late: * * CPU 0 CPU 1 * timekeeping_resume() * ktime_get_fast_timestamps() * mono, real = __ktime_get_real_fast() * inject_sleep_time() * update boot offset * boot = mono + bootoffset; * * That means that boot time already has the sleep time adjustment, but * real time does not. On the next readout both are in sync again. * * Preventing this for 64bit is not really feasible without destroying the * careful cache layout of the timekeeper because the sequence count and * struct tk_read_base would then need two cache lines instead of one. * * Access to the time keeper clock source is disabled accross the innermost * steps of suspend/resume. The accessors still work, but the timestamps * are frozen until time keeping is resumed which happens very early. * * For regular suspend/resume there is no observable difference vs. sched * clock, but it might affect some of the nasty low level debug printks. * * OTOH, access to sched clock is not guaranteed accross suspend/resume on * all systems either so it depends on the hardware in use. * * If that turns out to be a real problem then this could be mitigated by * using sched clock in a similar way as during early boot. But it's not as * trivial as on early boot because it needs some careful protection * against the clock monotonic timestamp jumping backwards on resume. */ void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) { struct timekeeper *tk = &tk_core.timekeeper; snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); } /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * The mirroring of the data to the shadow-timekeeper needs * to happen last here to ensure we don't over-write the * timekeeper structure on the next update with stale data */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); } /** * timekeeping_forward_now - update clock to the current time * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift; tk_normalize_xtime(tk); } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert mononotic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. This replaces the * get_seconds() interface which is not y2038 safe on 32bit systems. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource associated with the captured * system counter value is the same as the currently installed * timekeeper clocksource */ if (tk->tkr_mono.clock != system_counterval.cs) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); xt = tk_xtime(tk); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; goto out; } tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); if (!ret) { audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); } return ret; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @tv: pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 tmp; int ret = 0; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /** * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic * */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /** * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* * If the cs is in module, get a module reference. Succeeds * for built-in code (owner == NULL) as well. */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { old = tk->tkr_mono.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); module_put(old->owner); } else { module_put(new->owner); } } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * * Weak dummy function for arches that do not yet support it. * wall_time - current time as returned by persistent clock * boot_offset - offset that is defined as wall_time - boot_time * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tk, clock); tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @delta: pointer to a timespec delta value * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /** * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /** * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); suspend_timing_needed = false; timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); tick_resume(); hrtimers_resume(); } int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tk->tkr_mono.clock; cycle_now = tk->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update(tk, TK_MIRROR); halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplfies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tick_length())) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tick_length(); mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /** * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. * */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /** * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static void timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; u64 offset; int shift = 0, maxshift; unsigned int clock_set = 0; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; if (mode != TK_ADV_TICK) goto out; #else offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; #endif /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * * We could avoid this memcpy by switching pointers, but that * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this * memcpy under the tk_core.seq against one before we start * updating. */ timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) /* Have to call _delayed version, since in irq context*/ clock_was_set_delayed(); } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { timekeeping_advance(TK_ADV_TICK); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be postive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; unsigned long flags; struct timespec64 ts; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } tk_update_leap_state(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) timekeeping_advance(TK_ADV_FREQ); if (tai != orig_tai) clock_was_set(); ntp_notify_cmos_timer(); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ /** * xtime_update() - advances the timekeeping infrastructure * @ticks: number of ticks, that have elapsed since the last call. * * Must be called with interrupts disabled. */ void xtime_update(unsigned long ticks) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); do_timer(ticks); write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); update_wall_time(); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? */ int page_cluster; /* Protecting only lru_rotate.pvec which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; struct pagevec pvec; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * The following struct pagevec are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct lru_pvecs { local_lock_t lock; struct pagevec lru_add; struct pagevec lru_deactivate_file; struct pagevec lru_deactivate; struct pagevec lru_lazyfree; #ifdef CONFIG_SMP struct pagevec activate_page; #endif }; static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. */ static void __page_cache_release(struct page *page) { if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; unsigned long flags; spin_lock_irqsave(&pgdat->lru_lock, flags); lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&pgdat->lru_lock, flags); } __ClearPageWaiters(page); } static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); free_unref_page(page); } static void __put_compound_page(struct page *page) { /* * __page_cache_release() is supposed to be called for thp, not for * hugetlb. This is because hugetlb page does never have PageLRU set * (it's never listed to any LRU lists) and no memcg routines should * be called for hugetlb (it has a separate hugetlb_cgroup.) */ if (!PageHuge(page)) __page_cache_release(page); destroy_compound_page(page); } void __put_page(struct page *page) { if (is_zone_device_page(page)) { put_dev_pagemap(page->pgmap); /* * The page belongs to the device that created pgmap. Do * not return it to page allocator. */ return; } if (unlikely(PageCompound(page))) __put_compound_page(page); else __put_single_page(page); } EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru * * Release a list of pages which are strung together on page.lru. Currently * used by read_cache_pages() and related error recovery code. */ void put_pages_list(struct list_head *pages) { while (!list_empty(pages)) { struct page *victim; victim = lru_to_page(pages); list_del(&victim->lru); put_page(victim); } } EXPORT_SYMBOL(put_pages_list); /* * get_kernel_pages() - pin kernel pages in memory * @kiov: An array of struct kvec structures * @nr_segs: number of segments to pin * @write: pinning for read/write, currently ignored * @pages: array that receives pointers to the pages pinned. * Should be at least nr_segs long. * * Returns number of pages pinned. This may be fewer than the number * requested. If nr_pages is 0 or negative, returns 0. If no pages * were pinned, returns -errno. Each page returned must be released * with a put_page() call when it is finished with. */ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, struct page **pages) { int seg; for (seg = 0; seg < nr_segs; seg++) { if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); get_page(pages[seg]); } return seg; } EXPORT_SYMBOL_GPL(get_kernel_pages); /* * get_kernel_page() - pin a kernel page in memory * @start: starting kernel address * @write: pinning for read/write, currently ignored * @pages: array that receives pointer to the page pinned. * Must be at least nr_segs long. * * Returns 1 if page is pinned. If the page was not pinned, returns * -errno. The page returned must be released with a put_page() call * when it is finished with. */ int get_kernel_page(unsigned long start, int write, struct page **pages) { const struct kvec kiov = { .iov_base = (void *)start, .iov_len = PAGE_SIZE }; return get_kernel_pages(&kiov, 1, write, pages); } EXPORT_SYMBOL_GPL(get_kernel_page); static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), void *arg) { int i; struct pglist_data *pgdat = NULL; struct lruvec *lruvec; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); pgdat = pagepgdat; spin_lock_irqsave(&pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, pgdat); (*move_fn)(page, lruvec, arg); } if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); release_pages(pvec->pages, pvec->nr); pagevec_reinit(pvec); } static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, void *arg) { int *pgmoved = arg; if (PageLRU(page) && !PageUnevictable(page)) { del_page_from_lru_list(page, lruvec, page_lru(page)); ClearPageActive(page); add_page_to_lru_list_tail(page, lruvec, page_lru(page)); (*pgmoved) += thp_nr_pages(page); } } /* * pagevec_move_tail() must be called with IRQ disabled. * Otherwise this may cause nasty races. */ static void pagevec_move_tail(struct pagevec *pvec) { int pgmoved = 0; pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved); __count_vm_events(PGROTATED, pgmoved); } /* * Writeback is about to end against a page which has been marked for immediate * reclaim. If it still appears to be reclaimable, move it to the tail of the * inactive list. */ void rotate_reclaimable_page(struct page *page) { if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; get_page(page); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { do { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += nr_pages; else lruvec->anon_cost += nr_pages; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_page(struct page *page) { lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), page_is_file_lru(page), thp_nr_pages(page)); } static void __activate_page(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru); SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_activate(page); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } } #ifdef CONFIG_SMP static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, __activate_page, NULL); } static bool need_activate_page_drain(int cpu) { return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; } static void activate_page(struct page *page) { page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); local_unlock(&lru_pvecs.lock); } } #else static inline void activate_page_drain(int cpu) { } static void activate_page(struct page *page) { pg_data_t *pgdat = page_pgdat(page); page = compound_head(page); spin_lock_irq(&pgdat->lru_lock); __activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL); spin_unlock_irq(&pgdat->lru_lock); } #endif static void __lru_cache_activate_page(struct page *page) { struct pagevec *pvec; int i; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); /* * Search backwards on the optimistic assumption that the page being * activated has just been added to this pagevec. Note that only * the local pagevec is examined as a !PageLRU page could be in the * process of being released, reclaimed, migrated or on a remote * pagevec that is currently being drained. Furthermore, marking * a remote pagevec's page PageActive potentially hits a race where * a page is marked PageActive just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; if (pagevec_page == page) { SetPageActive(page); break; } } local_unlock(&lru_pvecs.lock); } /* * Mark a page as having seen activity. * * inactive,unreferenced -> inactive,referenced * inactive,referenced -> active,unreferenced * active,unreferenced -> active,referenced * * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ void mark_page_accessed(struct page *page) { page = compound_head(page); if (!PageReferenced(page)) { SetPageReferenced(page); } else if (PageUnevictable(page)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ } else if (!PageActive(page)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ if (PageLRU(page)) activate_page(page); else __lru_cache_activate_page(page); ClearPageReferenced(page); workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); } EXPORT_SYMBOL(mark_page_accessed); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. * * Queue the page for addition to the LRU via pagevec. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * pagevec is drained. This gives a chance for the caller of lru_cache_add() * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { struct pagevec *pvec; VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); get_page(page); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } EXPORT_SYMBOL(lru_cache_add); /** * lru_cache_add_inactive_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability * * Place @page on the inactive or unevictable LRU list, depending on its * evictability. */ void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { bool unevictable; VM_BUG_ON_PAGE(PageLRU(page), page); unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); } /* * If the page can not be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the page isn't page_mapped and dirty/writeback, the page * could reclaim asap using PG_reclaim. * * 1. active, mapped page -> none * 2. active, dirty/writeback page -> inactive, head, PG_reclaim * 3. inactive, mapped page -> none * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, why it moves inactive's head, the VM expects the page would * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, void *arg) { int lru; bool active; int nr_pages = thp_nr_pages(page); if (!PageLRU(page)) return; if (PageUnevictable(page)) return; /* Some processes are using the page */ if (page_mapped(page)) return; active = PageActive(page); lru = page_lru_base_type(page); del_page_from_lru_list(page, lruvec, lru + active); ClearPageActive(page); ClearPageReferenced(page); if (PageWriteback(page) || PageDirty(page)) { /* * PG_reclaim could be raced with end_page_writeback * It can make readahead confusing. But race window * is _really_ small and it's non-critical problem. */ add_page_to_lru_list(page, lruvec, lru); SetPageReclaim(page); } else { /* * The page's writeback ends up during pagevec * We moves tha page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec, lru); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); ClearPageActive(page); ClearPageReferenced(page); add_page_to_lru_list(page, lruvec, lru); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, LRU_INACTIVE_ANON + active); ClearPageActive(page); ClearPageReferenced(page); /* * Lazyfree pages are clean anonymous pages. They have * PG_swapbacked flag cleared, to distinguish them from normal * anonymous pages */ ClearPageSwapBacked(page); add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } } /* * Drain pages out of the cpu's pagevecs. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); if (pagevec_count(pvec)) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); activate_page_drain(cpu); } /** * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ void deactivate_file_page(struct page *page) { /* * In a workload with many unevictable page such as mprotect, * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); local_unlock(&lru_pvecs.lock); } } /* * deactivate_page - deactivate a page * @page: page to deactivate * * deactivate_page() moves @page to the inactive list if @page was on the active * list and was not an unevictable page. This is done to accelerate the reclaim * of @page. */ void deactivate_page(struct page *page) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); local_unlock(&lru_pvecs.lock); } } /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate * * mark_page_lazyfree() moves @page to the inactive file list. * This is done to accelerate the reclaim of @page. */ void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); local_unlock(&lru_pvecs.lock); } } void lru_add_drain(void) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&lru_pvecs.lock); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ void lru_add_drain_all(void) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee pagevec counter stores visible by this CPU are visible to * other CPUs before loading the current drain generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the new global * drain generation number is stored before loading pagevec counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ /** * release_pages - batched put_page() * @pages: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @pages. If it * fell to zero, remove the page from the LRU and free it. */ void release_pages(struct page **pages, int nr) { int i; LIST_HEAD(pages_to_free); struct pglist_data *locked_pgdat = NULL; struct lruvec *lruvec; unsigned long flags; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the * same pgdat. The lock is held only if pgdat != NULL. */ if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } page = compound_head(page); if (is_huge_zero_page(page)) continue; if (is_zone_device_page(page)) { if (locked_pgdat) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } /* * ZONE_DEVICE pages that return 'false' from * page_is_devmap_managed() do not require special * processing, and instead, expect a call to * put_page_testzero(). */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); continue; } } if (!put_page_testzero(page)) continue; if (PageCompound(page)) { if (locked_pgdat) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } __put_compound_page(page); continue; } if (PageLRU(page)) { struct pglist_data *pgdat = page_pgdat(page); if (pgdat != locked_pgdat) { if (locked_pgdat) spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); lock_batch = 0; locked_pgdat = pgdat; spin_lock_irqsave(&locked_pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, locked_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } __ClearPageWaiters(page); list_add(&page->lru, &pages_to_free); } if (locked_pgdat) spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); mem_cgroup_uncharge_list(&pages_to_free); free_unref_page_list(&pages_to_free); } EXPORT_SYMBOL(release_pages); /* * The pages which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __pagevec_release() will drain those queues here. __pagevec_lru_add() * and __pagevec_lru_add_active() call release_pages() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) { if (!pvec->percpu_pvec_drained) { lru_add_drain(); pvec->percpu_pvec_drained = true; } release_pages(pvec->pages, pagevec_count(pvec)); pagevec_reinit(pvec); } EXPORT_SYMBOL(__pagevec_release); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* used by __split_huge_page_refcount() */ void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_PAGE(!PageHead(page), page); VM_BUG_ON_PAGE(PageCompound(page_tail), page); VM_BUG_ON_PAGE(PageLRU(page_tail), page); lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock); if (!list) SetPageLRU(page_tail); if (likely(PageLRU(page))) list_add_tail(&page_tail->lru, &page->lru); else if (list) { /* page reclaim is reclaiming a huge page */ get_page(page_tail); list_add_tail(&page_tail->lru, list); } else { /* * Head page has not yet been counted, as an hpage, * so we must account for each subpage individually. * * Put page_tail on the list at the correct position * so they all end up in order. */ add_page_to_lru_list_tail(page_tail, lruvec, page_lru(page_tail)); } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { enum lru_list lru; int was_unevictable = TestClearPageUnevictable(page); int nr_pages = thp_nr_pages(page); VM_BUG_ON_PAGE(PageLRU(page), page); /* * Page becomes evictable in two ways: * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()]. * 2) Before acquiring LRU lock to put the page to correct LRU and then * a) do PageLRU check with lock [check_move_unevictable_pages] * b) do PageLRU check before lock [clear_page_mlock] * * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need * following strict ordering: * * #0: __pagevec_lru_add_fn #1: clear_page_mlock * * SetPageLRU() TestClearPageMlocked() * smp_mb() // explicit ordering // above provides strict * // ordering * PageMlocked() PageLRU() * * * if '#1' does not observe setting of PG_lru by '#0' and fails * isolation, the explicit barrier will make sure that page_evictable * check will put the page in correct LRU. Without smp_mb(), SetPageLRU * can be reordered after PageMlocked check and can make '#1' to fail * the isolation of the page whose Mlocked bit is cleared (#0 is also * looking at the same page) and the evictable page will be stranded * in an unevictable LRU. */ SetPageLRU(page); smp_mb__after_atomic(); if (page_evictable(page)) { lru = page_lru(page); if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { lru = LRU_UNEVICTABLE; ClearPageActive(page); SetPageUnevictable(page); if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_insertion(page, lru); } /* * Add the passed pages to the LRU, then drop the caller's refcount * on them. Reinitialises the caller's pagevec. */ void __pagevec_lru_add(struct pagevec *pvec) { pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL); } /** * pagevec_lookup_entries - gang pagecache lookup * @pvec: Where the resulting entries are placed * @mapping: The address_space to search * @start: The starting entry index * @nr_entries: The maximum number of pages * @indices: The cache indices corresponding to the entries in @pvec * * pagevec_lookup_entries() will search for and return a group of up * to @nr_pages pages and shadow entries in the mapping. All * entries are placed in @pvec. pagevec_lookup_entries() takes a * reference against actual pages in @pvec. * * The search returns a group of mapping-contiguous entries with * ascending indexes. There may be holes in the indices due to * not-present entries. * * Only one subpage of a Transparent Huge Page is returned in one call: * allowing truncate_inode_pages_range() to evict the whole THP without * cycling through a pagevec of extra references. * * pagevec_lookup_entries() returns the number of entries which were * found. */ unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_entries, pgoff_t *indices) { pvec->nr = find_get_entries(mapping, start, nr_entries, pvec->pages, indices); return pagevec_count(pvec); } /** * pagevec_remove_exceptionals - pagevec exceptionals pruning * @pvec: The pagevec to prune * * pagevec_lookup_entries() fills both pages and exceptional radix * tree entries into the pagevec. This function prunes all * exceptionals from @pvec without leaving holes, so that it can be * passed on to page-only pagevec operations. */ void pagevec_remove_exceptionals(struct pagevec *pvec) { int i, j; for (i = 0, j = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; if (!xa_is_value(page)) pvec->pages[j++] = page; } pvec->nr = j; } /** * pagevec_lookup_range - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search * @start: The starting page index * @end: The final page index * * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE * pages in the mapping starting from index @start and upto index @end * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a * reference against the pages in @pvec. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. We * also update @start to index the next page for the traversal. * * pagevec_lookup_range() returns the number of pages which were found. If this * number is smaller than PAGEVEC_SIZE, the end of specified range has been * reached. */ unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end) { pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned max_pages) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_nr_tag); /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } #ifdef CONFIG_DEV_PAGEMAP_OPS void put_devmap_managed_page(struct page *page) { int count; if (WARN_ON_ONCE(!page_is_devmap_managed(page))) return; count = page_ref_dec_return(page); /* * devmap page refcounts are 1-based, rather than 0-based: if * refcount is 1, then the page is free and the refcount is * stable because nobody holds a reference on the page. */ if (count == 1) free_devmap_managed_page(page); else if (!count) __put_page(page); } EXPORT_SYMBOL(put_devmap_managed_page); #endif |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to generic timeout handling of requests. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blkdev.h> #include <linux/fault-inject.h> #include "blk.h" #include "blk-mq.h" #ifdef CONFIG_FAIL_IO_TIMEOUT static DECLARE_FAULT_ATTR(fail_io_timeout); static int __init setup_fail_io_timeout(char *str) { return setup_fault_attr(&fail_io_timeout, str); } __setup("fail_io_timeout=", setup_fail_io_timeout); bool __blk_should_fake_timeout(struct request_queue *q) { return should_fail(&fail_io_timeout, 1); } EXPORT_SYMBOL_GPL(__blk_should_fake_timeout); static int __init fail_io_timeout_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout", NULL, &fail_io_timeout); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_io_timeout_debugfs); ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags); return sprintf(buf, "%d\n", set != 0); } ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); int val; if (count) { struct request_queue *q = disk->queue; char *p = (char *) buf; val = simple_strtoul(p, &p, 10); if (val) blk_queue_flag_set(QUEUE_FLAG_FAIL_IO, q); else blk_queue_flag_clear(QUEUE_FLAG_FAIL_IO, q); } return count; } #endif /* CONFIG_FAIL_IO_TIMEOUT */ /** * blk_abort_request - Request recovery for the specified command * @req: pointer to the request of interest * * This function requests that the block layer start recovery for the * request by deleting the timer and calling the q's timeout function. * LLDDs who implement their own error recovery MAY ignore the timeout * event if they generated blk_abort_request. */ void blk_abort_request(struct request *req) { /* * All we need to ensure is that timeout scan takes place * immediately and that scan sees the new timeout value. * No need for fancy synchronizations. */ WRITE_ONCE(req->deadline, jiffies); kblockd_schedule_work(&req->q->timeout_work); } EXPORT_SYMBOL_GPL(blk_abort_request); static unsigned long blk_timeout_mask __read_mostly; static int __init blk_timeout_init(void) { blk_timeout_mask = roundup_pow_of_two(HZ) - 1; return 0; } late_initcall(blk_timeout_init); /* * Just a rough estimate, we don't care about specific values for timeouts. */ static inline unsigned long blk_round_jiffies(unsigned long j) { return (j + blk_timeout_mask) + 1; } unsigned long blk_rq_timeout(unsigned long timeout) { unsigned long maxt; maxt = blk_round_jiffies(jiffies + BLK_MAX_TIMEOUT); if (time_after(timeout, maxt)) timeout = maxt; return timeout; } /** * blk_add_timer - Start timeout timer for a single request * @req: request that is about to start running. * * Notes: * Each request has its own timer, and as it is added to the queue, we * set up the timer. When the request completes, we cancel the timer. */ void blk_add_timer(struct request *req) { struct request_queue *q = req->q; unsigned long expiry; /* * Some LLDs, like scsi, peek at the timeout to prevent a * command from being retried forever. */ if (!req->timeout) req->timeout = q->rq_timeout; req->rq_flags &= ~RQF_TIMED_OUT; expiry = jiffies + req->timeout; WRITE_ONCE(req->deadline, expiry); /* * If the timer isn't already pending or this timeout is earlier * than an existing one, modify the timer. Round up to next nearest * second. */ expiry = blk_rq_timeout(blk_round_jiffies(expiry)); if (!timer_pending(&q->timeout) || time_before(expiry, q->timeout.expires)) { unsigned long diff = q->timeout.expires - expiry; /* * Due to added timer slack to group timers, the timer * will often be a little in front of what we asked for. * So apply some tolerance here too, otherwise we keep * modifying the timer because expires for value X * will be X + something. */ if (!timer_pending(&q->timeout) || (diff >= HZ / 2)) mod_timer(&q->timeout, expiry); } } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/dir.c - kernfs directory implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/sched.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/hash.h> #include "kernfs-internal.h" DEFINE_MUTEX(kernfs_mutex); static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() * will perform wakeups when releasing console_sem. Holding rename_lock * will introduce deadlock if the scheduler reads the kernfs_name in the * wakeup path. */ static DEFINE_SPINLOCK(kernfs_pr_cont_lock); static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by pr_cont_lock */ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) static bool kernfs_active(struct kernfs_node *kn) { lockdep_assert_held(&kernfs_mutex); return atomic_read(&kn->active) >= 0; } static bool kernfs_lockdep(struct kernfs_node *kn) { #ifdef CONFIG_DEBUG_LOCK_ALLOC return kn->flags & KERNFS_LOCKDEP; #else return false; #endif } static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) { if (!kn) return strlcpy(buf, "(null)", buflen); return strlcpy(buf, kn->parent ? kn->name : "/", buflen); } /* kernfs_node_depth - compute depth from @from to @to */ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; while (to->parent && to != from) { depth++; to = to->parent; } return depth; } static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, struct kernfs_node *b) { size_t da, db; struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b); if (ra != rb) return NULL; da = kernfs_depth(ra->kn, a); db = kernfs_depth(rb->kn, b); while (da > db) { a = a->parent; da--; } while (db > da) { b = b->parent; db--; } /* worst case b and a will be the same at root */ while (b != a) { b = b->parent; a = a->parent; } return a; } /** * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to, * where kn_from is treated as root of the path. * @kn_from: kernfs node which should be treated as root for the path * @kn_to: kernfs node to which path is needed * @buf: buffer to copy the path into * @buflen: size of @buf * * We need to handle couple of scenarios here: * [1] when @kn_from is an ancestor of @kn_to at some level * kn_from: /n1/n2/n3 * kn_to: /n1/n2/n3/n4/n5 * result: /n4/n5 * * [2] when @kn_from is on a different hierarchy and we need to find common * ancestor between @kn_from and @kn_to. * kn_from: /n1/n2/n3/n4 * kn_to: /n1/n2/n5 * result: /../../n5 * OR * kn_from: /n1/n2/n3/n4/n5 [depth=5] * kn_to: /n1/n2/n3 [depth=3] * result: /../.. * * [3] when @kn_to is NULL result will be "(null)" * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen) { struct kernfs_node *kn, *common; const char parent_str[] = "/.."; size_t depth_from, depth_to, len = 0; int i, j; if (!kn_to) return strlcpy(buf, "(null)", buflen); if (!kn_from) kn_from = kernfs_root(kn_to)->kn; if (kn_from == kn_to) return strlcpy(buf, "/", buflen); if (!buf) return -EINVAL; common = kernfs_common_ancestor(kn_from, kn_to); if (WARN_ON(!common)) return -EINVAL; depth_to = kernfs_depth(common, kn_to); depth_from = kernfs_depth(common, kn_from); buf[0] = '\0'; for (i = 0; i < depth_from; i++) len += strlcpy(buf + len, parent_str, len < buflen ? buflen - len : 0); /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { for (kn = kn_to, j = 0; j < i; j++) kn = kn->parent; len += strlcpy(buf + len, "/", len < buflen ? buflen - len : 0); len += strlcpy(buf + len, kn->name, len < buflen ? buflen - len : 0); } return len; } /** * kernfs_name - obtain the name of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * Copies the name of @kn into @buf of @buflen bytes. The behavior is * similar to strlcpy(). It returns the length of @kn's name and if @buf * isn't long enough, it's filled upto @buflen-1 and nul terminated. * * Fills buffer with "(null)" if @kn is NULL. * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { unsigned long flags; int ret; spin_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_name_locked(kn, buf, buflen); spin_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } /** * kernfs_path_from_node - build path of node @to relative to @from. * @from: parent kernfs_node relative to which we need to build the path * @to: kernfs_node of interest * @buf: buffer to copy @to's path into * @buflen: size of @buf * * Builds @to's path relative to @from in @buf. @from and @to must * be on the same kernfs-root. If @from is not parent of @to, then a relative * path (which includes '..'s) as needed to reach from @from to @to is * returned. * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, char *buf, size_t buflen) { unsigned long flags; int ret; spin_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_path_from_node_locked(to, from, buf, buflen); spin_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } EXPORT_SYMBOL_GPL(kernfs_path_from_node); /** * pr_cont_kernfs_name - pr_cont name of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_name(struct kernfs_node *kn) { unsigned long flags; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); pr_cont("%s", kernfs_pr_cont_buf); spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * pr_cont_kernfs_path - pr_cont path of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_path(struct kernfs_node *kn) { unsigned long flags; int sz; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); if (sz < 0) { pr_cont("(error)"); goto out; } if (sz >= sizeof(kernfs_pr_cont_buf)) { pr_cont("(name too long)"); goto out; } pr_cont("%s", kernfs_pr_cont_buf); out: spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * kernfs_get_parent - determine the parent node and pin it * @kn: kernfs_node of interest * * Determines @kn's parent, pins and returns it. This function can be * called from any context. */ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { struct kernfs_node *parent; unsigned long flags; spin_lock_irqsave(&kernfs_rename_lock, flags); parent = kn->parent; kernfs_get(parent); spin_unlock_irqrestore(&kernfs_rename_lock, flags); return parent; } /** * kernfs_name_hash * @name: Null terminated string to hash * @ns: Namespace tag to hash * * Returns 31 bit hash of ns + name (so it fits in an off_t ) */ static unsigned int kernfs_name_hash(const char *name, const void *ns) { unsigned long hash = init_name_hash(ns); unsigned int len = strlen(name); while (len--) hash = partial_name_hash(*name++, hash); hash = end_name_hash(hash); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ if (hash < 2) hash += 2; if (hash >= INT_MAX) hash = INT_MAX - 1; return hash; } static int kernfs_name_compare(unsigned int hash, const char *name, const void *ns, const struct kernfs_node *kn) { if (hash < kn->hash) return -1; if (hash > kn->hash) return 1; if (ns < kn->ns) return -1; if (ns > kn->ns) return 1; return strcmp(name, kn->name); } static int kernfs_sd_compare(const struct kernfs_node *left, const struct kernfs_node *right) { return kernfs_name_compare(left->hash, left->name, left->ns, right); } /** * kernfs_link_sibling - link kernfs_node into sibling rbtree * @kn: kernfs_node of interest * * Link @kn into its sibling rbtree which starts from * @kn->parent->dir.children. * * Locking: * mutex_lock(kernfs_mutex) * * RETURNS: * 0 on susccess -EEXIST on failure. */ static int kernfs_link_sibling(struct kernfs_node *kn) { struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; while (*node) { struct kernfs_node *pos; int result; pos = rb_to_kn(*node); parent = *node; result = kernfs_sd_compare(kn, pos); if (result < 0) node = &pos->rb.rb_left; else if (result > 0) node = &pos->rb.rb_right; else return -EEXIST; } /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); rb_insert_color(&kn->rb, &kn->parent->dir.children); /* successfully added, account subdir number */ if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs++; return 0; } /** * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree * @kn: kernfs_node of interest * * Try to unlink @kn from its sibling rbtree which starts from * kn->parent->dir.children. Returns %true if @kn was actually * removed, %false if @kn wasn't on the rbtree. * * Locking: * mutex_lock(kernfs_mutex) */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { if (RB_EMPTY_NODE(&kn->rb)) return false; if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs--; rb_erase(&kn->rb, &kn->parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } /** * kernfs_get_active - get an active reference to kernfs_node * @kn: kernfs_node to get an active reference to * * Get an active reference of @kn. This function is noop if @kn * is NULL. * * RETURNS: * Pointer to @kn on success, NULL on failure. */ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) { if (unlikely(!kn)) return NULL; if (!atomic_inc_unless_negative(&kn->active)) return NULL; if (kernfs_lockdep(kn)) rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_); return kn; } /** * kernfs_put_active - put an active reference to kernfs_node * @kn: kernfs_node to put an active reference to * * Put an active reference to @kn. This function is noop if @kn * is NULL. */ void kernfs_put_active(struct kernfs_node *kn) { int v; if (unlikely(!kn)) return; if (kernfs_lockdep(kn)) rwsem_release(&kn->dep_map, _RET_IP_); v = atomic_dec_return(&kn->active); if (likely(v != KN_DEACTIVATED_BIAS)) return; wake_up_all(&kernfs_root(kn)->deactivate_waitq); } /** * kernfs_drain - drain kernfs_node * @kn: kernfs_node to drain * * Drain existing usages and nuke all existing mmaps of @kn. Mutiple * removers may invoke this function concurrently on @kn and all will * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn) __releases(&kernfs_mutex) __acquires(&kernfs_mutex) { struct kernfs_root *root = kernfs_root(kn); lockdep_assert_held(&kernfs_mutex); WARN_ON_ONCE(kernfs_active(kn)); mutex_unlock(&kernfs_mutex); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS) lock_contended(&kn->dep_map, _RET_IP_); } /* but everyone should wait for draining */ wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); if (kernfs_lockdep(kn)) { lock_acquired(&kn->dep_map, _RET_IP_); rwsem_release(&kn->dep_map, _RET_IP_); } kernfs_drain_open_files(kn); mutex_lock(&kernfs_mutex); } /** * kernfs_get - get a reference count on a kernfs_node * @kn: the target kernfs_node */ void kernfs_get(struct kernfs_node *kn) { if (kn) { WARN_ON(!atomic_read(&kn->count)); atomic_inc(&kn->count); } } EXPORT_SYMBOL_GPL(kernfs_get); /** * kernfs_put - put a reference count on a kernfs_node * @kn: the target kernfs_node * * Put a reference count of @kn and destroy it if it reached zero. */ void kernfs_put(struct kernfs_node *kn) { struct kernfs_node *parent; struct kernfs_root *root; if (!kn || !atomic_dec_and_test(&kn->count)) return; root = kernfs_root(kn); repeat: /* * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ parent = kn->parent; WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", parent ? parent->name : "", kn->name, atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); kfree_const(kn->name); if (kn->iattr) { simple_xattrs_free(&kn->iattr->xattrs); kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); kmem_cache_free(kernfs_node_cache, kn); kn = parent; if (kn) { if (atomic_dec_and_test(&kn->count)) goto repeat; } else { /* just released the root kn, free @root too */ idr_destroy(&root->ino_idr); kfree(root); } } EXPORT_SYMBOL_GPL(kernfs_put); static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn; if (flags & LOOKUP_RCU) return -ECHILD; /* Always perform fresh lookup for negatives */ if (d_really_is_negative(dentry)) goto out_bad_unlocked; kn = kernfs_dentry_node(dentry); mutex_lock(&kernfs_mutex); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) goto out_bad; /* The kernfs node has been moved? */ if (kernfs_dentry_node(dentry->d_parent) != kn->parent) goto out_bad; /* The kernfs node has been renamed */ if (strcmp(dentry->d_name.name, kn->name) != 0) goto out_bad; /* The kernfs node has been moved to a different namespace */ if (kn->parent && kernfs_ns_enabled(kn->parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; mutex_unlock(&kernfs_mutex); return 1; out_bad: mutex_unlock(&kernfs_mutex); out_bad_unlocked: return 0; } const struct dentry_operations kernfs_dops = { .d_revalidate = kernfs_dop_revalidate, }; /** * kernfs_node_from_dentry - determine kernfs_node associated with a dentry * @dentry: the dentry in question * * Return the kernfs_node associated with @dentry. If @dentry is not a * kernfs one, %NULL is returned. * * While the returned kernfs_node will stay accessible as long as @dentry * is accessible, the returned node can be in any state and the caller is * fully responsible for determining what's accessible. */ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { if (dentry->d_sb->s_op == &kernfs_sops && !d_really_is_negative(dentry)) return kernfs_dentry_node(dentry); return NULL; } static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; u32 id_highbits; int ret; name = kstrdup_const(name, GFP_KERNEL); if (!name) return NULL; kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL); if (!kn) goto err_out1; idr_preload(GFP_KERNEL); spin_lock(&kernfs_idr_lock); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); if (ret >= 0 && ret < root->last_id_lowbits) root->id_highbits++; id_highbits = root->id_highbits; root->last_id_lowbits = ret; spin_unlock(&kernfs_idr_lock); idr_preload_end(); if (ret < 0) goto err_out2; kn->id = (u64)id_highbits << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); kn->name = name; kn->mode = mode; kn->flags = flags; if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = uid, .ia_gid = gid, }; ret = __kernfs_setattr(kn, &iattr); if (ret < 0) goto err_out3; } if (parent) { ret = security_kernfs_init_security(parent, kn); if (ret) goto err_out3; } return kn; err_out3: spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: kfree_const(name); return NULL; } struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; if (parent->mode & S_ISGID) { /* this code block imitates inode_init_owner() for * kernfs */ if (parent->iattr) gid = parent->iattr->ia_gid; if (flags & KERNFS_DIR) mode |= S_ISGID; } kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); kn->parent = parent; } return kn; } /* * kernfs_find_and_get_node_by_id - get kernfs_node from node id * @root: the kernfs root * @id: the target node id * * @id's lower 32bits encode ino and upper gen. If the gen portion is * zero, all generations are matched. * * RETURNS: * NULL on failure. Return a kernfs node with reference counter incremented */ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id) { struct kernfs_node *kn; ino_t ino = kernfs_id_ino(id); u32 gen = kernfs_id_gen(id); spin_lock(&kernfs_idr_lock); kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) goto err_unlock; if (sizeof(ino_t) >= sizeof(u64)) { /* we looked up with the low 32bits, compare the whole */ if (kernfs_ino(kn) != ino) goto err_unlock; } else { /* 0 matches all generations */ if (unlikely(gen && kernfs_gen(kn) != gen)) goto err_unlock; } /* * ACTIVATED is protected with kernfs_mutex but it was clear when * @kn was added to idr and we just wanna see it set. No need to * grab kernfs_mutex. */ if (unlikely(!(kn->flags & KERNFS_ACTIVATED) || !atomic_inc_not_zero(&kn->count))) goto err_unlock; spin_unlock(&kernfs_idr_lock); return kn; err_unlock: spin_unlock(&kernfs_idr_lock); return NULL; } /** * kernfs_add_one - add kernfs_node to parent without warning * @kn: kernfs_node to be added * * The caller must already have initialized @kn->parent. This * function increments nlink of the parent's inode if @kn is a * directory and link into the children list of the parent. * * RETURNS: * 0 on success, -EEXIST if entry with the given name already * exists. */ int kernfs_add_one(struct kernfs_node *kn) { struct kernfs_node *parent = kn->parent; struct kernfs_iattrs *ps_iattr; bool has_ns; int ret; mutex_lock(&kernfs_mutex); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", parent->name, kn->name)) goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) goto out_unlock; ret = -ENOENT; if (parent->flags & KERNFS_EMPTY_DIR) goto out_unlock; if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent)) goto out_unlock; kn->hash = kernfs_name_hash(kn->name, kn->ns); ret = kernfs_link_sibling(kn); if (ret) goto out_unlock; /* Update timestamps on the parent */ ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } mutex_unlock(&kernfs_mutex); /* * Activate the new node unless CREATE_DEACTIVATED is requested. * If not activated here, the kernfs user is responsible for * activating the node with kernfs_activate(). A node which hasn't * been activated is not visible to userland and its removal won't * trigger deactivation. */ if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return 0; out_unlock: mutex_unlock(&kernfs_mutex); return ret; } /** * kernfs_find_ns - find kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent. Returns pointer to * the found kernfs_node on success, %NULL on failure. */ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, const unsigned char *name, const void *ns) { struct rb_node *node = parent->dir.children.rb_node; bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; lockdep_assert_held(&kernfs_mutex); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", parent->name, name); return NULL; } hash = kernfs_name_hash(name, ns); while (node) { struct kernfs_node *kn; int result; kn = rb_to_kn(node); result = kernfs_name_compare(hash, name, ns, kn); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return kn; } return NULL; } static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, const void *ns) { size_t len; char *p, *name; lockdep_assert_held(&kernfs_mutex); spin_lock_irq(&kernfs_pr_cont_lock); len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); if (len >= sizeof(kernfs_pr_cont_buf)) { spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } p = kernfs_pr_cont_buf; while ((name = strsep(&p, "/")) && parent) { if (*name == '\0') continue; parent = kernfs_find_ns(parent, name, ns); } spin_unlock_irq(&kernfs_pr_cont_lock); return parent; } /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent and get a reference * if found. This function may sleep and returns pointer to the found * kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; mutex_lock(&kernfs_mutex); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); mutex_unlock(&kernfs_mutex); return kn; } EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** * kernfs_walk_and_get_ns - find and get kernfs_node with the given path * @parent: kernfs_node to search under * @path: path to look for * @ns: the namespace tag to use * * Look for kernfs_node with path @path under @parent and get a reference * if found. This function may sleep and returns pointer to the found * kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { struct kernfs_node *kn; mutex_lock(&kernfs_mutex); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); mutex_unlock(&kernfs_mutex); return kn; } /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags * @priv: opaque data associated with the new directory * * Returns the root of the new hierarchy on success, ERR_PTR() value on * failure. */ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { struct kernfs_root *root; struct kernfs_node *kn; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM); idr_init(&root->ino_idr); INIT_LIST_HEAD(&root->supers); /* * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino. * High bits generation. The starting value for both ino and * genenration is 1. Initialize upper 32bit allocation * accordingly. */ if (sizeof(ino_t) >= sizeof(u64)) root->id_highbits = 0; else root->id_highbits = 1; kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) { idr_destroy(&root->ino_idr); kfree(root); return ERR_PTR(-ENOMEM); } kn->priv = priv; kn->dir.root = root; root->syscall_ops = scops; root->flags = flags; root->kn = kn; init_waitqueue_head(&root->deactivate_waitq); if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return root; } /** * kernfs_destroy_root - destroy a kernfs hierarchy * @root: root of the hierarchy to destroy * * Destroy the hierarchy anchored at @root by removing all existing * directories and destroying @root. */ void kernfs_destroy_root(struct kernfs_root *root) { kernfs_remove(root->kn); /* will also free @root */ } /** * kernfs_create_dir_ns - create a directory * @parent: parent in which to create a new directory * @name: name of the new directory * @mode: mode of the new directory * @uid: uid of the new directory * @gid: gid of the new directory * @priv: opaque data associated with the new directory * @ns: optional namespace tag of the directory * * Returns the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, mode | S_IFDIR, uid, gid, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->dir.root = parent->dir.root; kn->ns = ns; kn->priv = priv; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } /** * kernfs_create_empty_dir - create an always empty directory * @parent: parent in which to create a new directory * @name: name of the new directory * * Returns the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->flags |= KERNFS_EMPTY_DIR; kn->dir.root = parent->dir.root; kn->ns = NULL; kn->priv = NULL; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct dentry *ret; struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; struct inode *inode; const void *ns = NULL; mutex_lock(&kernfs_mutex); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; kn = kernfs_find_ns(parent, dentry->d_name.name, ns); /* no such entry */ if (!kn || !kernfs_active(kn)) { ret = NULL; goto out_unlock; } /* attach dentry and inode */ inode = kernfs_get_inode(dir->i_sb, kn); if (!inode) { ret = ERR_PTR(-ENOMEM); goto out_unlock; } /* instantiate and hash dentry */ ret = d_splice_alias(inode, dentry); out_unlock: mutex_unlock(&kernfs_mutex); return ret; } static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct kernfs_node *parent = dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; int ret; if (!scops || !scops->mkdir) return -EPERM; if (!kernfs_get_active(parent)) return -ENODEV; ret = scops->mkdir(parent, dentry->d_name.name, mode); kernfs_put_active(parent); return ret; } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) { struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (!scops || !scops->rmdir) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; ret = scops->rmdir(kn); kernfs_put_active(kn); return ret; } static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct kernfs_node *kn = kernfs_dentry_node(old_dentry); struct kernfs_node *new_parent = new_dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (flags) return -EINVAL; if (!scops || !scops->rename) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; if (!kernfs_get_active(new_parent)) { kernfs_put_active(kn); return -ENODEV; } ret = scops->rename(kn, new_parent, new_dentry->d_name.name); kernfs_put_active(new_parent); kernfs_put_active(kn); return ret; } const struct inode_operations kernfs_dir_iops = { .lookup = kernfs_iop_lookup, .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .listxattr = kernfs_iop_listxattr, .mkdir = kernfs_iop_mkdir, .rmdir = kernfs_iop_rmdir, .rename = kernfs_iop_rename, }; static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos) { struct kernfs_node *last; while (true) { struct rb_node *rbn; last = pos; if (kernfs_type(pos) != KERNFS_DIR) break; rbn = rb_first(&pos->dir.children); if (!rbn) break; pos = rb_to_kn(rbn); } return last; } /** * kernfs_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: kernfs_node whose descendants to walk * * Find the next descendant to visit for post-order traversal of @root's * descendants. @root is included in the iteration and the last node to be * visited. */ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, struct kernfs_node *root) { struct rb_node *rbn; lockdep_assert_held(&kernfs_mutex); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) return kernfs_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ rbn = rb_next(&pos->rb); if (rbn) return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ return pos->parent; } /** * kernfs_activate - activate a node which started deactivated * @kn: kernfs_node whose subtree is to be activated * * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node * needs to be explicitly activated. A node which hasn't been activated * isn't visible to userland and deactivation is skipped during its * removal. This is useful to construct atomic init sequences where * creation of multiple nodes should either succeed or fail atomically. * * The caller is responsible for ensuring that this function is not called * after kernfs_remove*() is invoked on @kn. */ void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; mutex_lock(&kernfs_mutex); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { if (pos->flags & KERNFS_ACTIVATED) continue; WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb)); WARN_ON_ONCE(atomic_read(&pos->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &pos->active); pos->flags |= KERNFS_ACTIVATED; } mutex_unlock(&kernfs_mutex); } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos; lockdep_assert_held(&kernfs_mutex); /* * Short-circuit if non-root @kn has already finished removal. * This is for kernfs_remove_self() which plays with active ref * after removal. */ if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb))) return; pr_debug("kernfs %s: removing\n", kn->name); /* prevent any new usage under @kn by deactivating all nodes */ pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) if (kernfs_active(pos)) atomic_add(KN_DEACTIVATED_BIAS, &pos->active); /* deactivate and unlink the subtree node-by-node */ do { pos = kernfs_leftmost_descendant(kn); /* * kernfs_drain() drops kernfs_mutex temporarily and @pos's * base ref could have been put by someone else by the time * the function returns. Make sure it doesn't go away * underneath us. */ kernfs_get(pos); /* * Drain iff @kn was activated. This avoids draining and * its lockdep annotations for nodes which have never been * activated and allows embedding kernfs_remove() in create * error paths without worrying about draining. */ if (kn->flags & KERNFS_ACTIVATED) kernfs_drain(pos); else WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ if (!pos->parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = pos->parent ? pos->parent->iattr : NULL; /* update timestamps on the parent */ if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } kernfs_put(pos); } kernfs_put(pos); } while (pos != kn); } /** * kernfs_remove - remove a kernfs_node recursively * @kn: the kernfs_node to remove * * Remove @kn along with all its subdirectories and files. */ void kernfs_remove(struct kernfs_node *kn) { mutex_lock(&kernfs_mutex); __kernfs_remove(kn); mutex_unlock(&kernfs_mutex); } /** * kernfs_break_active_protection - break out of active protection * @kn: the self kernfs_node * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. Each invocation of * this function must also be matched with an invocation of * kernfs_unbreak_active_protection(). * * This function releases the active reference of @kn the caller is * holding. Once this function is called, @kn may be removed at any point * and the caller is solely responsible for ensuring that the objects it * dereferences are accessible. */ void kernfs_break_active_protection(struct kernfs_node *kn) { /* * Take out ourself out of the active ref dependency chain. If * we're called without an active ref, lockdep will complain. */ kernfs_put_active(kn); } /** * kernfs_unbreak_active_protection - undo kernfs_break_active_protection() * @kn: the self kernfs_node * * If kernfs_break_active_protection() was called, this function must be * invoked before finishing the kernfs operation. Note that while this * function restores the active reference, it doesn't and can't actually * restore the active protection - @kn may already or be in the process of * being removed. Once kernfs_break_active_protection() is invoked, that * protection is irreversibly gone for the kernfs operation instance. * * While this function may be called at any point after * kernfs_break_active_protection() is invoked, its most useful location * would be right before the enclosing kernfs operation returns. */ void kernfs_unbreak_active_protection(struct kernfs_node *kn) { /* * @kn->active could be in any state; however, the increment we do * here will be undone as soon as the enclosing kernfs operation * finishes and this temporary bump can't break anything. If @kn * is alive, nothing changes. If @kn is being deactivated, the * soon-to-follow put will either finish deactivation or restore * deactivated state. If @kn is already removed, the temporary * bump is guaranteed to be gone before @kn is released. */ atomic_inc(&kn->active); if (kernfs_lockdep(kn)) rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_); } /** * kernfs_remove_self - remove a kernfs_node from its own method * @kn: the self kernfs_node to remove * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. This can be used to * implement a file operation which deletes itself. * * For example, the "delete" file for a sysfs device directory can be * implemented by invoking kernfs_remove_self() on the "delete" file * itself. This function breaks the circular dependency of trying to * deactivate self while holding an active ref itself. It isn't necessary * to modify the usual removal path to use kernfs_remove_self(). The * "delete" implementation can simply invoke kernfs_remove_self() on self * before proceeding with the usual removal path. kernfs will ignore later * kernfs_remove() on self. * * kernfs_remove_self() can be called multiple times concurrently on the * same kernfs_node. Only the first one actually performs removal and * returns %true. All others will wait until the kernfs operation which * won self-removal finishes and return %false. Note that the losers wait * for the completion of not only the winning kernfs_remove_self() but also * the whole kernfs_ops which won the arbitration. This can be used to * guarantee, for example, all concurrent writes to a "delete" file to * finish only after the whole operation is complete. */ bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; mutex_lock(&kernfs_mutex); kernfs_break_active_protection(kn); /* * SUICIDAL is used to arbitrate among competing invocations. Only * the first one will actually perform removal. When the removal * is complete, SUICIDED is set and the active ref is restored * while holding kernfs_mutex. The ones which lost arbitration * waits for SUICDED && drained which can happen only after the * enclosing kernfs operation which executed the winning instance * of kernfs_remove_self() finished. */ if (!(kn->flags & KERNFS_SUICIDAL)) { kn->flags |= KERNFS_SUICIDAL; __kernfs_remove(kn); kn->flags |= KERNFS_SUICIDED; ret = true; } else { wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq; DEFINE_WAIT(wait); while (true) { prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE); if ((kn->flags & KERNFS_SUICIDED) && atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; mutex_unlock(&kernfs_mutex); schedule(); mutex_lock(&kernfs_mutex); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); ret = false; } /* * This must be done while holding kernfs_mutex; otherwise, waiting * for SUICIDED && deactivated could finish prematurely. */ kernfs_unbreak_active_protection(kn); mutex_unlock(&kernfs_mutex); return ret; } /** * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it * @parent: parent of the target * @name: name of the kernfs_node to remove * @ns: namespace tag of the kernfs_node to remove * * Look for the kernfs_node with @name and @ns under @parent and remove it. * Returns 0 on success, -ENOENT if such entry doesn't exist. */ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; if (!parent) { WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n", name); return -ENOENT; } mutex_lock(&kernfs_mutex); kn = kernfs_find_ns(parent, name, ns); if (kn) { kernfs_get(kn); __kernfs_remove(kn); kernfs_put(kn); } mutex_unlock(&kernfs_mutex); if (kn) return 0; else return -ENOENT; } /** * kernfs_rename_ns - move and rename a kernfs_node * @kn: target node * @new_parent: new parent to put @sd under * @new_name: new name * @new_ns: new namespace tag */ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { struct kernfs_node *old_parent; const char *old_name = NULL; int error; /* can't move or rename root */ if (!kn->parent) return -EINVAL; mutex_lock(&kernfs_mutex); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; error = 0; if ((kn->parent == new_parent) && (kn->ns == new_ns) && (strcmp(kn->name, new_name) == 0)) goto out; /* nothing to rename */ error = -EEXIST; if (kernfs_find_ns(new_parent, new_name, new_ns)) goto out; /* rename kernfs_node */ if (strcmp(kn->name, new_name) != 0) { error = -ENOMEM; new_name = kstrdup_const(new_name, GFP_KERNEL); if (!new_name) goto out; } else { new_name = NULL; } /* * Move to the appropriate place in the appropriate directories rbtree. */ kernfs_unlink_sibling(kn); kernfs_get(new_parent); /* rename_lock protects ->parent and ->name accessors */ spin_lock_irq(&kernfs_rename_lock); old_parent = kn->parent; kn->parent = new_parent; kn->ns = new_ns; if (new_name) { old_name = kn->name; kn->name = new_name; } spin_unlock_irq(&kernfs_rename_lock); kn->hash = kernfs_name_hash(kn->name, kn->ns); kernfs_link_sibling(kn); kernfs_put(old_parent); kfree_const(old_name); error = 0; out: mutex_unlock(&kernfs_mutex); return error; } /* Relationship between s_mode and the DT_xxx types */ static inline unsigned char dt_type(struct kernfs_node *kn) { return (kn->mode >> 12) & 15; } static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) { kernfs_put(filp->private_data); return 0; } static struct kernfs_node *kernfs_dir_pos(const void *ns, struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) { if (pos) { int valid = kernfs_active(pos) && pos->parent == parent && hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; } if (!pos && (hash > 1) && (hash < INT_MAX)) { struct rb_node *node = parent->dir.children.rb_node; while (node) { pos = rb_to_kn(node); if (hash < pos->hash) node = node->rb_left; else if (hash > pos->hash) node = node->rb_right; else break; } } /* Skip over entries which are dying/dead or in the wrong namespace */ while (pos && (!kernfs_active(pos) || pos->ns != ns)) { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } return pos; } static struct kernfs_node *kernfs_dir_next_pos(const void *ns, struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) { pos = kernfs_dir_pos(ns, parent, ino, pos); if (pos) { do { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } while (pos && (!kernfs_active(pos) || pos->ns != ns)); } return pos; } static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; const void *ns = NULL; if (!dir_emit_dots(file, ctx)) return 0; mutex_lock(&kernfs_mutex); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { const char *name = pos->name; unsigned int type = dt_type(pos); int len = strlen(name); ino_t ino = kernfs_ino(pos); ctx->pos = pos->hash; file->private_data = pos; kernfs_get(pos); mutex_unlock(&kernfs_mutex); if (!dir_emit(ctx, name, len, ino, type)) return 0; mutex_lock(&kernfs_mutex); } mutex_unlock(&kernfs_mutex); file->private_data = NULL; ctx->pos = INT_MAX; return 0; } const struct file_operations kernfs_dir_fops = { .read = generic_read_dir, .iterate_shared = kernfs_fop_readdir, .release = kernfs_dir_fop_release, .llseek = generic_file_llseek, }; |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H #include <asm/segment.h> #include <asm/page_types.h> #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ #ifdef __i386__ struct pt_regs { /* * NB: 32-bit x86 CPUs are inconsistent as what happens in the * following cases (where %seg represents a segment register): * * - pushl %seg: some do a 16-bit write and leave the high * bits alone * - movl %seg, [mem]: some do a 16-bit write despite the movl * - IDT entry: some (e.g. 486) will leave the high bits of CS * and (if applicable) SS undefined. * * Fortunately, x86-32 doesn't read the high bits on POP or IRET, * so we can just treat all of the segment registers as 16-bit * values. */ unsigned long bx; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; unsigned long bp; unsigned long ax; unsigned short ds; unsigned short __dsh; unsigned short es; unsigned short __esh; unsigned short fs; unsigned short __fsh; /* * On interrupt, gs and __gsh store the vector number. They never * store gs any more. */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; unsigned short __csh; unsigned long flags; unsigned long sp; unsigned short ss; unsigned short __ssh; }; #else /* __i386__ */ struct pt_regs { /* * C ABI says these regs are callee-preserved. They aren't saved on kernel entry * unless syscall needs a complete, fully filled "struct pt_regs". */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; unsigned long r8; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; /* * On syscall entry, this is syscall#. On CPU exception, this is error code. * On hw interrupt, it's IRQ number: */ unsigned long orig_ax; /* Return frame for iretq */ unsigned long ip; unsigned long cs; unsigned long flags; unsigned long sp; unsigned long ss; /* top of stack page */ }; #endif /* !__i386__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif #include <asm/proto.h> struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); static __always_inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } static __always_inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the * register set was from protected mode with RPL-3 CS value. This * tricky test checks that with one comparison. * * On x86_64, vm86 mode is mercifully nonexistent, and we don't need * the extra check. */ static __always_inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif } static inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return (regs->flags & X86_VM_MASK); #else return 0; /* No V86 mode support in long mode */ #endif } static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. */ return regs->cs == __USER_CS; #else /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif #else /* !CONFIG_X86_64 */ return false; #endif } /* * Determine whether the register set came from any context that is running in * 64-bit mode. */ static inline bool any_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 return !user_mode(regs) || user_64bit_mode(regs); #else return false; #endif } #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp static inline bool ip_within_syscall_gap(struct pt_regs *regs) { bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); #endif return ret; } #endif static __always_inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static __always_inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } static __always_inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } static __always_inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } static __always_inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } static __always_inline void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->flags & X86_EFLAGS_IF); } /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); extern const char *regs_query_register_name(unsigned int offset); #define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten. * @offset: offset number of the register. * * regs_get_register returns the value of a register. The @offset is the * offset of the register in struct pt_regs address which specified by @regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) { if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || offset == offsetof(struct pt_regs, ds) || offset == offsetof(struct pt_regs, es) || offset == offsetof(struct pt_regs, fs) || offset == offsetof(struct pt_regs, gs)) { return *(u16 *)((unsigned long)regs + offset); } #endif return *(unsigned long *)((unsigned long)regs + offset); } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns the address of the @n th entry of the * kernel stack which is specified by @regs. If the @n th entry is NOT in * the kernel stack, this returns NULL. */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return addr; else return NULL; } /* To avoid include hell, we can't include uaccess.h */ extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr; unsigned long val; long ret; addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } return 0; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * Note that this chooses most probably assignment, in some case * it can be incorrect. * This is expected to be called from kprobes or ftrace with regs * where the top of stack is the return address. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), offsetof(struct pt_regs, si), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), offsetof(struct pt_regs, r8), offsetof(struct pt_regs, r9), #define NR_REG_ARGUMENTS 6 #endif }; if (n >= NR_REG_ARGUMENTS) { n -= NR_REG_ARGUMENTS - 1; return regs_get_kernel_stack_nth(regs, n); } else return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); #ifdef CONFIG_X86_64 # define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) #else # define do_set_thread_area_64(p, s, t) (0) #endif #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PTRACE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Security server interface. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> * */ #ifndef _SELINUX_SECURITY_H_ #define _SELINUX_SECURITY_H_ #include <linux/compiler.h> #include <linux/dcache.h> #include <linux/magic.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include "flask.h" #include "policycap.h" #define SECSID_NULL 0x00000000 /* unspecified SID */ #define SECSID_WILD 0xffffffff /* wildcard SID */ #define SECCLASS_NULL 0x0000 /* no class */ /* Identify specific policy version changes */ #define POLICYDB_VERSION_BASE 15 #define POLICYDB_VERSION_BOOL 16 #define POLICYDB_VERSION_IPV6 17 #define POLICYDB_VERSION_NLCLASS 18 #define POLICYDB_VERSION_VALIDATETRANS 19 #define POLICYDB_VERSION_MLS 19 #define POLICYDB_VERSION_AVTAB 20 #define POLICYDB_VERSION_RANGETRANS 21 #define POLICYDB_VERSION_POLCAP 22 #define POLICYDB_VERSION_PERMISSIVE 23 #define POLICYDB_VERSION_BOUNDARY 24 #define POLICYDB_VERSION_FILENAME_TRANS 25 #define POLICYDB_VERSION_ROLETRANS 26 #define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS 27 #define POLICYDB_VERSION_DEFAULT_TYPE 28 #define POLICYDB_VERSION_CONSTRAINT_NAMES 29 #define POLICYDB_VERSION_XPERMS_IOCTL 30 #define POLICYDB_VERSION_INFINIBAND 31 #define POLICYDB_VERSION_GLBLUB 32 #define POLICYDB_VERSION_COMP_FTRANS 33 /* compressed filename transitions */ /* Range of policy versions we understand*/ #define POLICYDB_VERSION_MIN POLICYDB_VERSION_BASE #define POLICYDB_VERSION_MAX POLICYDB_VERSION_COMP_FTRANS /* Mask for just the mount related flags */ #define SE_MNTMASK 0x0f /* Super block security struct flags for mount options */ /* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */ #define CONTEXT_MNT 0x01 #define FSCONTEXT_MNT 0x02 #define ROOTCONTEXT_MNT 0x04 #define DEFCONTEXT_MNT 0x08 #define SBLABEL_MNT 0x10 /* Non-mount related flags */ #define SE_SBINITIALIZED 0x0100 #define SE_SBPROC 0x0200 #define SE_SBGENFS 0x0400 #define SE_SBGENFS_XATTR 0x0800 #define CONTEXT_STR "context" #define FSCONTEXT_STR "fscontext" #define ROOTCONTEXT_STR "rootcontext" #define DEFCONTEXT_STR "defcontext" #define SECLABEL_STR "seclabel" struct netlbl_lsm_secattr; extern int selinux_enabled_boot; /* * type_datum properties * available at the kernel policy version >= POLICYDB_VERSION_BOUNDARY */ #define TYPEDATUM_PROPERTY_PRIMARY 0x0001 #define TYPEDATUM_PROPERTY_ATTRIBUTE 0x0002 /* limitation of boundary depth */ #define POLICYDB_BOUNDS_MAXDEPTH 4 struct selinux_avc; struct selinux_policy; struct selinux_state { #ifdef CONFIG_SECURITY_SELINUX_DISABLE bool disabled; #endif #ifdef CONFIG_SECURITY_SELINUX_DEVELOP bool enforcing; #endif bool checkreqprot; bool initialized; bool policycap[__POLICYDB_CAPABILITY_MAX]; struct page *status_page; struct mutex status_lock; struct selinux_avc *avc; struct selinux_policy __rcu *policy; struct mutex policy_mutex; } __randomize_layout; void selinux_avc_init(struct selinux_avc **avc); extern struct selinux_state selinux_state; static inline bool selinux_initialized(const struct selinux_state *state) { /* do a synchronized load to avoid race conditions */ return smp_load_acquire(&state->initialized); } static inline void selinux_mark_initialized(struct selinux_state *state) { /* do a synchronized write to avoid race conditions */ smp_store_release(&state->initialized, true); } #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static inline bool enforcing_enabled(struct selinux_state *state) { return READ_ONCE(state->enforcing); } static inline void enforcing_set(struct selinux_state *state, bool value) { WRITE_ONCE(state->enforcing, value); } #else static inline bool enforcing_enabled(struct selinux_state *state) { return true; } static inline void enforcing_set(struct selinux_state *state, bool value) { } #endif static inline bool checkreqprot_get(const struct selinux_state *state) { return READ_ONCE(state->checkreqprot); } static inline void checkreqprot_set(struct selinux_state *state, bool value) { WRITE_ONCE(state->checkreqprot, value); } #ifdef CONFIG_SECURITY_SELINUX_DISABLE static inline bool selinux_disabled(struct selinux_state *state) { return READ_ONCE(state->disabled); } static inline void selinux_mark_disabled(struct selinux_state *state) { WRITE_ONCE(state->disabled, true); } #else static inline bool selinux_disabled(struct selinux_state *state) { return false; } #endif static inline bool selinux_policycap_netpeer(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_NETPEER]); } static inline bool selinux_policycap_openperm(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_OPENPERM]); } static inline bool selinux_policycap_extsockclass(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_EXTSOCKCLASS]); } static inline bool selinux_policycap_alwaysnetwork(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_ALWAYSNETWORK]); } static inline bool selinux_policycap_cgroupseclabel(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_CGROUPSECLABEL]); } static inline bool selinux_policycap_nnp_nosuid_transition(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_NNP_NOSUID_TRANSITION]); } static inline bool selinux_policycap_genfs_seclabel_symlinks(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]); } static inline bool selinux_policycap_ioctl_skip_cloexec(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_IOCTL_SKIP_CLOEXEC]); } struct selinux_policy_convert_data; struct selinux_load_state { struct selinux_policy *policy; struct selinux_policy_convert_data *convert_data; }; int security_mls_enabled(struct selinux_state *state); int security_load_policy(struct selinux_state *state, void *data, size_t len, struct selinux_load_state *load_state); void selinux_policy_commit(struct selinux_state *state, struct selinux_load_state *load_state); void selinux_policy_cancel(struct selinux_state *state, struct selinux_load_state *load_state); int security_read_policy(struct selinux_state *state, void **data, size_t *len); int security_policycap_supported(struct selinux_state *state, unsigned int req_cap); #define SEL_VEC_MAX 32 struct av_decision { u32 allowed; u32 auditallow; u32 auditdeny; u32 seqno; u32 flags; }; #define XPERMS_ALLOWED 1 #define XPERMS_AUDITALLOW 2 #define XPERMS_DONTAUDIT 4 #define security_xperm_set(perms, x) (perms[x >> 5] |= 1 << (x & 0x1f)) #define security_xperm_test(perms, x) (1 & (perms[x >> 5] >> (x & 0x1f))) struct extended_perms_data { u32 p[8]; }; struct extended_perms_decision { u8 used; u8 driver; struct extended_perms_data *allowed; struct extended_perms_data *auditallow; struct extended_perms_data *dontaudit; }; struct extended_perms { u16 len; /* length associated decision chain */ struct extended_perms_data drivers; /* flag drivers that are used */ }; /* definitions of av_decision.flags */ #define AVD_FLAGS_PERMISSIVE 0x0001 void security_compute_av(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct extended_perms *xperms); void security_compute_xperms_decision(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u8 driver, struct extended_perms_decision *xpermd); void security_compute_av_user(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd); int security_transition_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, const struct qstr *qstr, u32 *out_sid); int security_transition_sid_user(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, const char *objname, u32 *out_sid); int security_member_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 *out_sid); int security_change_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 *out_sid); int security_sid_to_context(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len); int security_sid_to_context_force(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len); int security_sid_to_context_inval(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len); int security_context_to_sid(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *out_sid, gfp_t gfp); int security_context_str_to_sid(struct selinux_state *state, const char *scontext, u32 *out_sid, gfp_t gfp); int security_context_to_sid_default(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *out_sid, u32 def_sid, gfp_t gfp_flags); int security_context_to_sid_force(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *sid); int security_get_user_sids(struct selinux_state *state, u32 callsid, char *username, u32 **sids, u32 *nel); int security_port_sid(struct selinux_state *state, u8 protocol, u16 port, u32 *out_sid); int security_ib_pkey_sid(struct selinux_state *state, u64 subnet_prefix, u16 pkey_num, u32 *out_sid); int security_ib_endport_sid(struct selinux_state *state, const char *dev_name, u8 port_num, u32 *out_sid); int security_netif_sid(struct selinux_state *state, char *name, u32 *if_sid); int security_node_sid(struct selinux_state *state, u16 domain, void *addr, u32 addrlen, u32 *out_sid); int security_validate_transition(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 tclass); int security_validate_transition_user(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 tclass); int security_bounded_transition(struct selinux_state *state, u32 oldsid, u32 newsid); int security_sid_mls_copy(struct selinux_state *state, u32 sid, u32 mls_sid, u32 *new_sid); int security_net_peersid_resolve(struct selinux_state *state, u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid, u32 *peer_sid); int security_get_classes(struct selinux_policy *policy, char ***classes, int *nclasses); int security_get_permissions(struct selinux_policy *policy, char *class, char ***perms, int *nperms); int security_get_reject_unknown(struct selinux_state *state); int security_get_allow_unknown(struct selinux_state *state); #define SECURITY_FS_USE_XATTR 1 /* use xattr */ #define SECURITY_FS_USE_TRANS 2 /* use transition SIDs, e.g. devpts/tmpfs */ #define SECURITY_FS_USE_TASK 3 /* use task SIDs, e.g. pipefs/sockfs */ #define SECURITY_FS_USE_GENFS 4 /* use the genfs support */ #define SECURITY_FS_USE_NONE 5 /* no labeling support */ #define SECURITY_FS_USE_MNTPOINT 6 /* use mountpoint labeling */ #define SECURITY_FS_USE_NATIVE 7 /* use native label support */ #define SECURITY_FS_USE_MAX 7 /* Highest SECURITY_FS_USE_XXX */ int security_fs_use(struct selinux_state *state, struct super_block *sb); int security_genfs_sid(struct selinux_state *state, const char *fstype, char *name, u16 sclass, u32 *sid); int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype, char *name, u16 sclass, u32 *sid); #ifdef CONFIG_NETLABEL int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, u32 *sid); int security_netlbl_sid_to_secattr(struct selinux_state *state, u32 sid, struct netlbl_lsm_secattr *secattr); #else static inline int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, u32 *sid) { return -EIDRM; } static inline int security_netlbl_sid_to_secattr(struct selinux_state *state, u32 sid, struct netlbl_lsm_secattr *secattr) { return -ENOENT; } #endif /* CONFIG_NETLABEL */ const char *security_get_initial_sid_context(u32 sid); /* * status notifier using mmap interface */ extern struct page *selinux_kernel_status_page(struct selinux_state *state); #define SELINUX_KERNEL_STATUS_VERSION 1 struct selinux_kernel_status { u32 version; /* version number of thie structure */ u32 sequence; /* sequence number of seqlock logic */ u32 enforcing; /* current setting of enforcing mode */ u32 policyload; /* times of policy reloaded */ u32 deny_unknown; /* current setting of deny_unknown */ /* * The version > 0 supports above members. */ } __packed; extern void selinux_status_update_setenforce(struct selinux_state *state, int enforcing); extern void selinux_status_update_policyload(struct selinux_state *state, int seqno); extern void selinux_complete_init(void); extern int selinux_disable(struct selinux_state *state); extern void exit_sel_fs(void); extern struct path selinux_null; extern struct vfsmount *selinuxfs_mount; extern void selnl_notify_setenforce(int val); extern void selnl_notify_policyload(u32 seqno); extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm); extern void avtab_cache_init(void); extern void ebitmap_cache_init(void); extern void hashtab_cache_init(void); extern int security_sidtab_hash_stats(struct selinux_state *state, char *page); #endif /* _SELINUX_SECURITY_H_ */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> #include <xen/xen.h> #include <asm/fpu/internal.h> #include <asm/sev-es.h> #include <asm/traps.h> #include <asm/kdebug.h> typedef bool (*ex_handler_t)(const struct exception_table_entry *, struct pt_regs *, int, unsigned long, unsigned long); static inline unsigned long ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } static inline ex_handler_t ex_fixup_handler(const struct exception_table_entry *x) { return (ex_handler_t)((unsigned long)&x->handler + x->handler); } __visible bool ex_handler_default(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_default); __visible bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { regs->ip = ex_fixup_addr(fixup); regs->ax = trapnr; return true; } EXPORT_SYMBOL_GPL(ex_handler_fault); /* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (task->thread.fpu.state) * should always be valid. However, past bugs have allowed userspace to set * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). * These caused XRSTOR to fail when switching to the task, leaking the FPU * registers of the task previously executing on the CPU. Mitigate this class * of vulnerability by restoring from the initial state (essentially, zeroing * out all the FPU registers) if we can't restore from the task's FPU state. */ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); __copy_kernel_to_fpregs(&init_fpstate, -1); return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr); } EXPORT_SYMBOL_GPL(ex_handler_fprestore); __visible bool ex_handler_uaccess(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?"); regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_uaccess); __visible bool ex_handler_copy(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?"); regs->ip = ex_fixup_addr(fixup); regs->ax = trapnr; return true; } EXPORT_SYMBOL(ex_handler_copy); __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, regs->ip, (void *)regs->ip)) show_stack_regs(regs); /* Pretend that the read succeeded and returned 0. */ regs->ip = ex_fixup_addr(fixup); regs->ax = 0; regs->dx = 0; return true; } EXPORT_SYMBOL(ex_handler_rdmsr_unsafe); __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, regs->ip, (void *)regs->ip)) show_stack_regs(regs); /* Pretend that the write succeeded. */ regs->ip = ex_fixup_addr(fixup); return true; } EXPORT_SYMBOL(ex_handler_wrmsr_unsafe); __visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { if (static_cpu_has(X86_BUG_NULL_SEG)) asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); asm volatile ("mov %0, %%fs" : : "rm" (0)); return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr); } EXPORT_SYMBOL(ex_handler_clear_fs); enum handler_type ex_get_fault_handler_type(unsigned long ip) { const struct exception_table_entry *e; ex_handler_t handler; e = search_exception_tables(ip); if (!e) return EX_HANDLER_NONE; handler = ex_fixup_handler(e); if (handler == ex_handler_fault) return EX_HANDLER_FAULT; else if (handler == ex_handler_uaccess || handler == ex_handler_copy) return EX_HANDLER_UACCESS; else return EX_HANDLER_OTHER; } int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { const struct exception_table_entry *e; ex_handler_t handler; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp; extern u32 pnp_bios_is_utter_crap; pnp_bios_is_utter_crap = 1; printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n"); __asm__ volatile( "movl %0, %%esp\n\t" "jmp *%1\n\t" : : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip)); panic("do_trap: can't hit this"); } #endif e = search_exception_tables(regs->ip); if (!e) return 0; handler = ex_fixup_handler(e); return handler(e, regs, trapnr, error_code, fault_addr); } extern unsigned int early_recursion_flag; /* Restricted version used during very early boot */ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { /* Ignore early NMIs. */ if (trapnr == X86_TRAP_NMI) return; if (early_recursion_flag > 2) goto halt_loop; /* * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. * Xen pv domains are not using the default __KERNEL_CS. */ if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* * The full exception fixup machinery is available as soon as * the early IDT is loaded. This means that it is the * responsibility of extable users to either function correctly * when handlers are invoked early or to simply avoid causing * exceptions before they're ready to handle them. * * This is better than filtering which handlers can be used, * because refusing to call a handler here is guaranteed to * result in a hard-to-debug panic. * * Keep in mind that not all vectors actually get here. Early * page faults, for example, are special. */ if (fixup_exception(regs, trapnr, regs->orig_ax, 0)) return; if (trapnr == X86_TRAP_UD) { if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { /* Skip the ud2. */ regs->ip += LEN_UD2; return; } /* * If this was a BUG and report_bug returns or if this * was just a normal #UD, we want to continue onward and * crash. */ } fail: early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, regs->orig_ax, read_cr2()); show_regs(regs); halt_loop: while (true) halt(); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 | // SPDX-License-Identifier: GPL-2.0 /* * kernel userspace event delivery * * Copyright (C) 2004 Red Hat, Inc. All rights reserved. * Copyright (C) 2004 Novell, Inc. All rights reserved. * Copyright (C) 2004 IBM, Inc. All rights reserved. * * Authors: * Robert Love <rml@novell.com> * Kay Sievers <kay.sievers@vrfy.org> * Arjan van de Ven <arjanv@redhat.com> * Greg Kroah-Hartman <greg@kroah.com> */ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/kobject.h> #include <linux/export.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/uidgid.h> #include <linux/uuid.h> #include <linux/ctype.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> u64 uevent_seqnum; #ifdef CONFIG_UEVENT_HELPER char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH; #endif struct uevent_sock { struct list_head list; struct sock *sk; }; #ifdef CONFIG_NET static LIST_HEAD(uevent_sock_list); #endif /* This lock protects uevent_seqnum and uevent_sock_list */ static DEFINE_MUTEX(uevent_sock_mutex); /* the strings here must match the enum in include/linux/kobject.h */ static const char *kobject_actions[] = { [KOBJ_ADD] = "add", [KOBJ_REMOVE] = "remove", [KOBJ_CHANGE] = "change", [KOBJ_MOVE] = "move", [KOBJ_ONLINE] = "online", [KOBJ_OFFLINE] = "offline", [KOBJ_BIND] = "bind", [KOBJ_UNBIND] = "unbind", }; static int kobject_action_type(const char *buf, size_t count, enum kobject_action *type, const char **args) { enum kobject_action action; size_t count_first; const char *args_start; int ret = -EINVAL; if (count && (buf[count-1] == '\n' || buf[count-1] == '\0')) count--; if (!count) goto out; args_start = strnchr(buf, count, ' '); if (args_start) { count_first = args_start - buf; args_start = args_start + 1; } else count_first = count; for (action = 0; action < ARRAY_SIZE(kobject_actions); action++) { if (strncmp(kobject_actions[action], buf, count_first) != 0) continue; if (kobject_actions[action][count_first] != '\0') continue; if (args) *args = args_start; *type = action; ret = 0; break; } out: return ret; } static const char *action_arg_word_end(const char *buf, const char *buf_end, char delim) { const char *next = buf; while (next <= buf_end && *next != delim) if (!isalnum(*next++)) return NULL; if (next == buf) return NULL; return next; } static int kobject_action_args(const char *buf, size_t count, struct kobj_uevent_env **ret_env) { struct kobj_uevent_env *env = NULL; const char *next, *buf_end, *key; int key_len; int r = -EINVAL; if (count && (buf[count - 1] == '\n' || buf[count - 1] == '\0')) count--; if (!count) return -EINVAL; env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return -ENOMEM; /* first arg is UUID */ if (count < UUID_STRING_LEN || !uuid_is_valid(buf) || add_uevent_var(env, "SYNTH_UUID=%.*s", UUID_STRING_LEN, buf)) goto out; /* * the rest are custom environment variables in KEY=VALUE * format with ' ' delimiter between each KEY=VALUE pair */ next = buf + UUID_STRING_LEN; buf_end = buf + count - 1; while (next <= buf_end) { if (*next != ' ') goto out; /* skip the ' ', key must follow */ key = ++next; if (key > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, '='); if (!next || next > buf_end || *next != '=') goto out; key_len = next - buf; /* skip the '=', value must follow */ if (++next > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, ' '); if (!next) goto out; if (add_uevent_var(env, "SYNTH_ARG_%.*s=%.*s", key_len, key, (int) (next - buf), buf)) goto out; } r = 0; out: if (r) kfree(env); else *ret_env = env; return r; } /** * kobject_synth_uevent - send synthetic uevent with arguments * * @kobj: struct kobject for which synthetic uevent is to be generated * @buf: buffer containing action type and action args, newline is ignored * @count: length of buffer * * Returns 0 if kobject_synthetic_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) { char *no_uuid_envp[] = { "SYNTH_UUID=0", NULL }; enum kobject_action action; const char *action_args; struct kobj_uevent_env *env; const char *msg = NULL, *devpath; int r; r = kobject_action_type(buf, count, &action, &action_args); if (r) { msg = "unknown uevent action string"; goto out; } if (!action_args) { r = kobject_uevent_env(kobj, action, no_uuid_envp); goto out; } r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { msg = "incorrect uevent action arguments"; goto out; } if (r) goto out; r = kobject_uevent_env(kobj, action, env->envp); kfree(env); out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); } return r; } #ifdef CONFIG_UEVENT_HELPER static int kobj_usermode_filter(struct kobject *kobj) { const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); return ns != init_ns; } return 0; } static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem) { int buffer_size = sizeof(env->buf) - env->buflen; int len; len = strlcpy(&env->buf[env->buflen], subsystem, buffer_size); if (len >= buffer_size) { pr_warn("init_uevent_argv: buffer size of %d too small, needed %d\n", buffer_size, len); return -ENOMEM; } env->argv[0] = uevent_helper; env->argv[1] = &env->buf[env->buflen]; env->argv[2] = NULL; env->buflen += len + 1; return 0; } static void cleanup_uevent_env(struct subprocess_info *info) { kfree(info->data); } #endif #ifdef CONFIG_NET static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct netlink_skb_parms *parms; struct sk_buff *skb = NULL; char *scratch; size_t len; /* allocate message with maximum possible size */ len = strlen(action_string) + strlen(devpath) + 2; skb = alloc_skb(len + env->buflen, GFP_KERNEL); if (!skb) return NULL; /* add header */ scratch = skb_put(skb, len); sprintf(scratch, "%s@%s", action_string, devpath); skb_put_data(skb, env->buf, env->buflen); parms = &NETLINK_CB(skb); parms->creds.uid = GLOBAL_ROOT_UID; parms->creds.gid = GLOBAL_ROOT_GID; parms->dst_group = 1; parms->portid = 0; return skb; } static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct sk_buff *skb = NULL; struct uevent_sock *ue_sk; int retval = 0; /* send netlink message */ list_for_each_entry(ue_sk, &uevent_sock_list, list) { struct sock *uevent_sock = ue_sk->sk; if (!netlink_has_listeners(uevent_sock, 1)) continue; if (!skb) { retval = -ENOMEM; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) continue; } retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } consume_skb(skb); return retval; } static int uevent_net_broadcast_tagged(struct sock *usk, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct user_namespace *owning_user_ns = sock_net(usk)->user_ns; struct sk_buff *skb = NULL; int ret = 0; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) return -ENOMEM; /* fix credentials */ if (owning_user_ns != &init_user_ns) { struct netlink_skb_parms *parms = &NETLINK_CB(skb); kuid_t root_uid; kgid_t root_gid; /* fix uid */ root_uid = make_kuid(owning_user_ns, 0); if (uid_valid(root_uid)) parms->creds.uid = root_uid; /* fix gid */ root_gid = make_kgid(owning_user_ns, 0); if (gid_valid(root_gid)) parms->creds.gid = root_gid; } ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } #endif static int kobject_uevent_net_broadcast(struct kobject *kobj, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { int ret = 0; #ifdef CONFIG_NET const struct kobj_ns_type_operations *ops; const struct net *net = NULL; ops = kobj_ns_ops(kobj); if (!ops && kobj->kset) { struct kobject *ksobj = &kobj->kset->kobj; if (ksobj->parent != NULL) ops = kobj_ns_ops(ksobj->parent); } /* kobjects currently only carry network namespace tags and they * are the only tag relevant here since we want to decide which * network namespaces to broadcast the uevent into. */ if (ops && ops->netlink_ns && kobj->ktype->namespace) if (ops->type == KOBJ_NS_TYPE_NET) net = kobj->ktype->namespace(kobj); if (!net) ret = uevent_net_broadcast_untagged(env, action_string, devpath); else ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, action_string, devpath); #endif return ret; } static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; size_t len; int i, j; for (i = 0; i < env->envp_idx;) { if (strncmp(env->envp[i], modalias_prefix, sizeof(modalias_prefix) - 1)) { i++; continue; } len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { /* @env->envp[] contains pointers to @env->buf[] * with @env->buflen chars, and we are removing * variable MODALIAS here pointed by @env->envp[i] * with length @len as shown below: * * 0 @env->buf[] @env->buflen * --------------------------------------------- * ^ ^ ^ ^ * | |-> @len <-| target block | * @env->envp[0] @env->envp[i] @env->envp[i + 1] * * so the "target block" indicated above is moved * backward by @len, and its right size is * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). */ memmove(env->envp[i], env->envp[i + 1], env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; } env->envp_idx--; env->buflen -= len; } } /** * kobject_uevent_env - send an uevent with environmental data * * @kobj: struct kobject that the action is happening to * @action: action that is happening * @envp_ext: pointer to environmental data * * Returns 0 if kobject_uevent_env() is completed with success or the * corresponding error when it fails. */ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp_ext[]) { struct kobj_uevent_env *env; const char *action_string = kobject_actions[action]; const char *devpath = NULL; const char *subsystem; struct kobject *top_kobj; struct kset *kset; const struct kset_uevent_ops *uevent_ops; int i = 0; int retval = 0; /* * Mark "remove" event done regardless of result, for some subsystems * do not want to re-trigger "remove" event via automatic cleanup. */ if (action == KOBJ_REMOVE) kobj->state_remove_uevent_sent = 1; pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); /* search the kset we belong to */ top_kobj = kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) { pr_debug("kobject: '%s' (%p): %s: attempted to send uevent " "without kset!\n", kobject_name(kobj), kobj, __func__); return -EINVAL; } kset = top_kobj->kset; uevent_ops = kset->uevent_ops; /* skip the event, if uevent_suppress is set*/ if (kobj->uevent_suppress) { pr_debug("kobject: '%s' (%p): %s: uevent_suppress " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kset, kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* originating subsystem */ if (uevent_ops && uevent_ops->name) subsystem = uevent_ops->name(kset, kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the " "event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* environment buffer */ env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* complete object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { retval = -ENOENT; goto exit; } /* default keys */ retval = add_uevent_var(env, "ACTION=%s", action_string); if (retval) goto exit; retval = add_uevent_var(env, "DEVPATH=%s", devpath); if (retval) goto exit; retval = add_uevent_var(env, "SUBSYSTEM=%s", subsystem); if (retval) goto exit; /* keys passed in from the caller */ if (envp_ext) { for (i = 0; envp_ext[i]; i++) { retval = add_uevent_var(env, "%s", envp_ext[i]); if (retval) goto exit; } } /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { retval = uevent_ops->uevent(kset, kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, __func__, retval); goto exit; } } switch (action) { case KOBJ_ADD: /* * Mark "add" event so we can make sure we deliver "remove" * event to userspace during automatic cleanup. If * the object did send an "add" event, "remove" will * automatically generated by the core, if not already done * by the caller. */ kobj->state_add_uevent_sent = 1; break; case KOBJ_UNBIND: zap_modalias_env(env); break; default: break; } mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ retval = add_uevent_var(env, "SEQNUM=%llu", ++uevent_seqnum); if (retval) { mutex_unlock(&uevent_sock_mutex); goto exit; } retval = kobject_uevent_net_broadcast(kobj, env, action_string, devpath); mutex_unlock(&uevent_sock_mutex); #ifdef CONFIG_UEVENT_HELPER /* call uevent_helper, usually only enabled during early boot */ if (uevent_helper[0] && !kobj_usermode_filter(kobj)) { struct subprocess_info *info; retval = add_uevent_var(env, "HOME=/"); if (retval) goto exit; retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin"); if (retval) goto exit; retval = init_uevent_argv(env, subsystem); if (retval) goto exit; retval = -ENOMEM; info = call_usermodehelper_setup(env->argv[0], env->argv, env->envp, GFP_KERNEL, NULL, cleanup_uevent_env, env); if (info) { retval = call_usermodehelper_exec(info, UMH_NO_WAIT); env = NULL; /* freed by cleanup_uevent_env */ } } #endif exit: kfree(devpath); kfree(env); return retval; } EXPORT_SYMBOL_GPL(kobject_uevent_env); /** * kobject_uevent - notify userspace by sending an uevent * * @kobj: struct kobject that the action is happening to * @action: action that is happening * * Returns 0 if kobject_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_uevent(struct kobject *kobj, enum kobject_action action) { return kobject_uevent_env(kobj, action, NULL); } EXPORT_SYMBOL_GPL(kobject_uevent); /** * add_uevent_var - add key value string to the environment buffer * @env: environment buffer structure * @format: printf format for the key=value pair * * Returns 0 if environment variable was added successfully or -ENOMEM * if no space was available. */ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { va_list args; int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } va_start(args, format); len = vsnprintf(&env->buf[env->buflen], sizeof(env->buf) - env->buflen, format, args); va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } env->envp[env->envp_idx++] = &env->buf[env->buflen]; env->buflen += len + 1; return 0; } EXPORT_SYMBOL_GPL(add_uevent_var); #if defined(CONFIG_NET) static int uevent_net_broadcast(struct sock *usk, struct sk_buff *skb, struct netlink_ext_ack *extack) { /* u64 to chars: 2^64 - 1 = 21 chars */ char buf[sizeof("SEQNUM=") + 21]; struct sk_buff *skbc; int ret; /* bump and prepare sequence number */ ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", ++uevent_seqnum); if (ret < 0 || (size_t)ret >= sizeof(buf)) return -ENOMEM; ret++; /* verify message does not overflow */ if ((skb->len + ret) > UEVENT_BUFFER_SIZE) { NL_SET_ERR_MSG(extack, "uevent message too big"); return -EINVAL; } /* copy skb and extend to accommodate sequence number */ skbc = skb_copy_expand(skb, 0, ret, GFP_KERNEL); if (!skbc) return -ENOMEM; /* append sequence number */ skb_put_data(skbc, buf, ret); /* remove msg header */ skb_pull(skbc, NLMSG_HDRLEN); /* set portid 0 to inform userspace message comes from kernel */ NETLINK_CB(skbc).portid = 0; NETLINK_CB(skbc).dst_group = 1; ret = netlink_broadcast(usk, skbc, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } static int uevent_net_rcv_skb(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net; int ret; if (!nlmsg_data(nlh)) return -EINVAL; /* * Verify that we are allowed to send messages to the target * network namespace. The caller must have CAP_SYS_ADMIN in the * owning user namespace of the target network namespace. */ net = sock_net(NETLINK_CB(skb).sk); if (!netlink_ns_capable(skb, net->user_ns, CAP_SYS_ADMIN)) { NL_SET_ERR_MSG(extack, "missing CAP_SYS_ADMIN capability"); return -EPERM; } mutex_lock(&uevent_sock_mutex); ret = uevent_net_broadcast(net->uevent_sock->sk, skb, extack); mutex_unlock(&uevent_sock_mutex); return ret; } static void uevent_net_rcv(struct sk_buff *skb) { netlink_rcv_skb(skb, &uevent_net_rcv_skb); } static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; struct netlink_kernel_cfg cfg = { .groups = 1, .input = uevent_net_rcv, .flags = NL_CFG_F_NONROOT_RECV }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } net->uevent_sock = ue_sk; /* Restrict uevents to initial user namespace. */ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_add_tail(&ue_sk->list, &uevent_sock_list); mutex_unlock(&uevent_sock_mutex); } return 0; } static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk = net->uevent_sock; if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_del(&ue_sk->list); mutex_unlock(&uevent_sock_mutex); } netlink_kernel_release(ue_sk->sk); kfree(ue_sk); } static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, }; static int __init kobject_uevent_init(void) { return register_pernet_subsys(&uevent_net_ops); } postcore_initcall(kobject_uevent_init); #endif |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } /** * instrument_atomic_read - instrument atomic read access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); } /** * instrument_atomic_write - instrument atomic write access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); } /** * instrument_copy_from_user - instrument writes of copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } #endif /* _LINUX_INSTRUMENTED_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long expires, unsigned int flags), TP_ARGS(timer, expires, flags), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = expires; __entry->now = jiffies; __entry->flags = flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_init - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_init, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = hrtimer->function; __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = hrtimer->function; ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <linux/kernel.h> /* * Simple doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); list->prev = list; } #ifdef CONFIG_DEBUG_LIST extern bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next); extern bool __list_del_entry_valid(struct list_head *entry); #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); entry->prev = entry; smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return (next == head) && (next == head->prev); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && (head->next != entry && head != entry)) return; if (entry == head) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; pos != (head); pos = pos->next) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; pos != (head); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; pos != (head); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ pos != (head); \ pos = n, n = pos->prev) /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ (&pos->member == (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behing - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sched #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCHED_H #include <linux/kthread.h> #include <linux/sched/numa_balancing.h> #include <linux/tracepoint.h> #include <linux/binfmts.h> /* * Tracepoint for calling kthread_stop, performed to end a kthread: */ TRACE_EVENT(sched_kthread_stop, TP_PROTO(struct task_struct *t), TP_ARGS(t), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) ), TP_fast_assign( memcpy(__entry->comm, t->comm, TASK_COMM_LEN); __entry->pid = t->pid; ), TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid) ); /* * Tracepoint for the return value of the kthread stopping: */ TRACE_EVENT(sched_kthread_stop_ret, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field( int, ret ) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); /** * sched_kthread_work_queue_work - called when a work gets queued * @worker: pointer to the kthread_worker * @work: pointer to struct kthread_work * * This event occurs when a work is queued immediately or once a * delayed work is actually queued (ie: once the delay has been * reached). */ TRACE_EVENT(sched_kthread_work_queue_work, TP_PROTO(struct kthread_worker *worker, struct kthread_work *work), TP_ARGS(worker, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __field( void *, worker) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __entry->worker = worker; ), TP_printk("work struct=%p function=%ps worker=%p", __entry->work, __entry->function, __entry->worker) ); /** * sched_kthread_work_execute_start - called immediately before the work callback * @work: pointer to struct kthread_work * * Allows to track kthread work execution. */ TRACE_EVENT(sched_kthread_work_execute_start, TP_PROTO(struct kthread_work *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * sched_kthread_work_execute_end - called immediately after the work callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(sched_kthread_work_execute_end, TP_PROTO(struct kthread_work *work, kthread_work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /* * Tracepoint for waking up a task: */ DECLARE_EVENT_CLASS(sched_wakeup_template, TP_PROTO(struct task_struct *p), TP_ARGS(__perf_task(p)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, success ) __field( int, target_cpu ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->success = 1; /* rudiment, kill when possible */ __entry->target_cpu = task_cpu(p); ), TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d", __entry->comm, __entry->pid, __entry->prio, __entry->target_cpu) ); /* * Tracepoint called when waking a task; this tracepoint is guaranteed to be * called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_waking, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG. * It is not always called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for waking up a new task: */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_PROTO(struct task_struct *p), TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p) { unsigned int state; #ifdef CONFIG_SCHED_DEBUG BUG_ON(p != current); #endif /* CONFIG_SCHED_DEBUG */ /* * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ if (preempt) return TASK_REPORT_MAX; /* * task_state_index() uses fls() and returns a value from 0-8 range. * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using * it for left shift operation to get the correct task->state * mapping. */ state = task_state_index(p); return state ? (1 << (state - 1)) : state; } #endif /* CREATE_TRACE_POINTS */ /* * Tracepoint for task switches, performed by the scheduler: */ TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, struct task_struct *prev, struct task_struct *next), TP_ARGS(preempt, prev, next), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) __field( pid_t, prev_pid ) __field( int, prev_prio ) __field( long, prev_state ) __array( char, next_comm, TASK_COMM_LEN ) __field( pid_t, next_pid ) __field( int, next_prio ) ), TP_fast_assign( memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; __entry->prev_state = __trace_sched_switch_state(preempt, prev); memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", { TASK_INTERRUPTIBLE, "S" }, { TASK_UNINTERRUPTIBLE, "D" }, { __TASK_STOPPED, "T" }, { __TASK_TRACED, "t" }, { EXIT_DEAD, "X" }, { EXIT_ZOMBIE, "Z" }, { TASK_PARKED, "P" }, { TASK_DEAD, "I" }) : "R", __entry->prev_state & TASK_REPORT_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); /* * Tracepoint for a task being migrated: */ TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu), TP_ARGS(p, dest_cpu), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu) ); DECLARE_EVENT_CLASS(sched_process_template, TP_PROTO(struct task_struct *p), TP_ARGS(p), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); /* * Tracepoint for freeing a task: */ DEFINE_EVENT(sched_process_template, sched_process_free, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a task exiting: */ DEFINE_EVENT(sched_process_template, sched_process_exit, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for waiting on task to unschedule: */ DEFINE_EVENT(sched_process_template, sched_wait_task, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a waiting task: */ TRACE_EVENT(sched_process_wait, TP_PROTO(struct pid *pid), TP_ARGS(pid), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( memcpy(__entry->comm, current->comm, TASK_COMM_LEN); __entry->pid = pid_nr(pid); __entry->prio = current->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); /* * Tracepoint for do_fork: */ TRACE_EVENT(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child), TP_ARGS(parent, child), TP_STRUCT__entry( __array( char, parent_comm, TASK_COMM_LEN ) __field( pid_t, parent_pid ) __array( char, child_comm, TASK_COMM_LEN ) __field( pid_t, child_pid ) ), TP_fast_assign( memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN); __entry->parent_pid = parent->pid; memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN); __entry->child_pid = child->pid; ), TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d", __entry->parent_comm, __entry->parent_pid, __entry->child_comm, __entry->child_pid) ); /* * Tracepoint for exec: */ TRACE_EVENT(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm), TP_ARGS(p, old_pid, bprm), TP_STRUCT__entry( __string( filename, bprm->filename ) __field( pid_t, pid ) __field( pid_t, old_pid ) ), TP_fast_assign( __assign_str(filename, bprm->filename); __entry->pid = p->pid; __entry->old_pid = old_pid; ), TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename), __entry->pid, __entry->old_pid) ); #ifdef CONFIG_SCHEDSTATS #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS #else #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT_NOP #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS_NOP #endif /* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ DECLARE_EVENT_CLASS_SCHEDSTAT(sched_stat_template, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(__perf_task(tsk), __perf_count(delay)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( u64, delay ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->delay = delay; ), TP_printk("comm=%s pid=%d delay=%Lu [ns]", __entry->comm, __entry->pid, (unsigned long long)__entry->delay) ); /* * Tracepoint for accounting wait time (time the task is runnable * but not actually running due to scheduler contention). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_wait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting sleep time (time the task is not runnable, * including iowait, see below). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_sleep, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting iowait time (time the task is not runnable * due to waiting on IO to complete). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_iowait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting blocked time (time the task is in uninterruptible). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting runtime (time the task is executing * on a CPU). */ DECLARE_EVENT_CLASS(sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime), TP_ARGS(tsk, __perf_count(runtime), vruntime), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( u64, runtime ) __field( u64, vruntime ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->runtime = runtime; __entry->vruntime = vruntime; ), TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]", __entry->comm, __entry->pid, (unsigned long long)__entry->runtime, (unsigned long long)__entry->vruntime) ); DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime), TP_ARGS(tsk, runtime, vruntime)); /* * Tracepoint for showing priority inheritance modifying a tasks * priority. */ TRACE_EVENT(sched_pi_setprio, TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task), TP_ARGS(tsk, pi_task), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, oldprio ) __field( int, newprio ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->oldprio = tsk->prio; __entry->newprio = pi_task ? min(tsk->normal_prio, pi_task->prio) : tsk->normal_prio; /* XXX SCHED_DEADLINE bits missing */ ), TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", __entry->comm, __entry->pid, __entry->oldprio, __entry->newprio) ); #ifdef CONFIG_DETECT_HUNG_TASK TRACE_EVENT(sched_process_hang, TP_PROTO(struct task_struct *tsk), TP_ARGS(tsk), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; ), TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid) ); #endif /* CONFIG_DETECT_HUNG_TASK */ /* * Tracks migration of tasks from one runqueue to another. Can be used to * detect if automatic NUMA balancing is bouncing between nodes. */ TRACE_EVENT(sched_move_numa, TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), TP_ARGS(tsk, src_cpu, dst_cpu), TP_STRUCT__entry( __field( pid_t, pid ) __field( pid_t, tgid ) __field( pid_t, ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->pid = task_pid_nr(tsk); __entry->tgid = task_tgid_nr(tsk); __entry->ngid = task_numa_group_id(tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_cpu = dst_cpu; __entry->dst_nid = cpu_to_node(dst_cpu); ), TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d", __entry->pid, __entry->tgid, __entry->ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_cpu, __entry->dst_nid) ); DECLARE_EVENT_CLASS(sched_numa_pair_template, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu), TP_STRUCT__entry( __field( pid_t, src_pid ) __field( pid_t, src_tgid ) __field( pid_t, src_ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( pid_t, dst_pid ) __field( pid_t, dst_tgid ) __field( pid_t, dst_ngid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->src_pid = task_pid_nr(src_tsk); __entry->src_tgid = task_tgid_nr(src_tsk); __entry->src_ngid = task_numa_group_id(src_tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_pid = dst_tsk ? task_pid_nr(dst_tsk) : 0; __entry->dst_tgid = dst_tsk ? task_tgid_nr(dst_tsk) : 0; __entry->dst_ngid = dst_tsk ? task_numa_group_id(dst_tsk) : 0; __entry->dst_cpu = dst_cpu; __entry->dst_nid = dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1; ), TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d", __entry->src_pid, __entry->src_tgid, __entry->src_ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid, __entry->dst_cpu, __entry->dst_nid) ); DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); /* * Tracepoint for waking a polling cpu without an IPI. */ TRACE_EVENT(sched_wake_idle_without_ipi, TP_PROTO(int cpu), TP_ARGS(cpu), TP_STRUCT__entry( __field( int, cpu ) ), TP_fast_assign( __entry->cpu = cpu; ), TP_printk("cpu=%d", __entry->cpu) ); /* * Following tracepoints are not exported in tracefs and provide hooking * mechanisms only for testing and debugging purposes. * * Postfixed with _tp to make them easily identifiable in the code. */ DECLARE_TRACE(pelt_cfs_tp, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(pelt_rt_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_dl_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_thermal_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_irq_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_cpu_capacity_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(sched_overutilized_tp, TP_PROTO(struct root_domain *rd, bool overutilized), TP_ARGS(rd, overutilized)); DECLARE_TRACE(sched_util_est_cfs_tp, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(sched_util_est_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_update_nr_running_tp, TP_PROTO(struct rq *rq, int change), TP_ARGS(rq, change)); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_mutex * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->lock_page (access_process_vm) * * ->i_mutex (generic_perform_write) * ->mmap_lock (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_adjust) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->pgdat->lru_lock (follow_page->mark_page_accessed) * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * * ->i_mmap_rwsem * ->tasklist_lock (memory_failure, collect_procs_ao) */ static void page_cache_delete(struct address_space *mapping, struct page *page, void *shadow) { XA_STATE(xas, &mapping->i_pages, page->index); unsigned int nr = 1; mapping_set_update(&xas, mapping); /* hugetlb pages are represented by a single entry in the xarray */ if (!PageHuge(page)) { xas_set_order(&xas, page->index, compound_order(page)); nr = compound_nr(page); } VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(nr != 1 && shadow, page); xas_store(&xas, shadow); xas_init_marks(&xas); page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ if (shadow) { mapping->nrexceptional += nr; /* * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing * with reclaim does not see both counters 0 at the * same time and miss a shadow entry. */ smp_wmb(); } mapping->nrpages -= nr; } static void unaccount_page_cache_page(struct address_space *mapping, struct page *page) { int nr; /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave * stale data around in the cleancache once our page is gone */ if (PageUptodate(page) && PageMappedToDisk(page)) cleancache_put_page(page); else cleancache_invalidate_page(mapping, page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_mapped(page), page); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { int mapcount; pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); dump_page(page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); mapcount = page_mapcount(page); if (mapping_exiting(mapping) && page_count(page) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped, * and we'd prefer not to leak it: if we're wrong, * some other bad page check should catch it later. */ page_mapcount_reset(page); page_ref_sub(page, mapcount); } } /* hugetlb pages do not participate in page cache accounting. */ if (PageHuge(page)) return; nr = thp_nr_pages(page); __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { __dec_node_page_state(page, NR_FILE_THPS); filemap_nr_thps_dec(mapping); } /* * At this point page must be either written or cleaned by * truncate. Dirty page here signals a bug and loss of * unwritten data. * * This fixes dirty accounting after removing the page entirely * but leaves PageDirty set: it has no effect for truncated * page and anyway will be cleared before returning page into * buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; trace_mm_filemap_delete_from_page_cache(page); unaccount_page_cache_page(mapping, page); page_cache_delete(mapping, page, shadow); } static void page_cache_free_page(struct address_space *mapping, struct page *page) { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; if (freepage) freepage(page); if (PageTransHuge(page) && !PageHuge(page)) { page_ref_sub(page, thp_nr_pages(page)); VM_BUG_ON_PAGE(page_count(page) <= 0, page); } else { put_page(page); } } /** * delete_from_page_cache - delete page from page cache * @page: the page which the kernel is trying to remove from page cache * * This must be called only on pages that have been verified to be in the page * cache and locked. It will never put the page into the free list, the caller * has a reference on the page. */ void delete_from_page_cache(struct page *page) { struct address_space *mapping = page_mapping(page); unsigned long flags; BUG_ON(!PageLocked(page)); xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); page_cache_free_page(mapping, page); } EXPORT_SYMBOL(delete_from_page_cache); /* * page_cache_delete_batch - delete several pages from page cache * @mapping: the mapping to which pages belong * @pvec: pagevec with pages to delete * * The function walks over mapping->i_pages and removes pages passed in @pvec * from the mapping. The function expects @pvec to be sorted by page index * and is optimised for it to be dense. * It tolerates holes in @pvec (mapping entries at those indices are not * modified). The function expects only THP head pages to be present in the * @pvec. * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct pagevec *pvec) { XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); int total_pages = 0; int i = 0; struct page *page; mapping_set_update(&xas, mapping); xas_for_each(&xas, page, ULONG_MAX) { if (i >= pagevec_count(pvec)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(page)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (page != pvec->pages[i]) { VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, page); continue; } WARN_ON_ONCE(!PageLocked(page)); if (page->index == xas.xa_index) page->mapping = NULL; /* Leave page->index set: truncation lookup relies on it */ /* * Move to the next page in the vector if this is a regular * page or the index is of the last sub-page of this compound * page. */ if (page->index + compound_nr(page) - 1 == xas.xa_index) i++; xas_store(&xas, NULL); total_pages++; } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec) { int i; unsigned long flags; if (!pagevec_count(pvec)) return; xa_lock_irqsave(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); unaccount_page_cache_page(mapping, pvec->pages[i]); } page_cache_delete_batch(mapping, pvec); xa_unlock_irqrestore(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) page_cache_free_page(mapping, pvec->pages[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); return ret; } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct page *page; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { page = xas_find(&xas, max); if (xas_retry(&xas, page)) continue; /* Shadow entries don't count */ if (xa_is_value(page)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return page != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct pagevec pvec; int nr_pages; if (end_byte < start_byte) return; pagevec_init(&pvec); while (index <= end) { unsigned i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, PAGECACHE_TAG_WRITEBACK); if (!nr_pages) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; wait_on_page_writeback(page); ClearPageError(page); } pagevec_release(&pvec); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { if (dax_mapping(mapping)) return mapping->nrexceptional; return mapping->nrpages; } /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) { int err2 = filemap_fdatawait_range(mapping, lstart, lend); if (!err) err = err2; } else { /* Clear any previously stored errors */ filemap_check_errors(mapping); } } else { err = filemap_check_errors(mapping); } return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_page - replace a pagecache page with a new one * @old: page to be replaced * @new: page to replace with * @gfp_mask: allocation mode * * This function replaces a page in the pagecache with a new one. On * success it acquires the pagecache reference for the new page and * drops it for the old page. Both the old and new pages must be * locked. This function does not add the new page to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. * * Return: %0 */ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); get_page(new); new->mapping = mapping; new->index = offset; mem_cgroup_migrate(old, new); xas_lock_irqsave(&xas, flags); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irqrestore(&xas, flags); if (freepage) freepage(old); put_page(old); return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); int error; bool charged = false; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); mapping_set_update(&xas, mapping); get_page(page); page->mapping = mapping; page->index = offset; if (!huge) { error = mem_cgroup_charge(page, current->mm, gfp); if (error) goto error; charged = true; } gfp &= GFP_RECLAIM_MASK; do { unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; if (order > thp_order(page)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } } if (old) { if (shadowp) *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); if (order > thp_order(page)) { xas_split(&xas, old, order); xas_reset(&xas); } } xas_store(&xas, page); if (xas_error(&xas)) goto unlock; if (old) mapping->nrexceptional--; mapping->nrpages++; /* hugetlb pages do not participate in page cache accounting */ if (!huge) __inc_lruvec_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); if (charged) mem_cgroup_uncharge(page); goto error; } trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ put_page(page); return error; } ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add * @mapping: the page's address_space * @offset: page index * @gfp_mask: page allocation mode * * This function is used to add a page to the pagecache. It must be locked. * This function does not add the page to the LRU. The caller must do that. * * Return: %0 on success, negative error code otherwise. */ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { return __add_to_page_cache_locked(page, mapping, offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { void *shadow = NULL; int ret; __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, gfp_mask, &shadow); if (unlikely(ret)) __ClearPageLocked(page); else { /* * The page might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed page. * The exception is pages getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(PageActive(page)); if (!(gfp_mask & __GFP_WRITE) && shadow) workingset_refault(page, shadow); lru_cache_add(page); } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA struct page *__page_cache_alloc(gfp_t gfp) { int n; struct page *page; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = __alloc_pages_node(n, gfp, 0); } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } return alloc_pages(gfp, 0); } EXPORT_SYMBOL(__page_cache_alloc); #endif /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *page_waitqueue(struct page *page) { return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&page_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->page->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->page->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in wait_on_page_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void wake_up_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; key.page = page; key.bit_nr = bit_nr; key.page_match = 0; bookmark.flags = 0; bookmark.private = NULL; bookmark.func = NULL; INIT_LIST_HEAD(&bookmark.entry); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); while (bookmark.flags & WQ_FLAG_BOOKMARK) { /* * Take a breather from holding the lock, * allow pages that finish wake up asynchronously * to acquire the lock and remove themselves * from wait queue */ spin_unlock_irqrestore(&q->lock, flags); cpu_relax(); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); } /* * It is possible for other pages to have collided on the waitqueue * hash, so in that case check for a page match. That prevents a long- * term waiter * * It is still possible to miss a case here, when we woke page waiters * and removed them from the waitqueue, but there are still other * page waiters. */ if (!waitqueue_active(q) || !key.page_match) { ClearPageWaiters(page); /* * It's possible to miss clearing Waiters here, when we woke * our page waiters, but the hashed waitqueue has waiters for * other pages on it. * * That's okay, it's a rare case. The next waker will clear it. */ } spin_unlock_irqrestore(&q->lock, flags); } static void wake_up_page(struct page *page, int bit) { if (!PageWaiters(page)) return; wake_up_page_bit(page, bit); } /* * A choice of three behaviors for wait_on_page_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __lock_page() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like put_and_wait_on_page_locked() on PG_locked. */ }; /* * Attempt to check (or get) the page bit, and mark us done * if successful. */ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &page->flags)) return false; } else if (test_bit(bit_nr, &page->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, enum behavior behavior) { int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; bool delayacct = false; unsigned long pflags; if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { if (!PageSwapBacked(page)) { delayacct_thrashing_start(); delayacct = true; } psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the SetPageWaiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); SetPageWaiters(page); if (!trylock_page_bit_common(page, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the page. */ if (behavior == DROP) put_page(page); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, &page->flags))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the PageWaiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { if (delayacct) delayacct_thrashing_end(); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } void wait_on_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit); int wait_on_page_bit_killable(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit_killable); static int __wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait, bool set) { struct wait_queue_head *q = page_waitqueue(page); int ret = 0; wait->page = page; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); SetPageWaiters(page); if (set) ret = !trylock_page(page); else ret = PageLocked(page); /* * If we were succesful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } static int wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait) { if (!PageLocked(page)) return 0; return __wait_on_page_locked_async(compound_head(page), wait, false); } /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. * * The caller should hold a reference on @page. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the page to * come unlocked. After this function returns, the caller should not * dereference @page. */ void put_and_wait_on_page_locked(struct page *page) { wait_queue_head_t *q; page = compound_head(page); q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); } /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue * @page: Page defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) { wait_queue_head_t *q = page_waitqueue(page); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); SetPageWaiters(page); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(add_page_wait_queue); #ifndef clear_bit_unlock_is_negative_byte /* * PG_waiters is the high bit in the same byte as PG_lock. * * On x86 (and on many other architectures), we can clear PG_lock and * test the sign bit at the same time. But if the architecture does * not support that special operation, we just do this all by hand * instead. * * The read of PG_waiters has to be after (or concurrently with) PG_locked * being cleared, but a memory barrier should be unnecessary since it is * in the same byte as PG_locked. */ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) { clear_bit_unlock(nr, mem); /* smp_mb__after_atomic(); */ return test_bit(PG_waiters, mem); } #endif /** * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in wait_on_page_locked(). * Also wakes sleepers in wait_on_page_writeback() because the wakeup * mechanism between PageLocked pages and PageWriteback pages is shared. * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. * * Note that this depends on PG_waiters being the sign bit in the byte * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to * clear the PG_locked bit and test PG_waiters at the same time fairly * portably (architectures that do LL/SC can test any bit, while x86 can * test the sign bit). */ void unlock_page(struct page *page) { BUILD_BUG_ON(PG_waiters != 7); page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) wake_up_page_bit(page, PG_locked); } EXPORT_SYMBOL(unlock_page); /** * end_page_writeback - end writeback against a page * @page: the page */ void end_page_writeback(struct page *page) { /* * TestClearPageReclaim could be used here but it is an atomic * operation and overkill in this particular case. Failing to * shuffle a page marked for immediate reclaim is too mild to * justify taking an atomic operation penalty at the end of * ever page writeback. */ if (PageReclaim(page)) { ClearPageReclaim(page); rotate_reclaimable_page(page); } /* * Writeback does not hold a page reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the page is not freed and * reused before the wake_up_page(). */ get_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); put_page(page); } EXPORT_SYMBOL(end_page_writeback); /* * After completing I/O on a page, call this routine to update the page * flags appropriately */ void page_endio(struct page *page, bool is_write, int err) { if (!is_write) { if (!err) { SetPageUptodate(page); } else { ClearPageUptodate(page); SetPageError(page); } unlock_page(page); } else { if (err) { struct address_space *mapping; SetPageError(page); mapping = page_mapping(page); if (mapping) mapping_set_error(mapping, err); } end_page_writeback(page); } } EXPORT_SYMBOL_GPL(page_endio); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @__page: the page to lock */ void __lock_page(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__lock_page); int __lock_page_killable(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__lock_page_killable); int __lock_page_async(struct page *page, struct wait_page_queue *wait) { return __wait_on_page_locked_async(page, wait, true); } /* * Return values: * 1 - page is locked; mmap_lock is still held. * 0 - page is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 * with the page locked and the mmap_lock unperturbed. */ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return 0; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) wait_on_page_locked_killable(page); else wait_on_page_locked(page); return 0; } else { if (flags & FAULT_FLAG_KILLABLE) { int ret; ret = __lock_page_killable(page); if (ret) { mmap_read_unlock(mm); return 0; } } else __lock_page(page); return 1; } } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == 0) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /** * find_get_entry - find and get a page cache entry * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, the head page is returned with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; rcu_read_lock(); repeat: xas_reset(&xas); page = xas_load(&xas); if (xas_retry(&xas, page)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!page || xa_is_value(page)) goto out; if (!page_cache_get_speculative(page)) goto repeat; /* * Has the page moved or been split? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != xas_reload(&xas))) { put_page(page); goto repeat; } out: rcu_read_unlock(); return page; } /** * find_lock_entry - Locate and lock a page cache entry. * @mapping: The address_space to search. * @index: The page cache index. * * Looks up the page at @mapping & @index. If there is a page in the * cache, the head page is returned locked and with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Context: May sleep. * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) { struct page *page; repeat: page = find_get_entry(mapping, index); if (page && !xa_is_value(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } return page; } /** * pagecache_get_page - Find and get a reference to a page. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the page is returned. * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * * * %FGP_ACCESSED - The page will be marked accessed. * * %FGP_LOCK - The page is returned locked. * * %FGP_HEAD - If the page is present and a THP, return the head page * rather than the exact page specified by the index. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. * * %FGP_WRITE - The page will be written * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask * * %FGP_NOWAIT - Don't get blocked by page lock * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * * Return: The found page or %NULL otherwise. */ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp_mask) { struct page *page; repeat: page = find_get_entry(mapping, index); if (xa_is_value(page)) page = NULL; if (!page) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!trylock_page(page)) { put_page(page); return NULL; } } else { lock_page(page); } /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } if (fgp_flags & FGP_ACCESSED) mark_page_accessed(page); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (page_is_idle(page)) clear_page_idle(page); } if (!(fgp_flags & FGP_HEAD)) page = find_subpage(page, index); no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp_mask |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp_mask &= ~__GFP_FS; page = __page_cache_alloc(gfp_mask); if (!page) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); err = add_to_page_cache_lru(page, mapping, index, gfp_mask); if (unlikely(err)) { put_page(page); page = NULL; if (err == -EEXIST) goto repeat; } /* * add_to_page_cache_lru locks the page, and for mmap we expect * an unlocked page. */ if (page && (fgp_flags & FGP_FOR_MMAP)) unlock_page(page); } return page; } EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @nr_entries: The maximum number of entries * @entries: Where the resulting entries are placed * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a group of up to * @nr_entries entries in the mapping. The entries are placed at * @entries. find_get_entries() takes a reference against any actual * pages it returns. * * The search returns a group of mapping-contiguous page cache entries * with ascending indexes. There may be holes in the indices due to * not-present pages. * * Any shadow entries of evicted pages, or swap entries from * shmem/tmpfs, are included in the returned array. * * If it finds a Transparent Huge Page, head or tail, find_get_entries() * stops at that page: the caller is likely to have a better way to handle * the compound page as a whole, and then skip its extent, than repeatedly * calling find_get_entries() to return all its tails. * * Return: the number of pages and shadow entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (xa_is_value(page)) goto export; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; /* * Terminate early on finding a THP, to allow the caller to * handle it all at once; but continue if this is hugetlbfs. */ if (PageTransHuge(page) && !PageHuge(page)) { page = find_subpage(page, xas.xa_index); nr_entries = ret + 1; } export: indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } /** * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_range() will search for and return a group of up to @nr_pages * pages in the mapping starting at index @start and up to index @end * (inclusive). The pages are placed at @pages. find_get_pages_range() takes * a reference against the returned pages. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. * We also update @start to index the next page for the traversal. * * Return: the number of pages which were found. If this number is * smaller than @nr_pages, the end of specified range has been * reached. */ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *start); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each(&xas, page, end) { if (xas_retry(&xas, page)) continue; /* Skip over shadow, swap and DAX entries */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broken anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return ret; } /** * find_get_pages_contig - gang contiguous pagecache lookup * @mapping: The address_space to search * @index: The starting page index * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_contig() works exactly like find_get_pages(), except * that the returned number of pages are guaranteed to be contiguous. * * Return: the number of pages which were found. */ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(page)) break; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_contig); /** * find_get_pages_range_tag - find and return pages in given range matching @tag * @mapping: the address_space to search * @index: the starting page index * @end: The final page index (inclusive) * @tag: the tag index * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * * Like find_get_pages, except we only return pages which are tagged with * @tag. We update @index to index the next page for the traversal. * * Return: the number of pages which were found. */ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *index); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each_marked(&xas, page, end, tag) { if (xas_retry(&xas, page)) continue; /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *index = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when we got to @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the * iteration when there is a page at index -1 but that is already * broken anyway. */ if (end == (pgoff_t)-1) *index = (pgoff_t)-1; else *index = end + 1; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_range_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /** * generic_file_buffered_read - generic file read routine * @iocb: the iocb to read * @iter: data destination * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. * * Return: * * total number of bytes copied, including those the were already @written * * negative error code if nothing was copied */ ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t written) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; loff_t *ppos = &iocb->ki_pos; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error = 0; if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; prev_offset = ra->prev_pos & (PAGE_SIZE-1); last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if (written && (iocb->ki_flags & IOCB_WAITQ)) iocb->ki_flags |= IOCB_NOWAIT; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: if (fatal_signal_pending(current)) { error = -EINTR; goto out; } page = find_get_page(mapping, index); if (!page) { if (iocb->ki_flags & IOCB_NOIO) goto would_block; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { if (iocb->ki_flags & IOCB_NOIO) { put_page(page); goto out; } page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } if (!PageUptodate(page)) { /* * See comment in do_read_cache_page on why * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = wait_on_page_locked_async(page, iocb->ki_waitq); } else { if (iocb->ki_flags & IOCB_NOWAIT) { put_page(page); goto would_block; } error = wait_on_page_locked_killable(page); } if (unlikely(error)) goto readpage_error; if (PageUptodate(page)) goto page_ok; if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; /* Did it get truncated before we got the lock? */ if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } page_ok: /* * i_size must be checked after we know the page is Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ nr = PAGE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { put_page(page); goto out; } } nr = nr - offset; /* If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; prev_offset = offset; put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; if (ret < nr) { error = -EFAULT; goto out; } continue; page_not_up_to_date: /* Get exclusive access to the page ... */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); put_page(page); continue; } /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) { unlock_page(page); put_page(page); goto would_block; } /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. * PG_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page. */ error = mapping->a_ops->readpage(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { put_page(page); error = 0; goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_mapping_pages got it */ unlock_page(page); put_page(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(ra); error = -EIO; goto readpage_error; } unlock_page(page); } goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ put_page(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ page = page_cache_alloc(mapping); if (!page) { error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { put_page(page); if (error == -EEXIST) { error = 0; goto find_page; } goto out; } goto readpage; } would_block: error = -EAGAIN; out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; } EXPORT_SYMBOL_GPL(generic_file_buffered_read); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) goto out; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t size; size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_has_page(mapping, iocb->ki_pos, iocb->ki_pos + count - 1)) return -EAGAIN; } else { retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); if (retval < 0) goto out; } file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || iocb->ki_pos >= size || IS_DAX(inode)) goto out; } retval = generic_file_buffered_read(iocb, iter, retval); out: return retval; } EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @page - the page to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_page_or_retry in that it can drop the mmap_lock. * It differs in that it actually returns the page locked if it returns 1 and 0 * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin * will point to the pinned file and needs to be fput()'ed at a later point. */ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { if (trylock_page(page)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__lock_page_killable(page)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals * if we return VM_FAULT_RETRY, so we need to drop the * mmap_lock here and return 0 if we don't have a fpin. */ if (*fpin == NULL) mmap_read_unlock(vmf->vma->vm_mm); return 0; } } else __lock_page(page); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vmf->vma->vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; do_page_cache_ra(&ractl, ra->size, ra->async_size); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct page *page) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; unsigned int mmap_miss; pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (PageReadahead(page)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); } return fpin; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; pgoff_t max_off; struct page *page; vm_fault_t ret = 0; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { /* * We found the page, so try async readahead before * waiting for the lock. */ fpin = do_async_mmap_readahead(vmf, page); } else if (!page) { /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: page = pagecache_get_page(mapping, offset, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (!page) { if (fpin) goto out_retry; return VM_FAULT_OOM; } } if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(compound_head(page)->mapping != mapping)) { unlock_page(page); put_page(page); goto retry_find; } VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ if (unlikely(!PageUptodate(page))) goto page_not_uptodate; /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { unlock_page(page); goto out_retry; } /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) { unlock_page(page); put_page(page); return VM_FAULT_SIGBUS; } vmf->page = page; return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ ClearPageError(page); fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } if (fpin) goto out_retry; put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; shrink_readahead_size_eio(ra); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (page) put_page(page); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long max_idx; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *head, *page; unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); rcu_read_lock(); xas_for_each(&xas, head, end_pgoff) { if (xas_retry(&xas, head)) continue; if (xa_is_value(head)) goto next; /* * Check for a locked page first, as a speculative * reference may adversely influence page migration. */ if (PageLocked(head)) goto next; if (!page_cache_get_speculative(head)) goto next; /* Has the page moved or been split? */ if (unlikely(head != xas_reload(&xas))) goto skip; page = find_subpage(head, xas.xa_index); if (!PageUptodate(head) || PageReadahead(page) || PageHWPoison(page)) goto skip; if (!trylock_page(head)) goto skip; if (head->mapping != mapping || !PageUptodate(head)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas.xa_index >= max_idx) goto unlock; if (mmap_miss > 0) mmap_miss--; vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; if (alloc_set_pte(vmf, page)) goto unlock; unlock_page(head); goto next; unlock: unlock_page(head); skip: put_page(head); next: /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) break; } rcu_read_unlock(); WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the page dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty page and writeprotect it again. */ set_page_dirty(page); wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *wait_on_page_read(struct page *page) { if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { put_page(page); page = ERR_PTR(-EIO); } } return page; } static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data, gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } filler: if (filler) err = filler(data, page); else err = mapping->a_ops->readpage(data, page); if (err < 0) { put_page(page); return ERR_PTR(err); } page = wait_on_page_read(page); if (IS_ERR(page)) return page; goto out; } if (PageUptodate(page)) goto out; /* * Page is not up to date and may be locked due to one of the following * case a: Page is being filled and the page lock is held * case b: Read/write error clearing the page uptodate status * case c: Truncation in progress (page locked) * case d: Reclaim in progress * * Case a, the page will be up to date when the page is unlocked. * There is no need to serialise on the page lock here as the page * is pinned so the lock gives no additional protection. Even if the * page is truncated, the data is still valid if PageUptodate as * it's a race vs truncate race. * Case b, the page will not be up to date * Case c, the page may be truncated but in itself, the data may still * be valid after IO completes as it's a read vs truncate race. The * operation must restart if the page is not uptodate on unlock but * otherwise serialising on page lock to stabilise the mapping gives * no additional guarantees to the caller as the page lock is * released before return. * Case d, similar to truncation. If reclaim holds the page lock, it * will be a race with remove_mapping that determines if the mapping * is valid on unlock but otherwise the data is valid and there is * no need to serialise with page lock. * * As the page lock gives no additional guarantee, we optimistically * wait on the page to be unlocked and check if it's up to date and * use the page if it is. Otherwise, the page lock is required to * distinguish between the different cases. The motivation is that we * avoid spurious serialisations and wakeups when multiple processes * wait on the same page for IO to complete. */ wait_on_page_locked(page); if (PageUptodate(page)) goto out; /* Distinguish between all the cases under the safety of the lock */ lock_page(page); /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); put_page(page); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (PageUptodate(page)) { unlock_page(page); goto out; } /* * A previous I/O error may have been due to temporary * failures. * Clear page error before actual read, PG_error will be * set again if read page fails. */ ClearPageError(page); goto filler; out: mark_page_accessed(page); return page; } /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); } EXPORT_SYMBOL(pagecache_write_begin); int pagecache_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); /* * Warn about a page cache invalidation failure during a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; struct inode *inode = file_inode(filp); char *path; errseq_set(&inode->i_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written; size_t write_len; pgoff_t end; write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ if (filemap_range_has_page(inode->i_mapping, pos, pos + write_len - 1)) return -EAGAIN; } else { written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) goto out; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ if (written) { if (written == -EBUSY) return 0; goto out; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0 && mapping->nrpages && invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end)) dio_warn_stale_pagecache(file); if (written > 0) { pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; } EXPORT_SYMBOL(generic_file_direct_write); /* * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { struct page *page; int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; if (flags & AOP_FLAG_NOFS) fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; unsigned int flags = 0; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * Not only is this an optimisation, but it is also required * to check that the address is actually valid, when atomic * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) break; copied = status; cond_resched(); iov_iter_advance(i, copied); if (unlikely(copied == 0)) { /* * If we were unable to copy any data at all, we must * fall back to a single segment length write. * * If we didn't fallback here, we could livelock * because not all segments in the iov can be copied at * once without a pagefault. */ bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } pos += copied; written += copied; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); return written ? written : status; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_mutex to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; ssize_t status; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; err = file_update_time(file); if (err) goto out; if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos, endbyte; written = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; status = generic_perform_write(file, from, pos = iocb->ki_pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ if (unlikely(status < 0)) { err = status; goto out; } /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + status - 1; err = filemap_write_and_wait_range(mapping, pos, endbyte); if (err == 0) { iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return * the number of bytes which were direct-written */ } } else { written = generic_perform_write(file, from, iocb->ki_pos); if (likely(written > 0)) iocb->ki_pos += written; } out: current->backing_dev_info = NULL; return written ? written : err; } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page * * @page: the page which the kernel is trying to free * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page * (presumably at page->private). * * This may also be called if PG_fscache is set on a page, indicating that the * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). * * Return: %1 if the release was successful, otherwise return zero. */ int try_to_release_page(struct page *page, gfp_t gfp_mask) { struct address_space * const mapping = page->mapping; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping && mapping->a_ops->releasepage) return mapping->a_ops->releasepage(page, gfp_mask); return try_to_free_buffers(page); } EXPORT_SYMBOL(try_to_release_page); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KERNEL_PRINTK__ #define __KERNEL_PRINTK__ #include <stdarg.h> #include <linux/init.h> #include <linux/kern_levels.h> #include <linux/linkage.h> #include <linux/cache.h> #include <linux/ratelimit_types.h> extern const char linux_banner[]; extern const char linux_proc_banner[]; extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ #define PRINTK_MAX_SINGLE_HEADER_LEN 2 static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { switch (buffer[1]) { case '0' ... '7': case 'c': /* KERN_CONT */ return buffer[1]; } } return 0; } static inline const char *printk_skip_level(const char *buffer) { if (printk_get_level(buffer)) return buffer + 2; return buffer; } static inline const char *printk_skip_headers(const char *buffer) { while (printk_get_level(buffer)) buffer = printk_skip_level(buffer); return buffer; } #define CONSOLE_EXT_LOG_MAX 8192 /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ /* * Default used to be hard-coded at 7, quiet used to be hardcoded at 4, * we're now allowing both to be set from kernel config. */ #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT #define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET extern int console_printk[]; #define console_loglevel (console_printk[0]) #define default_message_loglevel (console_printk[1]) #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) static inline void console_silent(void) { console_loglevel = CONSOLE_LOGLEVEL_SILENT; } static inline void console_verbose(void) { if (console_loglevel) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 extern char devkmsg_log_str[]; struct ctl_table; extern int suppress_printk; struct va_format { const char *fmt; va_list *va; }; /* * FW_BUG * Add this to a message where you are sure the firmware is buggy or behaves * really stupid or out of spec. Be aware that the responsible BIOS developer * should be able to fix this issue or at least get a concrete idea of the * problem by reading your message without the need of looking at the kernel * code. * * Use it for definite and high priority BIOS bugs. * * FW_WARN * Use it for not that clear (e.g. could the kernel messed up things already?) * and medium priority BIOS bugs. * * FW_INFO * Use this one if you want to tell the user or vendor about something * suspicious, but generally harmless related to the firmware. * * Use it for information or very low priority BIOS bugs. */ #define FW_BUG "[Firmware Bug]: " #define FW_WARN "[Firmware Warn]: " #define FW_INFO "[Firmware Info]: " /* * HW_ERR * Add this to a message for hardware errors, so that user can report * it to hardware vendor instead of LKML or software vendor. */ #define HW_ERR "[Hardware Error]: " /* * DEPRECATED * Add this to a message whenever you want to warn user space about the use * of a deprecated aspect of an API so they can stop using it */ #define DEPRECATED "[Deprecated]: " /* * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format checking. */ #define no_printk(fmt, ...) \ ({ \ if (0) \ printk(fmt, ##__VA_ARGS__); \ 0; \ }) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif #ifdef CONFIG_PRINTK_NMI extern void printk_nmi_enter(void); extern void printk_nmi_exit(void); extern void printk_nmi_direct_enter(void); extern void printk_nmi_direct_exit(void); #else static inline void printk_nmi_enter(void) { } static inline void printk_nmi_exit(void) { } static inline void printk_nmi_direct_enter(void) { } static inline void printk_nmi_direct_exit(void) { } #endif /* PRINTK_NMI */ struct dev_printk_info; #ifdef CONFIG_PRINTK asmlinkage __printf(4, 0) int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args); asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ __printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use * printk_ratelimited() or plain old __ratelimit(). */ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); extern int printk_delay_msec; extern int dmesg_restrict; extern int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos); extern void wake_up_klogd(void); char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_vmcoreinfo_setup(void); void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack(void) __cold; extern void printk_safe_flush(void); extern void printk_safe_flush_on_panic(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) { return 0; } static inline __printf(1, 2) __cold int printk(const char *s, ...) { return 0; } static inline __printf(1, 2) __cold int printk_deferred(const char *s, ...) { return 0; } static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec) { return false; } static inline void wake_up_klogd(void) { } static inline char *log_buf_addr_get(void) { return NULL; } static inline u32 log_buf_len_get(void) { return 0; } static inline void log_buf_vmcoreinfo_setup(void) { } static inline void setup_log_buf(int early) { } static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } static inline void dump_stack_print_info(const char *log_lvl) { } static inline void show_regs_print_info(const char *log_lvl) { } static inline void dump_stack(void) { } static inline void printk_safe_flush(void) { } static inline void printk_safe_flush_on_panic(void) { } #endif extern int kptr_restrict; /** * pr_fmt - used by the pr_*() macros to generate the printk format string * @fmt: format string passed from a pr_*() macro * * This macro can be used to generate a unified format string for pr_*() * macros. A common use is to prefix all pr_*() messages in a file with a common * string. For example, defining this at the top of a source file: * * #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt * * would prefix all pr_info, pr_emerg... messages in the file with the module * name. */ #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif /** * pr_emerg - Print an emergency-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) /** * pr_alert - Print an alert-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_alert(fmt, ...) \ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_crit - Print a critical-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_crit(fmt, ...) \ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_err - Print an error-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) /** * pr_warn - Print a warning-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt() * to generate the format string. */ #define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) /** * pr_notice - Print a notice-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) /** * pr_info - Print an info-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /** * pr_cont - Continues a previous log message in the same line. * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CONT loglevel. It should only be * used when continuing a log message with no newline ('\n') enclosed. Otherwise * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) /** * pr_devel - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is * defined. Otherwise it does nothing. * * It uses pr_fmt() to generate the format string. */ #ifdef DEBUG #define pr_devel(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #include <linux/dynamic_debug.h> /** * pr_debug - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is * set. Otherwise, if DEBUG is defined, it's equivalent to a printk with * KERN_DEBUG loglevel. If DEBUG is not defined it does nothing. * * It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses * pr_fmt() internally). */ #define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) #elif defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * Print a one-time message (analogous to WARN_ONCE() et al): */ #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ ({ \ static bool __section(".data.once") __print_once; \ bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ __print_once = true; \ printk(fmt, ##__VA_ARGS__); \ } \ unlikely(__ret_print_once); \ }) #define printk_deferred_once(fmt, ...) \ ({ \ static bool __section(".data.once") __print_once; \ bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ __print_once = true; \ printk_deferred(fmt, ##__VA_ARGS__); \ } \ unlikely(__ret_print_once); \ }) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_once(fmt, ...) \ printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_once(fmt, ...) \ printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_once(fmt, ...) \ printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_once(fmt, ...) \ printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_once(fmt, ...) \ printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_once(fmt, ...) \ printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_once(fmt, ...) \ printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_once, don't do that... */ #if defined(DEBUG) #define pr_devel_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(DEBUG) #define pr_debug_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * ratelimited messages with local ratelimit_state, * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK #define printk_ratelimited(fmt, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else #define printk_ratelimited(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_ratelimited(fmt, ...) \ printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_ratelimited(fmt, ...) \ printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_ratelimited(fmt, ...) \ printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_ratelimited, don't do that... */ #if defined(DEBUG) #define pr_devel_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define pr_debug_ratelimited(fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ __ratelimit(&_rs)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define pr_debug_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif extern const struct file_operations kmsg_fops; enum { DUMP_PREFIX_NONE, DUMP_PREFIX_ADDRESS, DUMP_PREFIX_OFFSET }; extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize, char *linebuf, size_t linebuflen, bool ascii); #ifdef CONFIG_PRINTK extern void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); #else static inline void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, const void *buf, size_t len) { } #endif #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #elif defined(DEBUG) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #else static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } #endif /** * print_hex_dump_bytes - shorthand form of print_hex_dump() with default params * @prefix_str: string to prefix each line with; * caller supplies trailing spaces for alignment if desired * @prefix_type: controls whether prefix of an offset, address, or none * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) * @buf: data blob to dump * @len: number of bytes in the @buf * * Calls print_hex_dump(), with log level of KERN_DEBUG, * rowsize of 16, groupsize of 1, and ASCII output included. */ #define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true) #ifdef CONFIG_PRINTK extern void __printk_safe_enter(void); extern void __printk_safe_exit(void); /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts * must be disabled for the deferred duration. */ #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit #else static inline void printk_deferred_enter(void) { } static inline void printk_deferred_exit(void) { } #endif #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_SCHED_H #define BLK_MQ_SCHED_H #include "blk-mq.h" #include "blk-mq-tag.h" void blk_mq_sched_assign_ioc(struct request *rq); void blk_mq_sched_request_inserted(struct request *rq); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs); bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue, bool async); void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list, bool run_queue_async); void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx); int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e); void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e); void blk_mq_sched_free_requests(struct request_queue *q); static inline bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { if (blk_queue_nomerges(q) || !bio_mergeable(bio)) return false; return __blk_mq_sched_bio_merge(q, bio, nr_segs); } static inline bool blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { struct elevator_queue *e = q->elevator; if (e && e->type->ops.allow_merge) return e->type->ops.allow_merge(q, rq, bio); return true; } static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) { struct elevator_queue *e = rq->q->elevator; if (e && e->type->ops.completed_request) e->type->ops.completed_request(rq, now); } static inline void blk_mq_sched_requeue_request(struct request *rq) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request) e->type->ops.requeue_request(rq); } static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx) { struct elevator_queue *e = hctx->queue->elevator; if (e && e->type->ops.has_work) return e->type->ops.has_work(hctx); return false; } static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx) { return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> static struct kmem_cache *user_ns_cachep __read_mostly; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifing that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; ns->ns.ops = &userns_operations; atomic_set(&ns->count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_free_inum(&ns->ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); dec_user_namespaces(ucounts); ns = parent; } while (atomic_dec_and_test(&parent->count)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /** * idmap_key struct holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; /* == 0 unless used with map_id_range_down() */ }; /** * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /** * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /** * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } static u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /** * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) { unsigned idx; u32 first, last; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last) return &map->extent[idx]; } return NULL; } /** * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) { struct idmap_key key; key.map_up = true; key.count = 1; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } static u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_up_base(extents, map, id); else extent = map_id_up_max(extents, map, id); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /** * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /** * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup(map->forward, map->nr_extents * sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file * @map_ns: user namespace of the target process * @new_map: requested idmap * * If a process requests mapping parent uid 0 into the new ns, verify that the * process writing the map had the CAP_SETFCAP capability as the target process * will be able to write fscaps that are valid in ancestor user namespaces. * * Return: true if the mapping is allowed, false if not. */ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; struct uid_gid_extent *extent0 = NULL; for (idx = 0; idx < new_map->nr_extents; idx++) { if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent0 = &new_map->extent[idx]; else extent0 = &new_map->forward[idx]; if (extent0->lower_first == 0) break; extent0 = NULL; } if (!extent0) return true; if (map_ns == file_ns) { /* The process unshared its ns and is writing to its own * /proc/self/uid_map. User already has full capabilites in * the new namespace. Verify that the parent had CAP_SETFCAP * when it unshared. * */ if (!file_ns->parent_could_setfcap) return false; } else { /* Process p1 is writing to uid_map of p2, who is in a child * user namespace to p1's. Verify that the opener of the map * file has CAP_SETFCAP against the parent of the new map * namespace */ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) return false; } return true; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf = NULL, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certaint the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) return false; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also had the approprpiate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsset *nsset, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = nsset_cred(nsset); if (!cred) return -EINVAL; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); return 0; } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); return 0; } subsys_initcall(user_namespaces_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(page) ( \ (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \ (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \ (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \ (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \ (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, int lru ), TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) __field(int, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); __entry->lru = lru; __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu lru=%d flags=%s%s%s%s%s%s", __entry->page, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu", __entry->page, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/ww_mutex.h> #include <linux/preempt.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 /* * Sequence counters (seqcount_t) * * This is the raw counting mechanism, without any writer protection. * * Write side critical sections must be serialized and non-preemptible. * * If readers can be invoked from hardirq or softirq contexts, * interrupts or bottom halves must also be respectively disabled before * entering the write section. * * This mechanism can't be used if the protected data contains pointers, * as the writer can invalidate a pointer that a reader is following. * * If the write serialization mechanism is one of the common kernel * locking primitives, use a sequence counter with associated lock * (seqcount_LOCKNAME_t) instead. * * If it's desired to automatically handle the sequence counter writer * serialization and non-preemptibility requirements, use a sequential * lock (seqlock_t) instead. * * See Documentation/locking/seqlock.rst */ typedef struct seqcount { unsigned sequence; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } seqcount_t; static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot * disable preemption. It can lead to higher latencies, and the write side * sections will not be able to acquire locks which become sleeping locks * (e.g. spinlock_t). * * To remain preemptible while avoiding a possible livelock caused by the * reader preempting the writer, use a different technique: let the reader * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the * case, acquire then release the associated LOCKNAME writer serialization * lock. This will allow any possibly-preempted writer to make progress * until the end of its writer serialization lock critical section. * * This lock-unlock technique must be implemented for all of PREEMPT_RT * sleeping locks. See Documentation/locking/locktypes.rst */ #if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) #define __SEQ_LOCK(expr) expr #else #define __SEQ_LOCK(expr) #endif /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock); #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex); #define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex); /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockmember: argument for lockdep_assert_held() * @lockbase: associated lock release function (prefix only) * @lock_acquire: associated lock acquisition function (full call) */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \ typedef struct seqcount_##lockname { \ seqcount_t seqcount; \ __SEQ_LOCK(locktype *lock); \ } seqcount_##lockname##_t; \ \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = READ_ONCE(s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lock_acquire); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = READ_ONCE(s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(lockmember)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return READ_ONCE(s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_spin, raw_spin_lock(s->lock)) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s)) #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop((void *)(s)), \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop), \ __seqprop_case((s), ww_mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr) #define seqprop_sequence(s) __seqprop(s, sequence) #define seqprop_preemptible(s) __seqprop(s, preemptible) #define seqprop_assert(s) __seqprop(s, assert) /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ while ((__seq = seqprop_sequence(s)) & 1) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) \ ({ \ unsigned _seq = __read_seqcount_begin(s); \ \ smp_rmb(); \ _seq; \ }) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(seqprop_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned __seq = seqprop_sequence(s); \ \ smp_rmb(); \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ do___read_seqcount_retry(seqprop_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ do_read_seqcount_retry(seqprop_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return do___read_seqcount_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_begin(s) \ do { \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_raw_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_end(s) \ do { \ do_raw_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst */ #define write_seqcount_begin_nested(s, subclass) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \ } while (0) static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); do_raw_write_seqcount_begin(s); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * write_seqcount_begin opens a write side critical section of the given * seqcount_t. * * Context: seqcount_t write side critical sections must be serialized and * non-preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_write_seqcount_begin(seqcount_t *s) { do_write_seqcount_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * The write section must've been opened with write_seqcount_begin(). */ #define write_seqcount_end(s) \ do { \ do_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); do_raw_write_seqcount_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before and after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ do_raw_write_seqcount_barrier(seqprop_ptr(s)) static inline void do_raw_write_seqcount_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ do_write_seqcount_invalidate(seqprop_ptr(s)) static inline void do_write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { return read_seqcount_retry(&s->seqcount, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * smp_wmb(); // Ensure that the last data[1] update is visible * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[0], ...); * * smp_wmb(); // Ensure that the data[0] update is visible * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[1], ...); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = raw_read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /* * Sequential locks (seqlock_t) * * Sequence counters with an embedded spinlock for writer serialization * and non-preemptibility. * * For more info, see: * - Comments on top of seqcount_t * - Documentation/locking/seqlock.rst */ typedef struct { /* * Make sure that readers don't starve writers on PREEMPT_RT: use * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). */ seqcount_spinlock_t seqcount; spinlock_t lock; } seqlock_t; #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use the the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); do_write_seqcount_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } #endif /* __LINUX_SEQLOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/dax.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ union { short preferred_node; /* preferred */ nodemask_t nodes; /* interleave/bind */ /* undefined for default */ } v; union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } #define vma_policy(vma) ((vma)->vm_policy) static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. * Maintain the policies in a pseudo mm that contains vmas. The vmas * carry the policy. As a special twist the pseudo mm is indexed in pages, not * bytes, so that we can work with shared memory segments bigger than * unsigned long. */ struct sp_node { struct rb_node nd; unsigned long start, end; struct mempolicy *policy; }; struct shared_policy { struct rb_root root; rwlock_t lock; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *new); void mpol_free_shared_policy(struct shared_policy *p); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { struct mempolicy *mpol = get_task_policy(current); return policy_nodemask(gfp, mpol); } extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); #else struct mempolicy {}; static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *p) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *p) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) { return NULL; } #define vma_policy(vma) NULL static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { return NULL; } #endif /* CONFIG_NUMA */ #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *parent; unsigned long flags; /* nothing to do for root */ if (!cgroup_parent(cgrp)) return; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (cgroup_rstat_cpu(cgrp, cpu)->updated_next) return; raw_spin_lock_irqsave(cpu_lock, flags); /* put @cgrp and all ancestors on the corresponding updated lists */ for (parent = cgroup_parent(cgrp); parent; cgrp = parent, parent = cgroup_parent(cgrp)) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; } raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree * @pos: current position * @root: root of the tree to traversal * @cpu: target cpu * * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, if a child is visited, its parent is * guaranteed to be visited afterwards. */ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; if (pos == root) return NULL; /* * We're gonna walk down to the first leaf and visit/remove it. We * can pick whatever unvisited node as the starting point. */ if (!pos) pos = root; else pos = cgroup_parent(pos); /* walk down to the first leaf */ while (true) { rstatc = cgroup_rstat_cpu(pos, cpu); if (rstatc->updated_children == pos) break; pos = rstatc->updated_children; } /* * Unlink @pos from the tree. As the updated_children list is * singly linked, we have to walk it to find the removal point. * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ if (rstatc->updated_next) { struct cgroup *parent = cgroup_parent(pos); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); struct cgroup_rstat_cpu *nrstatc; struct cgroup **nextp; nextp = &prstatc->updated_children; while (true) { nrstatc = cgroup_rstat_cpu(*nextp, cpu); if (*nextp == pos) break; WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; rstatc->updated_next = NULL; return pos; } /* only happens for @root */ return NULL; } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; raw_spin_lock(cpu_lock); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } raw_spin_unlock(cpu_lock); /* if @may_sleep, play nice and yield if necessary */ if (may_sleep && (need_resched() || spin_needbreak(&cgroup_rstat_lock))) { spin_unlock_irq(&cgroup_rstat_lock); if (!cond_resched()) cpu_relax(); spin_lock_irq(&cgroup_rstat_lock); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); spin_unlock_irq(&cgroup_rstat_lock); } /** * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() * @cgrp: target cgroup * * This function can be called from any context. */ void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) { unsigned long flags; spin_lock_irqsave(&cgroup_rstat_lock, flags); cgroup_rstat_flush_locked(cgrp, false); spin_unlock_irqrestore(&cgroup_rstat_lock, flags); } /** * cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() */ void cgroup_rstat_flush_release(void) __releases(&cgroup_rstat_lock) { spin_unlock_irq(&cgroup_rstat_lock); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_base_stat cur, delta; unsigned seq; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); cur.cputime = rstatc->bstat.cputime; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate percpu delta to global */ delta = cur; cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); /* propagate global delta to parent */ if (parent) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); u64_stats_update_begin(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc) { u64_stats_update_end(&rstatc->bsync); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct task_cputime *cputime) { int i; cputime->stime = 0; cputime->utime = 0; cputime->sum_exec_runtime = 0; for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; } } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; struct task_cputime cputime; if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); cgroup_rstat_flush_release(); } else { root_cgroup_cputime(&cputime); usage = cputime.sum_exec_runtime; utime = cputime.utime; stime = cputime.stime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H #include <linux/compiler.h> #include <asm/percpu.h> #ifndef __ASSEMBLY__ struct task_struct; DECLARE_PER_CPU(struct task_struct *, current_task); static __always_inline struct task_struct *get_current(void) { return this_cpu_read_stable(current_task); } #define current get_current() #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CURRENT_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/printk.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Modified to make sys_syslog() more flexible: added commands to * return the last 4k of kernel messages, regardless of whether * they've been read or not. Added option to suppress kernel printk's * to the console. Added hook for sending the console messages * elsewhere, in preparation for a serial line console (someday). * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/crash_core.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> #include <asm/sections.h> #include <trace/events/initcall.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. */ int oops_in_progress; EXPORT_SYMBOL(oops_in_progress); /* * console_sem protects the console_drivers list, and also * provides serialisation for access to the entire console * driver system. */ static DEFINE_SEMAPHORE(console_sem); struct console *console_drivers; EXPORT_SYMBOL_GPL(console_drivers); /* * System may need to suppress printk message under certain * circumstances, like after kernel panic happens. */ int __read_mostly suppress_printk; #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; #endif enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, __DEVKMSG_LOG_BIT_LOCK, }; enum devkmsg_log_masks { DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), }; /* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ #define DEVKMSG_LOG_MASK_DEFAULT 0 static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; static int __control_devkmsg(char *str) { size_t len; if (!str) return -EINVAL; len = str_has_prefix(str, "on"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_ON; return len; } len = str_has_prefix(str, "off"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_OFF; return len; } len = str_has_prefix(str, "ratelimit"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; return len; } return -EINVAL; } static int __init control_devkmsg(char *str) { if (__control_devkmsg(str) < 0) { pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; } /* * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) strcpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) strcpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* * Sysctl cannot change it anymore. The kernel command line setting of * this parameter is to force the setting to be permanent throughout the * runtime of the system. This is a precation measure against userspace * trying to be a smarta** and attempting to change it up on us. */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; return 1; } __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; unsigned int old; int err; if (write) { if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) return -EINVAL; old = devkmsg_log; strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE); } err = proc_dostring(table, write, buffer, lenp, ppos); if (err) return err; if (write) { err = __control_devkmsg(devkmsg_log_str); /* * Do not accept an unknown string OR a known string with * trailing crap... */ if (err < 0 || (err + 1 != *lenp)) { /* ... and restore old setting. */ devkmsg_log = old; strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE); return -EINVAL; } } return 0; } /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ #define down_console_sem() do { \ down(&console_sem);\ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ } while (0) static int __down_trylock_console_sem(unsigned long ip) { int lock_failed; unsigned long flags; /* * Here and in __up_console_sem() we need to be in safe mode, * because spindump/WARN/etc from under console ->lock will * deadlock in printk()->down_trylock_console_sem() otherwise. */ printk_safe_enter_irqsave(flags); lock_failed = down_trylock(&console_sem); printk_safe_exit_irqrestore(flags); if (lock_failed) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; } #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) static void __up_console_sem(unsigned long ip) { unsigned long flags; mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's * definitely not the perfect debug tool (we don't know if _WE_ * hold it and are racing, but it helps tracking those weird code * paths in the console code where we end up in places I want * locked without the console sempahore held). */ static int console_locked, console_suspended; /* * If exclusive_console is non-NULL then only this console is to be printed to. */ static struct console *exclusive_console; /* * Array of consoles built from command line options (console=) */ #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; static bool has_preferred_console; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; enum con_msg_format_flags { MSG_FORMAT_DEFAULT = 0, MSG_FORMAT_SYSLOG = (1 << 0), }; static int console_msg_format = MSG_FORMAT_DEFAULT; /* * The printk log buffer consists of a sequenced collection of records, each * containing variable length message text. Every record also contains its * own meta-data (@info). * * Every record meta-data carries the timestamp in microseconds, as well as * the standard userspace syslog level and syslog facility. The usual kernel * messages use LOG_KERN; userspace-injected messages always carry a matching * syslog facility, by default LOG_USER. The origin of every message can be * reliably determined that way. * * The human readable log message of a record is available in @text, the * length of the message text in @text_len. The stored message is not * terminated. * * Optionally, a record can carry a dictionary of properties (key/value * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * * Valid characters in property names are [a-zA-Z0-9.-_]. Property names * and values are terminated by a '\0' character. * * Example of record values: * record.text_buf = "it's a line" (unterminated) * record.info.seq = 56 * record.info.ts_nsec = 36863 * record.info.text_len = 11 * record.info.facility = 0 (LOG_KERN) * record.info.flags = 0 * record.info.level = 3 (LOG_ERR) * record.info.caller_id = 299 (task 299) * record.info.dev_info.subsystem = "pci" (terminated) * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) * * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" * * Users of the export format should ignore possible additional values * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. */ enum log_flags { LOG_NEWLINE = 2, /* text ended with a newline */ LOG_CONT = 8, /* text is a fragment of a continuation line */ }; /* * The logbuf_lock protects kmsg buffer, indices, counters. This can be taken * within the scheduler's rq lock. It must be released before calling * console_unlock() or anything else that might wake up a process. */ DEFINE_RAW_SPINLOCK(logbuf_lock); /* * Helper macros to lock/unlock logbuf_lock and switch between * printk-safe/unsafe modes. */ #define logbuf_lock_irq() \ do { \ printk_safe_enter_irq(); \ raw_spin_lock(&logbuf_lock); \ } while (0) #define logbuf_unlock_irq() \ do { \ raw_spin_unlock(&logbuf_lock); \ printk_safe_exit_irq(); \ } while (0) #define logbuf_lock_irqsave(flags) \ do { \ printk_safe_enter_irqsave(flags); \ raw_spin_lock(&logbuf_lock); \ } while (0) #define logbuf_unlock_irqrestore(flags) \ do { \ raw_spin_unlock(&logbuf_lock); \ printk_safe_exit_irqrestore(flags); \ } while (0) #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; /* the next printk record to write to the console */ static u64 console_seq; static u64 exclusive_console_stop_seq; static unsigned long console_dropped; /* the next printk record to read after the last 'clear' command */ static u64 clear_seq; #ifdef CONFIG_PRINTK_CALLER #define PREFIX_MAX 48 #else #define PREFIX_MAX 32 #endif #define LOG_LINE_MAX (1024 - PREFIX_MAX) #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* * Define the average message size. This only affects the number of * descriptors that will be available. Underestimating is better than * overestimating (too many available descriptors is better than not enough). */ #define PRB_AVGBITS 5 /* 32 character average length */ #if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS #error CONFIG_LOG_BUF_SHIFT value too small. #endif _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, PRB_AVGBITS, &__log_buf[0]); static struct printk_ringbuffer printk_rb_dynamic; static struct printk_ringbuffer *prb = &printk_rb_static; /* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. */ static bool __printk_percpu_data_ready __read_mostly; bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } /* Return log buffer address */ char *log_buf_addr_get(void) { return log_buf; } /* Return log buffer size */ u32 log_buf_len_get(void) { return log_buf_len; } /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available * when the index points to the middle. */ #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; if (*text_len > max_text_len) *text_len = max_text_len; /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); if (*text_len >= *trunc_msg_len) *text_len -= *trunc_msg_len; else *trunc_msg_len = 0; } /* insert record into the buffer, discard old ones, update heads */ static int log_store(u32 caller_id, int facility, int level, enum log_flags flags, u64 ts_nsec, const struct dev_printk_info *dev_info, const char *text, u16 text_len) { struct prb_reserved_entry e; struct printk_record r; u16 trunc_msg_len = 0; prb_rec_init_wr(&r, text_len); if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ truncate_msg(&text_len, &trunc_msg_len); prb_rec_init_wr(&r, text_len + trunc_msg_len); /* survive when the log buffer is too small for trunc_msg */ if (!prb_reserve(&e, prb, &r)) return 0; } /* fill message */ memcpy(&r.text_buf[0], text, text_len); if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); r.info->text_len = text_len + trunc_msg_len; r.info->facility = facility; r.info->level = level & 7; r.info->flags = flags & 0x1f; if (ts_nsec > 0) r.info->ts_nsec = ts_nsec; else r.info->ts_nsec = local_clock(); r.info->caller_id = caller_id; if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* A message without a trailing newline can be continued. */ if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); return (text_len + trunc_msg_len); } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); static int syslog_action_restricted(int type) { if (dmesg_restrict) return 1; /* * Unless restricted, we allow "read all" and "get buffer size" * for everybody. */ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; } static int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; /* * For historical reasons, accept CAP_SYS_ADMIN too, with * a warning. */ if (capable(CAP_SYS_ADMIN)) { pr_warn_once("%s (%d): Attempt to access syslog with " "CAP_SYS_ADMIN but no CAP_SYSLOG " "(deprecated).\n", current->comm, task_pid_nr(current)); goto ok; } return -EPERM; } ok: return security_syslog(type); } static void append_char(char **pp, char *e, char c) { if (*pp < e) *(*pp)++ = c; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER u32 id = info->caller_id; snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); #else caller[0] = '\0'; #endif do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", (info->facility << 3) | info->level, info->seq, ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } static ssize_t msg_add_ext_text(char *buf, size_t size, const char *text, size_t text_len, unsigned char endc) { char *p = buf, *e = buf + size; size_t i; /* escape non-printable characters */ for (i = 0; i < text_len; i++) { unsigned char c = text[i]; if (c < ' ' || c >= 127 || c == '\\') p += scnprintf(p, e - p, "\\x%02x", c); else append_char(&p, e, c); } append_char(&p, e, endc); return p - buf; } static ssize_t msg_add_dict_text(char *buf, size_t size, const char *key, const char *val) { size_t val_len = strlen(val); ssize_t len; if (!val_len) return 0; len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); return len; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { ssize_t len; len = msg_add_ext_text(buf, size, text, text_len, '\n'); if (!dev_info) goto out; len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", dev_info->subsystem); len += msg_add_dict_text(buf + len, size - len, "DEVICE", dev_info->device); out: return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { u64 seq; struct ratelimit_state rs; struct mutex lock; char buf[CONSOLE_EXT_LOG_MAX]; struct printk_info info; char text_buf[CONSOLE_EXT_LOG_MAX]; struct printk_record record; }; static __printf(3, 4) __cold int devkmsg_emit(int facility, int level, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; } static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ struct file *file = iocb->ki_filp; struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; if (!user || len > LOG_LINE_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return len; /* Ratelimit when not explicitly enabled. */ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { if (!___ratelimit(&user->rs, current->comm)) return ret; } buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; buf[len] = '\0'; if (!copy_from_iter_full(buf, len, from)) { kfree(buf); return -EFAULT; } /* * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace * the decimal value represents 32bit, the lower 3 bit are the log * level, the rest are the log facility. * * If no prefix or no userspace facility is specified, we * enforce LOG_USER, to be able to reliably distinguish * kernel-generated messages from userspace-injected ones. */ line = buf; if (line[0] == '<') { char *endp = NULL; unsigned int u; u = simple_strtoul(line + 1, &endp, 10); if (endp && endp[0] == '>') { level = LOG_LEVEL(u); if (LOG_FACILITY(u) != 0) facility = LOG_FACILITY(u); endp++; len -= endp - line; line = endp; } } devkmsg_emit(facility, level, "%s", line); kfree(buf); return ret; } static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; struct printk_record *r = &user->record; size_t len; ssize_t ret; if (!user) return -EBADF; ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; logbuf_lock_irq(); if (!prb_read_valid(prb, user->seq, r)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; logbuf_unlock_irq(); goto out; } logbuf_unlock_irq(); ret = wait_event_interruptible(log_wait, prb_read_valid(prb, user->seq, r)); if (ret) goto out; logbuf_lock_irq(); } if (r->info->seq != user->seq) { /* our last seen message is gone, return error and reset */ user->seq = r->info->seq; ret = -EPIPE; logbuf_unlock_irq(); goto out; } len = info_print_ext_header(user->buf, sizeof(user->buf), r->info); len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len, &r->text_buf[0], r->info->text_len, &r->info->dev_info); user->seq = r->info->seq + 1; logbuf_unlock_irq(); if (len > count) { ret = -EINVAL; goto out; } if (copy_to_user(buf, user->buf, len)) { ret = -EFAULT; goto out; } ret = len; out: mutex_unlock(&user->lock); return ret; } /* * Be careful when modifying this function!!! * * Only few operations are supported because the device works only with the * entire variable length messages (records). Non-standard values are * returned in the other cases and has been this way for quite some time. * User space applications might depend on this behavior. */ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) { struct devkmsg_user *user = file->private_data; loff_t ret = 0; if (!user) return -EBADF; if (offset) return -ESPIPE; logbuf_lock_irq(); switch (whence) { case SEEK_SET: /* the first record */ user->seq = prb_first_valid_seq(prb); break; case SEEK_DATA: /* * The first record after the last SYSLOG_ACTION_CLEAR, * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ user->seq = clear_seq; break; case SEEK_END: /* after the last record */ user->seq = prb_next_seq(prb); break; default: ret = -EINVAL; } logbuf_unlock_irq(); return ret; } static __poll_t devkmsg_poll(struct file *file, poll_table *wait) { struct devkmsg_user *user = file->private_data; struct printk_info info; __poll_t ret = 0; if (!user) return EPOLLERR|EPOLLNVAL; poll_wait(file, &log_wait, wait); logbuf_lock_irq(); if (prb_read_valid_info(prb, user->seq, &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != user->seq) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } logbuf_unlock_irq(); return ret; } static int devkmsg_open(struct inode *inode, struct file *file) { struct devkmsg_user *user; int err; if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return -EPERM; /* write-only does not need any file context */ if ((file->f_flags & O_ACCMODE) != O_WRONLY) { err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, SYSLOG_FROM_READER); if (err) return err; } user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); if (!user) return -ENOMEM; ratelimit_default_init(&user->rs); ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); mutex_init(&user->lock); prb_rec_init_rd(&user->record, &user->info, &user->text_buf[0], sizeof(user->text_buf)); logbuf_lock_irq(); user->seq = prb_first_valid_seq(prb); logbuf_unlock_irq(); file->private_data = user; return 0; } static int devkmsg_release(struct inode *inode, struct file *file) { struct devkmsg_user *user = file->private_data; if (!user) return 0; ratelimit_state_exit(&user->rs); mutex_destroy(&user->lock); kfree(user); return 0; } const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, }; #ifdef CONFIG_CRASH_CORE /* * This appends the listed symbols to /proc/vmcore * * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ void log_buf_vmcoreinfo_setup(void) { struct dev_printk_info *dev_info = NULL; VMCOREINFO_SYMBOL(prb); VMCOREINFO_SYMBOL(printk_rb_static); VMCOREINFO_SYMBOL(clear_seq); /* * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); VMCOREINFO_OFFSET(printk_ringbuffer, fail); VMCOREINFO_STRUCT_SIZE(prb_desc_ring); VMCOREINFO_OFFSET(prb_desc_ring, count_bits); VMCOREINFO_OFFSET(prb_desc_ring, descs); VMCOREINFO_OFFSET(prb_desc_ring, infos); VMCOREINFO_OFFSET(prb_desc_ring, head_id); VMCOREINFO_OFFSET(prb_desc_ring, tail_id); VMCOREINFO_STRUCT_SIZE(prb_desc); VMCOREINFO_OFFSET(prb_desc, state_var); VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); VMCOREINFO_OFFSET(prb_data_blk_lpos, next); VMCOREINFO_STRUCT_SIZE(printk_info); VMCOREINFO_OFFSET(printk_info, seq); VMCOREINFO_OFFSET(printk_info, ts_nsec); VMCOREINFO_OFFSET(printk_info, text_len); VMCOREINFO_OFFSET(printk_info, caller_id); VMCOREINFO_OFFSET(printk_info, dev_info); VMCOREINFO_STRUCT_SIZE(dev_printk_info); VMCOREINFO_OFFSET(dev_printk_info, subsystem); VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); VMCOREINFO_OFFSET(dev_printk_info, device); VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); VMCOREINFO_STRUCT_SIZE(prb_data_ring); VMCOREINFO_OFFSET(prb_data_ring, size_bits); VMCOREINFO_OFFSET(prb_data_ring, data); VMCOREINFO_OFFSET(prb_data_ring, head_lpos); VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); } #endif /* requested log_buf_len from kernel cmdline */ static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ static void __init log_buf_len_update(u64 size) { if (size > (u64)LOG_BUF_LEN_MAX) { size = (u64)LOG_BUF_LEN_MAX; pr_err("log_buf over 2G is not supported.\n"); } if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { u64 size; if (!str) return -EINVAL; size = memparse(str, &str); log_buf_len_update(size); return 0; } early_param("log_buf_len", log_buf_len_setup); #ifdef CONFIG_SMP #define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) static void __init log_buf_add_cpu(void) { unsigned int cpu_extra; /* * archs should set up cpu_possible_bits properly with * set_cpu_possible() after setup_arch() but just in * case lets ensure this is valid. */ if (num_possible_cpus() == 1) return; cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; /* by default this will only continue through for large > 64 CPUs */ if (cpu_extra <= __LOG_BUF_LEN / 2) return; pr_info("log_buf_len individual max cpu contribution: %d bytes\n", __LOG_CPU_MAX_BUF_LEN); pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", cpu_extra); pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); log_buf_len_update(cpu_extra + __LOG_BUF_LEN); } #else /* !CONFIG_SMP */ static inline void log_buf_add_cpu(void) {} #endif /* CONFIG_SMP */ static void __init set_percpu_data_ready(void) { printk_safe_init(); /* Make sure we set this flag only after printk_safe() init is done */ barrier(); __printk_percpu_data_ready = true; } static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_reserved_entry e; struct printk_record dest_r; prb_rec_init_wr(&dest_r, r->info->text_len); if (!prb_reserve(&e, rb, &dest_r)) return 0; memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); dest_r.info->text_len = r->info->text_len; dest_r.info->facility = r->info->facility; dest_r.info->level = r->info->level; dest_r.info->flags = r->info->flags; dest_r.info->ts_nsec = r->info->ts_nsec; dest_r.info->caller_id = r->info->caller_id; memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); prb_final_commit(&e); return prb_record_text_space(&e); } static char setup_text_buf[LOG_LINE_MAX] __initdata; void __init setup_log_buf(int early) { struct printk_info *new_infos; unsigned int new_descs_count; struct prb_desc *new_descs; struct printk_info info; struct printk_record r; size_t new_descs_size; size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very * early, e.g. from setup_arch(), and second - when percpu_areas * are initialised. */ if (!early) set_percpu_data_ready(); if (log_buf != __log_buf) return; if (!early && !new_log_buf_len) log_buf_add_cpu(); if (!new_log_buf_len) return; new_descs_count = new_log_buf_len >> PRB_AVGBITS; if (new_descs_count == 0) { pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); return; } new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { pr_err("log_buf_len: %lu text bytes not available\n", new_log_buf_len); return; } new_descs_size = new_descs_count * sizeof(struct prb_desc); new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); if (unlikely(!new_descs)) { pr_err("log_buf_len: %zu desc bytes not available\n", new_descs_size); goto err_free_log_buf; } new_infos_size = new_descs_count * sizeof(struct printk_info); new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); if (unlikely(!new_infos)) { pr_err("log_buf_len: %zu info bytes not available\n", new_infos_size); goto err_free_descs; } prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); prb_init(&printk_rb_dynamic, new_log_buf, ilog2(new_log_buf_len), new_descs, ilog2(new_descs_count), new_infos); logbuf_lock_irqsave(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; prb_for_each_record(0, &printk_rb_static, seq, &r) free -= add_to_rb(&printk_rb_dynamic, &r); /* * This is early enough that everything is still running on the * boot CPU and interrupts are disabled. So no new messages will * appear during the transition to the dynamic buffer. */ prb = &printk_rb_dynamic; logbuf_unlock_irqrestore(flags); if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); } pr_info("log_buf_len: %u bytes\n", log_buf_len); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); return; err_free_descs: memblock_free(__pa(new_descs), new_descs_size); err_free_log_buf: memblock_free(__pa(new_log_buf), new_log_buf_len); } static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = true; pr_info("debug: ignoring loglevel setting.\n"); return 0; } early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); static bool suppress_message_printing(int level) { return (level >= console_loglevel && !ignore_loglevel); } #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) { unsigned long lpj; lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ loops_per_msec = (unsigned long long)lpj / 1000 * HZ; get_option(&str, &boot_delay); if (boot_delay > 10 * 1000) boot_delay = 0; pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); return 0; } early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress_message_printing(level)) { return; } k = (unsigned long long)loops_per_msec * boot_delay; timeout = jiffies + msecs_to_jiffies(boot_delay); while (k) { k--; cpu_relax(); /* * use (volatile) jiffies to prevent * compiler reduction; loop termination via jiffies * is secondary and may or may not happen. */ if (time_after(jiffies, timeout)) break; touch_nmi_watchdog(); } } #else static inline void boot_delay_msec(int level) { } #endif static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); static size_t print_syslog(unsigned int level, char *buf) { return sprintf(buf, "<%u>", level); } static size_t print_time(u64 ts, char *buf) { unsigned long rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu]", (unsigned long)ts, rem_nsec / 1000); } #ifdef CONFIG_PRINTK_CALLER static size_t print_caller(u32 id, char *buf) { char caller[12]; snprintf(caller, sizeof(caller), "%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); return sprintf(buf, "[%6s]", caller); } #else #define print_caller(id, buf) 0 #endif static size_t info_print_prefix(const struct printk_info *info, bool syslog, bool time, char *buf) { size_t len = 0; if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len); len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; buf[len] = '\0'; } return len; } /* * Prepare the record for printing. The text is shifted within the given * buffer to avoid a need for another one. The following operations are * done: * * - Add prefix for each line. * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). * - Add a string terminator. * * Since the produced string is always terminated, the maximum possible * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added * prefixes and the newline. The terminator is not counted. The dropped * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) { size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; char prefix[PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; size_t len = 0; char *next; /* * If the message was truncated because the buffer was not large * enough, treat the available text as if it were the full text. */ if (text_len > buf_size) text_len = buf_size; prefix_len = info_print_prefix(r->info, syslog, time, prefix); /* * @text_len: bytes of unprocessed text * @line_len: bytes of current line _without_ newline * @text: pointer to beginning of current line * @len: number of bytes prepared in r->text_buf */ for (;;) { next = memchr(text, '\n', text_len); if (next) { line_len = next - text; } else { /* Drop truncated line(s). */ if (truncated) break; line_len = text_len; } /* * Truncate the text if there is not enough space to add the * prefix and a trailing newline and a terminator. */ if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ if (len + prefix_len + line_len + 1 + 1 > buf_size) break; text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); /* * Increment the prepared length to include the text and * prefix that were just moved+copied. Also increment for the * newline at the end of this line. If this is the last line, * there is no newline, but it will be added immediately below. */ len += prefix_len + line_len + 1; if (text_len == line_len) { /* * This is the last line. Add the trailing newline * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; } /* * Advance beyond the added prefix and the related line with * its newline. */ text += prefix_len + line_len + 1; /* * The remaining text has only decreased by the line with its * newline. * * Note that @text_len can become zero. It happens when @text * ended with a newline (either due to truncation or the * original string ending with "\n\n"). The loop is correctly * repeated and (if not truncated) an empty line with a prefix * will be prepared. */ text_len -= line_len + 1; } /* * If a buffer was provided, it will be terminated. Space for the * string terminator is guaranteed to be available. The terminator is * not counted in the return value. */ if (buf_size > 0) r->text_buf[len] = 0; return len; } static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { char prefix[PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); /* * Each line will be preceded with a prefix. The intermediate * newlines are already within the text, but a final trailing * newline will be added. */ return ((prefix_len * line_count) + info->text_len + 1); } static int syslog_print(char __user *buf, int size) { struct printk_info info; struct printk_record r; char *text; int len = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); while (size > 0) { size_t n; size_t skip; logbuf_lock_irq(); if (!prb_read_valid(prb, syslog_seq, &r)) { logbuf_unlock_irq(); break; } if (r.info->seq != syslog_seq) { /* message is gone, move to next valid one */ syslog_seq = r.info->seq; syslog_partial = 0; } /* * To keep reading/counting partial line consistent, * use printk_time value as of the beginning of a line. */ if (!syslog_partial) syslog_time = printk_time; skip = syslog_partial; n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; logbuf_unlock_irq(); if (!n) break; if (copy_to_user(buf, text + skip, n)) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; unsigned int line_count; struct printk_record r; char *text; int len = 0; u64 seq; bool time; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; logbuf_lock_irq(); /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ prb_for_each_info(clear_seq, prb, seq, &info, &line_count) len += get_record_print_text_size(&info, line_count, true, time); /* move first record forward until length fits into the buffer */ prb_for_each_info(clear_seq, prb, seq, &info, &line_count) { if (len <= size) break; len -= get_record_print_text_size(&info, line_count, true, time); } prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); len = 0; prb_for_each_record(seq, prb, seq, &r) { int textlen; textlen = record_print_text(&r, true, time); if (len + textlen > size) { seq--; break; } logbuf_unlock_irq(); if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; logbuf_lock_irq(); if (len < 0) break; } if (clear) clear_seq = seq; logbuf_unlock_irq(); kfree(text); return len; } static void syslog_clear(void) { logbuf_lock_irq(); clear_seq = prb_next_seq(prb); logbuf_unlock_irq(); } int do_syslog(int type, char __user *buf, int len, int source) { struct printk_info info; bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = wait_event_interruptible(log_wait, prb_read_valid(prb, syslog_seq, NULL)); if (error) return error; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: logbuf_lock_irq(); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ logbuf_unlock_irq(); return 0; } if (info.seq != syslog_seq) { /* messages are gone, move to first one */ syslog_seq = info.seq; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = prb_next_seq(prb) - syslog_seq; } else { bool time = syslog_partial ? syslog_time : printk_time; unsigned int line_count; u64 seq; prb_for_each_info(syslog_seq, prb, seq, &info, &line_count) { error += get_record_print_text_size(&info, line_count, true, time); time = printk_time; } error -= syslog_partial; } logbuf_unlock_irq(); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ static void console_lock_spinning_enable(void) { raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose the lock if there was a busy waiter. * They must not touch items synchronized by console_lock * in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ static int console_lock_spinning_disable_and_check(void) { int waiter; raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, _THIS_IP_); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); /* * Update @console_may_schedule for trylock because the previous * owner may have been schedulable. */ console_may_schedule = 0; return 1; } /* * Call the console drivers, asking them to write out * log_buf[start] to log_buf[end - 1]. * The console_lock must be held. */ static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) { static char dropped_text[64]; size_t dropped_len = 0; struct console *con; trace_console_rcuidle(text, len); if (!console_drivers) return; if (console_dropped) { dropped_len = snprintf(dropped_text, sizeof(dropped_text), "** %lu printk messages dropped **\n", console_dropped); console_dropped = 0; } for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; if (!(con->flags & CON_ENABLED)) continue; if (!con->write) continue; if (!cpu_online(smp_processor_id()) && !(con->flags & CON_ANYTIME)) continue; if (con->flags & CON_EXTENDED) con->write(con, ext_text, ext_len); else { if (dropped_len) con->write(con, dropped_text, dropped_len); con->write(con, text, len); } } } int printk_delay_msec __read_mostly; static inline void printk_delay(void) { if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : 0x80000000 + raw_smp_processor_id(); } static size_t log_output(int facility, int level, enum log_flags lflags, const struct dev_printk_info *dev_info, char *text, size_t text_len) { const u32 caller_id = printk_caller_id(); if (lflags & LOG_CONT) { struct prb_reserved_entry e; struct printk_record r; prb_rec_init_wr(&r, text_len); if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) { memcpy(&r.text_buf[r.info->text_len], text, text_len); r.info->text_len += text_len; if (lflags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); } else { prb_commit(&e); } return text_len; } } /* Store it in the record log */ return log_store(caller_id, facility, level, lflags, 0, dev_info, text, text_len); } /* Must be called under logbuf_lock. */ int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len; enum log_flags lflags = 0; /* * The printf needs to come first; we need the syslog * prefix which might be passed-in as a parameter. */ text_len = vscnprintf(text, sizeof(textbuf), fmt, args); /* mark and strip a trailing newline */ if (text_len && text[text_len-1] == '\n') { text_len--; lflags |= LOG_NEWLINE; } /* strip kernel syslog prefix and extract log level or control flags */ if (facility == 0) { int kern_level; while ((kern_level = printk_get_level(text)) != 0) { switch (kern_level) { case '0' ... '7': if (level == LOGLEVEL_DEFAULT) level = kern_level - '0'; break; case 'c': /* KERN_CONT */ lflags |= LOG_CONT; } text_len -= 2; text += 2; } } if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) lflags |= LOG_NEWLINE; return log_output(facility, level, lflags, dev_info, text, text_len); } asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { int printed_len; bool in_sched = false; unsigned long flags; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; in_sched = true; } boot_delay_msec(level); printk_delay(); /* This stops the holder of console_sem just where we want him */ logbuf_lock_irqsave(flags); printed_len = vprintk_store(facility, level, dev_info, fmt, args); logbuf_unlock_irqrestore(flags); /* If called from the scheduler, we can not call up(). */ if (!in_sched) { /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to * console */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); asmlinkage int vprintk(const char *fmt, va_list args) { return vprintk_func(fmt, args); } EXPORT_SYMBOL(vprintk); int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); /** * printk - print a kernel message * @fmt: format string * * This is printk(). It can be called from any context. We want it to work. * * We try to grab the console_lock. If we succeed, it's easy - we log the * output and call the console drivers. If we fail to get the semaphore, we * place the output into the log buffer and return. The current holder of * the console_sem will notice the new output in console_unlock(); and will * send it to the consoles before releasing the lock. * * One effect of this deferred printing is that code which calls printk() and * then changes console_loglevel may break. This is because console_loglevel * is inspected when the actual printing occurs. * * See also: * printf(3) * * See the vsnprintf() documentation for format string extensions over C99. */ asmlinkage __visible int printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_func(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(printk); #else /* CONFIG_PRINTK */ #define LOG_LINE_MAX 0 #define PREFIX_MAX 0 #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 static u64 syslog_seq; static u64 console_seq; static u64 exclusive_console_stop_seq; static unsigned long console_dropped; static size_t record_print_text(const struct printk_record *r, bool syslog, bool time) { return 0; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { return 0; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { return 0; } static void console_lock_spinning_enable(void) { } static int console_lock_spinning_disable_and_check(void) { return 0; } static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static int __add_preferred_console(char *name, int idx, char *options, char *brl_options, bool user_specified) { struct console_cmdline *c; int i; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { if (strcmp(c->name, name) == 0 && c->index == idx) { if (!brl_options) preferred_console = i; if (user_specified) c->user_specified = true; return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; strlcpy(c->name, name, sizeof(c->name)); c->options = options; c->user_specified = user_specified; braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */ char *s, *options, *brl_options = NULL; int idx; /* * console="" or console=null have been suggested as a way to * disable console output. Use ttynull that has been created * for exacly this purpose. */ if (str[0] == 0 || strcmp(str, "null") == 0) { __add_preferred_console("ttynull", 0, NULL, NULL, true); return 1; } if (_braille_console_setup(&str, &brl_options)) return 1; /* * Decode str into name, index, options. */ if (str[0] >= '0' && str[0] <= '9') { strcpy(buf, "ttyS"); strncpy(buf + 4, str, sizeof(buf) - 5); } else { strncpy(buf, str, sizeof(buf) - 1); } buf[sizeof(buf) - 1] = 0; options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strcpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strcpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if (isdigit(*s) || *s == ',') break; idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(buf, idx, options, brl_options, true); console_set_on_cmdline = 1; return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(char *name, int idx, char *options) { return __add_preferred_console(name, idx, options, NULL, false); } bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); /** * suspend_console - suspend the console subsystem * * This disables printk() while we go into suspend states */ void suspend_console(void) { if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); console_lock(); console_suspended = 1; up_console_sem(); } void resume_console(void) { if (!console_suspend_enabled) return; down_console_sem(); console_suspended = 0; console_unlock(); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { if (!cpuhp_tasks_frozen) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); } return 0; } /** * console_lock - lock the console system for exclusive use. * * Acquires a lock which guarantees that the caller has * exclusive access to the console system and the console_drivers list. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); down_console_sem(); if (console_suspended) return; console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to lock the console system for exclusive use. * * Try to acquire a lock which guarantees that the caller has exclusive * access to the console system and the console_drivers list. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { if (down_trylock_console_sem()) return 0; if (console_suspended) { up_console_sem(); return 0; } console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); /* * Check if we have any console that is capable of printing while cpu is * booting or shutting down. Requires console_sem. */ static int have_callable_console(void) { struct console *con; for_each_console(con) if ((con->flags & CON_ENABLED) && (con->flags & CON_ANYTIME)) return 1; return 0; } /* * Can we actually use the console at this time on this cpu? * * Console drivers may assume that per-cpu resources have been allocated. So * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't * call them until this CPU is officially up. */ static inline int can_use_console(void) { return cpu_online(raw_smp_processor_id()) || have_callable_console(); } /** * console_unlock - unlock the console system * * Releases the console_lock which the caller holds on the console system * and the console driver list. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock(); emits * the output prior to releasing the lock. * * If there is output waiting, we wake /dev/kmsg and syslog() users. * * console_unlock(); may be called from any context. */ void console_unlock(void) { static char ext_text[CONSOLE_EXT_LOG_MAX]; static char text[LOG_LINE_MAX + PREFIX_MAX]; unsigned long flags; bool do_cond_resched, retry; struct printk_info info; struct printk_record r; if (console_suspended) { up_console_sem(); return; } prb_rec_init_rd(&r, &info, text, sizeof(text)); /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. * * console_trylock() is not able to detect the preemptive * context reliably. Therefore the value must be stored before * and cleared after the "again" goto label. */ do_cond_resched = console_may_schedule; again: console_may_schedule = 0; /* * We released the console_sem lock, so we need to recheck if * cpu is online and (if not) is there at least one CON_ANYTIME * console. */ if (!can_use_console()) { console_locked = 0; up_console_sem(); return; } for (;;) { size_t ext_len = 0; size_t len; printk_safe_enter_irqsave(flags); raw_spin_lock(&logbuf_lock); skip: if (!prb_read_valid(prb, console_seq, &r)) break; if (console_seq != r.info->seq) { console_dropped += r.info->seq - console_seq; console_seq = r.info->seq; } if (suppress_message_printing(r.info->level)) { /* * Skip record we have buffered and already printed * directly to the console when we received it, and * record that has level above the console loglevel. */ console_seq++; goto skip; } /* Output to all consoles once old messages replayed. */ if (unlikely(exclusive_console && console_seq >= exclusive_console_stop_seq)) { exclusive_console = NULL; } /* * Handle extended console text first because later * record_print_text() will modify the record buffer in-place. */ if (nr_ext_console_drivers) { ext_len = info_print_ext_header(ext_text, sizeof(ext_text), r.info); ext_len += msg_print_ext_body(ext_text + ext_len, sizeof(ext_text) - ext_len, &r.text_buf[0], r.info->text_len, &r.info->dev_info); } len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); console_seq++; raw_spin_unlock(&logbuf_lock); /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. */ console_lock_spinning_enable(); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(ext_text, ext_len, text, len); start_critical_timings(); if (console_lock_spinning_disable_and_check()) { printk_safe_exit_irqrestore(flags); return; } printk_safe_exit_irqrestore(flags); if (do_cond_resched) cond_resched(); } console_locked = 0; raw_spin_unlock(&logbuf_lock); up_console_sem(); /* * Someone could have filled up the buffer again, so re-check if there's * something to flush. In case we cannot trylock the console_sem again, * there's a new owner and the console_unlock() from them will do the * flush, no worries. */ raw_spin_lock(&logbuf_lock); retry = prb_read_valid(prb, console_seq, NULL); raw_spin_unlock(&logbuf_lock); printk_safe_exit_irqrestore(flags); if (retry && console_trylock()) goto again; } EXPORT_SYMBOL(console_unlock); /** * console_conditional_schedule - yield the CPU if required * * If the console code is currently allowed to sleep, and * if this CPU should yield the CPU to another task, do * so here. * * Must be called within console_lock();. */ void __sched console_conditional_schedule(void) { if (console_may_schedule) cond_resched(); } EXPORT_SYMBOL(console_conditional_schedule); void console_unblank(void) { struct console *c; /* * console_unblank can no longer be called in interrupt context unless * oops_in_progress is set to 1.. */ if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; for_each_console(c) if ((c->flags & CON_ENABLED) && c->unblank) c->unblank(); console_unlock(); } /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(enum con_flush_mode mode) { /* * If someone else is holding the console lock, trylock will fail * and may_schedule may be set. Ignore and proceed to unlock so * that messages are flushed out. As this can be called from any * context and we don't want to get preempted while flushing, * ensure may_schedule is cleared. */ console_trylock(); console_may_schedule = 0; if (mode == CONSOLE_REPLAY_ALL) { unsigned long flags; logbuf_lock_irqsave(flags); console_seq = prb_first_valid_seq(prb); logbuf_unlock_irqrestore(flags); } console_unlock(); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; console_lock(); for_each_console(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can disable console output before suspending a port, and can * re-enable output afterwards. */ void console_stop(struct console *console) { console_lock(); console->flags &= ~CON_ENABLED; console_unlock(); } EXPORT_SYMBOL(console_stop); void console_start(struct console *console) { console_lock(); console->flags |= CON_ENABLED; console_unlock(); } EXPORT_SYMBOL(console_start); static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); static int console_call_setup(struct console *newcon, char *options) { int err; if (!newcon->setup) return 0; /* Synchronize with possible boot console. */ console_lock(); err = newcon->setup(newcon, options); console_unlock(); return err; } /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected * by either the command line or add_preferred_console() and * setup/enable it. * * Care need to be taken with consoles that are statically * enabled such as netconsole */ static int try_enable_preferred_console(struct console *newcon, bool user_specified) { struct console_cmdline *c; int i, err; for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { if (c->user_specified != user_specified) continue; if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return 0; err = console_call_setup(newcon, c->options); if (err) return err; } newcon->flags |= CON_ENABLED; if (i == preferred_console) { newcon->flags |= CON_CONSDEV; has_preferred_console = true; } return 0; } /* * Some consoles, such as pstore and netconsole, can be enabled even * without matching. Accept the pre-enabled consoles only when match() * and setup() had a chance to be called. */ if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) return 0; return -ENOENT; } /* Try to enable the console unconditionally */ static void try_enable_default_console(struct console *newcon) { if (newcon->index < 0) newcon->index = 0; if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; if (newcon->device) { newcon->flags |= CON_CONSDEV; has_preferred_console = true; } } /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { unsigned long flags; struct console *bcon = NULL; int err; for_each_console(bcon) { if (WARN(bcon == newcon, "console '%s%d' already registered\n", bcon->name, bcon->index)) return; } /* * before we register a new CON_BOOT console, make sure we don't * already have a valid console */ if (newcon->flags & CON_BOOT) { for_each_console(bcon) { if (!(bcon->flags & CON_BOOT)) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); return; } } } if (console_drivers && console_drivers->flags & CON_BOOT) bcon = console_drivers; if (!has_preferred_console || bcon || !console_drivers) has_preferred_console = preferred_console >= 0; /* * See if we want to use this console driver. If we * didn't select a console we take the first one * that registers here. */ if (!has_preferred_console) try_enable_default_console(newcon); /* See if this console matches one we selected on the command line */ err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) return; /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) newcon->flags &= ~CON_PRINTBUFFER; /* * Put this console in the list - keep the * preferred driver at the head of the list. */ console_lock(); if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) { newcon->next = console_drivers; console_drivers = newcon; if (newcon->next) newcon->next->flags &= ~CON_CONSDEV; /* Ensure this flag is always set for the head of the list */ newcon->flags |= CON_CONSDEV; } else { newcon->next = console_drivers->next; console_drivers->next = newcon; } if (newcon->flags & CON_EXTENDED) nr_ext_console_drivers++; if (newcon->flags & CON_PRINTBUFFER) { /* * console_unlock(); will print out the buffered messages * for us. */ logbuf_lock_irqsave(flags); /* * We're about to replay the log buffer. Only do this to the * just-registered console to avoid excessive message spam to * the already-registered consoles. * * Set exclusive_console with disabled interrupts to reduce * race window with eventual console_flush_on_panic() that * ignores console_lock. */ exclusive_console = newcon; exclusive_console_stop_seq = console_seq; console_seq = syslog_seq; logbuf_unlock_irqrestore(flags); } console_unlock(); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ pr_info("%sconsole [%s%d] enabled\n", (newcon->flags & CON_BOOT) ? "boot" : "" , newcon->name, newcon->index); if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { /* We need to iterate through all boot consoles, to make * sure we print everything out, before we unregister them. */ for_each_console(bcon) if (bcon->flags & CON_BOOT) unregister_console(bcon); } } EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { struct console *con; int res; pr_info("%sconsole [%s%d] disabled\n", (console->flags & CON_BOOT) ? "boot" : "" , console->name, console->index); res = _braille_unregister_console(console); if (res < 0) return res; if (res > 0) return 0; res = -ENODEV; console_lock(); if (console_drivers == console) { console_drivers=console->next; res = 0; } else { for_each_console(con) { if (con->next == console) { con->next = console->next; res = 0; break; } } } if (res) goto out_disable_unlock; if (console->flags & CON_EXTENDED) nr_ext_console_drivers--; /* * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. */ if (console_drivers != NULL && console->flags & CON_CONSDEV) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; console_unlock(); console_sysfs_notify(); if (console->exit) res = console->exit(console); return res; out_disable_unlock: console->flags &= ~CON_ENABLED; console_unlock(); return res; } EXPORT_SYMBOL(unregister_console); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistred when the real preferred console is registered. */ static int __init printk_late_init(void) { struct console *con; int ret; for_each_console(con) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console(con); } } ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = __this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { .func = wake_up_klogd_work_func, .flags = ATOMIC_INIT(IRQ_WORK_LAZY), }; void wake_up_klogd(void) { if (!printk_percpu_data_ready()) return; preempt_disable(); if (waitqueue_active(&log_wait)) { this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } void defer_console_output(void) { if (!printk_percpu_data_ready()) return; preempt_disable(); __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); preempt_enable(); } int vprintk_deferred(const char *fmt, va_list args) { int r; r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); defer_console_output(); return r; } int printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) { switch (reason) { case KMSG_DUMP_PANIC: return "Panic"; case KMSG_DUMP_OOPS: return "Oops"; case KMSG_DUMP_EMERG: return "Emergency"; case KMSG_DUMP_SHUTDOWN: return "Shutdown"; default: return "Unknown"; } } EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump(enum kmsg_dump_reason reason) { struct kmsg_dumper *dumper; unsigned long flags; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { enum kmsg_dump_reason max_reason = dumper->max_reason; /* * If client has not provided a specific max_reason, default * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. */ if (max_reason == KMSG_DUMP_UNDEF) { max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : KMSG_DUMP_OOPS; } if (reason > max_reason) continue; /* initialize iterator with data about the stored records */ dumper->active = true; logbuf_lock_irqsave(flags); dumper->cur_seq = clear_seq; dumper->next_seq = prb_next_seq(prb); logbuf_unlock_irqrestore(flags); /* invoke dumper which will iterate over records */ dumper->dump(dumper, reason); /* reset iterator */ dumper->active = false; } rcu_read_unlock(); } /** * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. * * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; prb_rec_init_rd(&r, &info, line, size); if (!dumper->active) goto out; /* Read text or count text lines? */ if (line) { if (!prb_read_valid(prb, dumper->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { if (!prb_read_valid_info(prb, dumper->cur_seq, &info, &line_count)) { goto out; } l = get_record_print_text_size(&info, line_count, syslog, printk_time); } dumper->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } /** * kmsg_dump_get_line - retrieve one kmsg log line * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { unsigned long flags; bool ret; logbuf_lock_irqsave(flags); ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); logbuf_unlock_irqrestore(flags); return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, char *buf, size_t size, size_t *len) { struct printk_info info; unsigned int line_count; struct printk_record r; unsigned long flags; u64 seq; u64 next_seq; size_t l = 0; bool ret = false; bool time = printk_time; prb_rec_init_rd(&r, &info, buf, size); if (!dumper->active || !buf || !size) goto out; logbuf_lock_irqsave(flags); if (prb_read_valid_info(prb, dumper->cur_seq, &info, NULL)) { if (info.seq != dumper->cur_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = info.seq; } } /* last entry */ if (dumper->cur_seq >= dumper->next_seq) { logbuf_unlock_irqrestore(flags); goto out; } /* calculate length of entire buffer */ seq = dumper->cur_seq; while (prb_read_valid_info(prb, seq, &info, &line_count)) { if (r.info->seq >= dumper->next_seq) break; l += get_record_print_text_size(&info, line_count, syslog, time); seq = r.info->seq + 1; } /* move first record forward until length fits into the buffer */ seq = dumper->cur_seq; while (l >= size && prb_read_valid_info(prb, seq, &info, &line_count)) { if (r.info->seq >= dumper->next_seq) break; l -= get_record_print_text_size(&info, line_count, syslog, time); seq = r.info->seq + 1; } /* last message in next interation */ next_seq = seq; /* actually read text into the buffer now */ l = 0; while (prb_read_valid(prb, seq, &r)) { if (r.info->seq >= dumper->next_seq) break; l += record_print_text(&r, syslog, time); /* adjust record to store to remaining buffer space */ prb_rec_init_rd(&r, &info, buf + l, size - l); seq = r.info->seq + 1; } dumper->next_seq = next_seq; ret = true; logbuf_unlock_irqrestore(flags); out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind_nolock - reset the iterator (unlocked version) * @dumper: registered kmsg dumper * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. * * The function is similar to kmsg_dump_rewind(), but grabs no locks. */ void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) { dumper->cur_seq = clear_seq; dumper->next_seq = prb_next_seq(prb); } /** * kmsg_dump_rewind - reset the iterator * @dumper: registered kmsg dumper * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dumper *dumper) { unsigned long flags; logbuf_lock_irqsave(flags); kmsg_dump_rewind_nolock(dumper); logbuf_unlock_irqrestore(flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the kernel access vector cache (AVC). * * Authors: Stephen Smalley, <sds@tycho.nsa.gov> * James Morris <jmorris@redhat.com> * * Update: KaiGai, Kohei <kaigai@ak.jp.nec.com> * Replaced the avc_lock spinlock by RCU. * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/dcache.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/percpu.h> #include <linux/list.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/ip.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include "avc.h" #include "avc_ss.h" #include "classmap.h" #define CREATE_TRACE_POINTS #include <trace/events/avc.h> #define AVC_CACHE_SLOTS 512 #define AVC_DEF_CACHE_THRESHOLD 512 #define AVC_CACHE_RECLAIM 16 #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS #define avc_cache_stats_incr(field) this_cpu_inc(avc_cache_stats.field) #else #define avc_cache_stats_incr(field) do {} while (0) #endif struct avc_entry { u32 ssid; u32 tsid; u16 tclass; struct av_decision avd; struct avc_xperms_node *xp_node; }; struct avc_node { struct avc_entry ae; struct hlist_node list; /* anchored in avc_cache->slots[i] */ struct rcu_head rhead; }; struct avc_xperms_decision_node { struct extended_perms_decision xpd; struct list_head xpd_list; /* list of extended_perms_decision */ }; struct avc_xperms_node { struct extended_perms xp; struct list_head xpd_head; /* list head of extended_perms_decision */ }; struct avc_cache { struct hlist_head slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */ spinlock_t slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */ atomic_t lru_hint; /* LRU hint for reclaim scan */ atomic_t active_nodes; u32 latest_notif; /* latest revocation notification */ }; struct avc_callback_node { int (*callback) (u32 event); u32 events; struct avc_callback_node *next; }; #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 }; #endif struct selinux_avc { unsigned int avc_cache_threshold; struct avc_cache avc_cache; }; static struct selinux_avc selinux_avc; void selinux_avc_init(struct selinux_avc **avc) { int i; selinux_avc.avc_cache_threshold = AVC_DEF_CACHE_THRESHOLD; for (i = 0; i < AVC_CACHE_SLOTS; i++) { INIT_HLIST_HEAD(&selinux_avc.avc_cache.slots[i]); spin_lock_init(&selinux_avc.avc_cache.slots_lock[i]); } atomic_set(&selinux_avc.avc_cache.active_nodes, 0); atomic_set(&selinux_avc.avc_cache.lru_hint, 0); *avc = &selinux_avc; } unsigned int avc_get_cache_threshold(struct selinux_avc *avc) { return avc->avc_cache_threshold; } void avc_set_cache_threshold(struct selinux_avc *avc, unsigned int cache_threshold) { avc->avc_cache_threshold = cache_threshold; } static struct avc_callback_node *avc_callbacks; static struct kmem_cache *avc_node_cachep; static struct kmem_cache *avc_xperms_data_cachep; static struct kmem_cache *avc_xperms_decision_cachep; static struct kmem_cache *avc_xperms_cachep; static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass) { return (ssid ^ (tsid<<2) ^ (tclass<<4)) & (AVC_CACHE_SLOTS - 1); } /** * avc_init - Initialize the AVC. * * Initialize the access vector cache. */ void __init avc_init(void) { avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node), 0, SLAB_PANIC, NULL); avc_xperms_cachep = kmem_cache_create("avc_xperms_node", sizeof(struct avc_xperms_node), 0, SLAB_PANIC, NULL); avc_xperms_decision_cachep = kmem_cache_create( "avc_xperms_decision_node", sizeof(struct avc_xperms_decision_node), 0, SLAB_PANIC, NULL); avc_xperms_data_cachep = kmem_cache_create("avc_xperms_data", sizeof(struct extended_perms_data), 0, SLAB_PANIC, NULL); } int avc_get_hash_stats(struct selinux_avc *avc, char *page) { int i, chain_len, max_chain_len, slots_used; struct avc_node *node; struct hlist_head *head; rcu_read_lock(); slots_used = 0; max_chain_len = 0; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc->avc_cache.slots[i]; if (!hlist_empty(head)) { slots_used++; chain_len = 0; hlist_for_each_entry_rcu(node, head, list) chain_len++; if (chain_len > max_chain_len) max_chain_len = chain_len; } } rcu_read_unlock(); return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", atomic_read(&avc->avc_cache.active_nodes), slots_used, AVC_CACHE_SLOTS, max_chain_len); } /* * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver, struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { if (xpd_node->xpd.driver == driver) return &xpd_node->xpd; } return NULL; } static inline unsigned int avc_xperms_has_perm(struct extended_perms_decision *xpd, u8 perm, u8 which) { unsigned int rc = 0; if ((which == XPERMS_ALLOWED) && (xpd->used & XPERMS_ALLOWED)) rc = security_xperm_test(xpd->allowed->p, perm); else if ((which == XPERMS_AUDITALLOW) && (xpd->used & XPERMS_AUDITALLOW)) rc = security_xperm_test(xpd->auditallow->p, perm); else if ((which == XPERMS_DONTAUDIT) && (xpd->used & XPERMS_DONTAUDIT)) rc = security_xperm_test(xpd->dontaudit->p, perm); return rc; } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, u8 driver, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); xpd = avc_xperms_decision_lookup(driver, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } static void avc_xperms_decision_free(struct avc_xperms_decision_node *xpd_node) { struct extended_perms_decision *xpd; xpd = &xpd_node->xpd; if (xpd->allowed) kmem_cache_free(avc_xperms_data_cachep, xpd->allowed); if (xpd->auditallow) kmem_cache_free(avc_xperms_data_cachep, xpd->auditallow); if (xpd->dontaudit) kmem_cache_free(avc_xperms_data_cachep, xpd->dontaudit); kmem_cache_free(avc_xperms_decision_cachep, xpd_node); } static void avc_xperms_free(struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node, *tmp; if (!xp_node) return; list_for_each_entry_safe(xpd_node, tmp, &xp_node->xpd_head, xpd_list) { list_del(&xpd_node->xpd_list); avc_xperms_decision_free(xpd_node); } kmem_cache_free(avc_xperms_cachep, xp_node); } static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) memcpy(dest->allowed->p, src->allowed->p, sizeof(src->allowed->p)); if (dest->used & XPERMS_AUDITALLOW) memcpy(dest->auditallow->p, src->auditallow->p, sizeof(src->auditallow->p)); if (dest->used & XPERMS_DONTAUDIT) memcpy(dest->dontaudit->p, src->dontaudit->p, sizeof(src->dontaudit->p)); } /* * similar to avc_copy_xperms_decision, but only copy decision * information relevant to this perm */ static inline void avc_quick_copy_xperms_decision(u8 perm, struct extended_perms_decision *dest, struct extended_perms_decision *src) { /* * compute index of the u32 of the 256 bits (8 u32s) that contain this * command permission */ u8 i = perm >> 5; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; if (dest->used & XPERMS_AUDITALLOW) dest->auditallow->p[i] = src->auditallow->p[i]; if (dest->used & XPERMS_DONTAUDIT) dest->dontaudit->p[i] = src->dontaudit->p[i]; } static struct avc_xperms_decision_node *avc_xperms_decision_alloc(u8 which) { struct avc_xperms_decision_node *xpd_node; struct extended_perms_decision *xpd; xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd_node) return NULL; xpd = &xpd_node->xpd; if (which & XPERMS_ALLOWED) { xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->allowed) goto error; } if (which & XPERMS_AUDITALLOW) { xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->auditallow) goto error; } if (which & XPERMS_DONTAUDIT) { xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->dontaudit) goto error; } return xpd_node; error: avc_xperms_decision_free(xpd_node); return NULL; } static int avc_add_xperms_decision(struct avc_node *node, struct extended_perms_decision *src) { struct avc_xperms_decision_node *dest_xpd; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); node->ae.xp_node->xp.len++; return 0; } static struct avc_xperms_node *avc_xperms_alloc(void) { struct avc_xperms_node *xp_node; xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xp_node) return xp_node; INIT_LIST_HEAD(&xp_node->xpd_head); return xp_node; } static int avc_xperms_populate(struct avc_node *node, struct avc_xperms_node *src) { struct avc_xperms_node *dest; struct avc_xperms_decision_node *dest_xpd; struct avc_xperms_decision_node *src_xpd; if (src->xp.len == 0) return 0; dest = avc_xperms_alloc(); if (!dest) return -ENOMEM; memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { dest_xpd = avc_xperms_decision_alloc(src_xpd->xpd.used); if (!dest_xpd) goto error; avc_copy_xperms_decision(&dest_xpd->xpd, &src_xpd->xpd); list_add(&dest_xpd->xpd_list, &dest->xpd_head); } node->ae.xp_node = dest; return 0; error: avc_xperms_free(dest); return -ENOMEM; } static inline u32 avc_xperms_audit_required(u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; if (audited && xpd) { if (avc_xperms_has_perm(xpd, perm, XPERMS_DONTAUDIT)) audited &= ~requested; } } else if (result) { audited = denied = requested; } else { audited = requested & avd->auditallow; if (audited && xpd) { if (!avc_xperms_has_perm(xpd, perm, XPERMS_AUDITALLOW)) audited &= ~requested; } } *deniedp = denied; return audited; } static inline int avc_xperms_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, struct common_audit_data *ad) { u32 audited, denied; audited = avc_xperms_audit_required( requested, avd, xpd, perm, result, &denied); if (likely(!audited)) return 0; return slow_avc_audit(state, ssid, tsid, tclass, requested, audited, denied, result, ad); } static void avc_node_free(struct rcu_head *rhead) { struct avc_node *node = container_of(rhead, struct avc_node, rhead); avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); } static void avc_node_delete(struct selinux_avc *avc, struct avc_node *node) { hlist_del_rcu(&node->list); call_rcu(&node->rhead, avc_node_free); atomic_dec(&avc->avc_cache.active_nodes); } static void avc_node_kill(struct selinux_avc *avc, struct avc_node *node) { avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); atomic_dec(&avc->avc_cache.active_nodes); } static void avc_node_replace(struct selinux_avc *avc, struct avc_node *new, struct avc_node *old) { hlist_replace_rcu(&old->list, &new->list); call_rcu(&old->rhead, avc_node_free); atomic_dec(&avc->avc_cache.active_nodes); } static inline int avc_reclaim_node(struct selinux_avc *avc) { struct avc_node *node; int hvalue, try, ecx; unsigned long flags; struct hlist_head *head; spinlock_t *lock; for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) { hvalue = atomic_inc_return(&avc->avc_cache.lru_hint) & (AVC_CACHE_SLOTS - 1); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; if (!spin_trylock_irqsave(lock, flags)) continue; rcu_read_lock(); hlist_for_each_entry(node, head, list) { avc_node_delete(avc, node); avc_cache_stats_incr(reclaims); ecx++; if (ecx >= AVC_CACHE_RECLAIM) { rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); goto out; } } rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); } out: return ecx; } static struct avc_node *avc_alloc_node(struct selinux_avc *avc) { struct avc_node *node; node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!node) goto out; INIT_HLIST_NODE(&node->list); avc_cache_stats_incr(allocations); if (atomic_inc_return(&avc->avc_cache.active_nodes) > avc->avc_cache_threshold) avc_reclaim_node(avc); out: return node; } static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { node->ae.ssid = ssid; node->ae.tsid = tsid; node->ae.tclass = tclass; memcpy(&node->ae.avd, avd, sizeof(node->ae.avd)); } static inline struct avc_node *avc_search_node(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node, *ret = NULL; int hvalue; struct hlist_head *head; hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; hlist_for_each_entry_rcu(node, head, list) { if (ssid == node->ae.ssid && tclass == node->ae.tclass && tsid == node->ae.tsid) { ret = node; break; } } return ret; } /** * avc_lookup - Look up an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * * Look up an AVC entry that is valid for the * (@ssid, @tsid), interpreting the permissions * based on @tclass. If a valid AVC entry exists, * then this function returns the avc_node. * Otherwise, this function returns NULL. */ static struct avc_node *avc_lookup(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node; avc_cache_stats_incr(lookups); node = avc_search_node(avc, ssid, tsid, tclass); if (node) return node; avc_cache_stats_incr(misses); return NULL; } static int avc_latest_notif_update(struct selinux_avc *avc, int seqno, int is_insert) { int ret = 0; static DEFINE_SPINLOCK(notif_lock); unsigned long flag; spin_lock_irqsave(¬if_lock, flag); if (is_insert) { if (seqno < avc->avc_cache.latest_notif) { pr_warn("SELinux: avc: seqno %d < latest_notif %d\n", seqno, avc->avc_cache.latest_notif); ret = -EAGAIN; } } else { if (seqno > avc->avc_cache.latest_notif) avc->avc_cache.latest_notif = seqno; } spin_unlock_irqrestore(¬if_lock, flag); return ret; } /** * avc_insert - Insert an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @avd: resulting av decision * @xp_node: resulting extended permissions * * Insert an AVC entry for the SID pair * (@ssid, @tsid) and class @tclass. * The access vectors and the sequence number are * normally provided by the security server in * response to a security_compute_av() call. If the * sequence number @avd->seqno is not less than the latest * revocation notification, then the function copies * the access vectors into a cache entry, returns * avc_node inserted. Otherwise, this function returns NULL. */ static struct avc_node *avc_insert(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { struct avc_node *pos, *node = NULL; int hvalue; unsigned long flag; spinlock_t *lock; struct hlist_head *head; if (avc_latest_notif_update(avc, avd->seqno, 1)) return NULL; node = avc_alloc_node(avc); if (!node) return NULL; avc_node_populate(node, ssid, tsid, tclass, avd); if (avc_xperms_populate(node, xp_node)) { avc_node_kill(avc, node); return NULL; } hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (pos->ae.ssid == ssid && pos->ae.tsid == tsid && pos->ae.tclass == tclass) { avc_node_replace(avc, node, pos); goto found; } } hlist_add_head_rcu(&node->list, head); found: spin_unlock_irqrestore(lock, flag); return node; } /** * avc_audit_pre_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_pre_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; u32 av = sad->audited; const char **perms; int i, perm; audit_log_format(ab, "avc: %s ", sad->denied ? "denied" : "granted"); if (av == 0) { audit_log_format(ab, " null"); return; } perms = secclass_map[sad->tclass-1].perms; audit_log_format(ab, " {"); i = 0; perm = 1; while (i < (sizeof(av) * 8)) { if ((perm & av) && perms[i]) { audit_log_format(ab, " %s", perms[i]); av &= ~perm; } i++; perm <<= 1; } if (av) audit_log_format(ab, " 0x%x", av); audit_log_format(ab, " } for "); } /** * avc_audit_post_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_post_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; char *scontext = NULL; char *tcontext = NULL; const char *tclass = NULL; u32 scontext_len; u32 tcontext_len; int rc; rc = security_sid_to_context(sad->state, sad->ssid, &scontext, &scontext_len); if (rc) audit_log_format(ab, " ssid=%d", sad->ssid); else audit_log_format(ab, " scontext=%s", scontext); rc = security_sid_to_context(sad->state, sad->tsid, &tcontext, &tcontext_len); if (rc) audit_log_format(ab, " tsid=%d", sad->tsid); else audit_log_format(ab, " tcontext=%s", tcontext); tclass = secclass_map[sad->tclass-1].name; audit_log_format(ab, " tclass=%s", tclass); if (sad->denied) audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1); trace_selinux_audited(sad, scontext, tcontext, tclass); kfree(tcontext); kfree(scontext); /* in case of invalid context report also the actual context string */ rc = security_sid_to_context_inval(sad->state, sad->ssid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " srawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } rc = security_sid_to_context_inval(sad->state, sad->tsid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " trawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } } /* This is the slow part of avc audit with big stack footprint */ noinline int slow_avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a) { struct common_audit_data stack_data; struct selinux_audit_data sad; if (WARN_ON(!tclass || tclass >= ARRAY_SIZE(secclass_map))) return -EINVAL; if (!a) { a = &stack_data; a->type = LSM_AUDIT_DATA_NONE; } sad.tclass = tclass; sad.requested = requested; sad.ssid = ssid; sad.tsid = tsid; sad.audited = audited; sad.denied = denied; sad.result = result; sad.state = state; a->selinux_audit_data = &sad; common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback); return 0; } /** * avc_add_callback - Register a callback for security events. * @callback: callback function * @events: security events * * Register a callback function for events in the set @events. * Returns %0 on success or -%ENOMEM if insufficient memory * exists to add the callback. */ int __init avc_add_callback(int (*callback)(u32 event), u32 events) { struct avc_callback_node *c; int rc = 0; c = kmalloc(sizeof(*c), GFP_KERNEL); if (!c) { rc = -ENOMEM; goto out; } c->callback = callback; c->events = events; c->next = avc_callbacks; avc_callbacks = c; out: return rc; } /** * avc_update_node Update an AVC entry * @event : Updating event * @perms : Permission mask bits * @ssid,@tsid,@tclass : identifier of an AVC entry * @seqno : sequence number when decision was made * @xpd: extended_perms_decision to be added to the node * @flags: the AVC_* flags, e.g. AVC_NONBLOCKING, AVC_EXTENDED_PERMS, or 0. * * if a valid AVC entry doesn't exist,this function returns -ENOENT. * if kmalloc() called internal returns NULL, this function returns -ENOMEM. * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ static int avc_update_node(struct selinux_avc *avc, u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, struct extended_perms_decision *xpd, u32 flags) { int hvalue, rc = 0; unsigned long flag; struct avc_node *pos, *node, *orig = NULL; struct hlist_head *head; spinlock_t *lock; /* * If we are in a non-blocking code path, e.g. VFS RCU walk, * then we must not add permissions to a cache entry * because we will not audit the denial. Otherwise, * during the subsequent blocking retry (e.g. VFS ref walk), we * will find the permissions already granted in the cache entry * and won't audit anything at all, leading to silent denials in * permissive mode that only appear when in enforcing mode. * * See the corresponding handling of MAY_NOT_BLOCK in avc_audit() * and selinux_inode_permission(). */ if (flags & AVC_NONBLOCKING) return 0; node = avc_alloc_node(avc); if (!node) { rc = -ENOMEM; goto out; } /* Lock the target slot */ hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (ssid == pos->ae.ssid && tsid == pos->ae.tsid && tclass == pos->ae.tclass && seqno == pos->ae.avd.seqno){ orig = pos; break; } } if (!orig) { rc = -ENOENT; avc_node_kill(avc, node); goto out_unlock; } /* * Copy and replace original node. */ avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd); if (orig->ae.xp_node) { rc = avc_xperms_populate(node, orig->ae.xp_node); if (rc) { avc_node_kill(avc, node); goto out_unlock; } } switch (event) { case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) avc_xperms_allow_perm(node->ae.xp_node, driver, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: node->ae.avd.allowed &= ~perms; break; case AVC_CALLBACK_AUDITALLOW_ENABLE: node->ae.avd.auditallow |= perms; break; case AVC_CALLBACK_AUDITALLOW_DISABLE: node->ae.avd.auditallow &= ~perms; break; case AVC_CALLBACK_AUDITDENY_ENABLE: node->ae.avd.auditdeny |= perms; break; case AVC_CALLBACK_AUDITDENY_DISABLE: node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: avc_add_xperms_decision(node, xpd); break; } avc_node_replace(avc, node, orig); out_unlock: spin_unlock_irqrestore(lock, flag); out: return rc; } /** * avc_flush - Flush the cache */ static void avc_flush(struct selinux_avc *avc) { struct hlist_head *head; struct avc_node *node; spinlock_t *lock; unsigned long flag; int i; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc->avc_cache.slots[i]; lock = &avc->avc_cache.slots_lock[i]; spin_lock_irqsave(lock, flag); /* * With preemptable RCU, the outer spinlock does not * prevent RCU grace periods from ending. */ rcu_read_lock(); hlist_for_each_entry(node, head, list) avc_node_delete(avc, node); rcu_read_unlock(); spin_unlock_irqrestore(lock, flag); } } /** * avc_ss_reset - Flush the cache and revalidate migrated permissions. * @seqno: policy sequence number */ int avc_ss_reset(struct selinux_avc *avc, u32 seqno) { struct avc_callback_node *c; int rc = 0, tmprc; avc_flush(avc); for (c = avc_callbacks; c; c = c->next) { if (c->events & AVC_CALLBACK_RESET) { tmprc = c->callback(AVC_CALLBACK_RESET); /* save the first error encountered for the return value and continue processing the callbacks */ if (!rc) rc = tmprc; } } avc_latest_notif_update(avc, seqno, 0); return rc; } /* * Slow-path helper function for avc_has_perm_noaudit, * when the avc_node lookup fails. We get called with * the RCU read lock held, and need to return with it * still held, but drop if for the security compute. * * Don't inline this, since it's the slow-path and just * results in a bigger stack frame. */ static noinline struct avc_node *avc_compute_av(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { rcu_read_unlock(); INIT_LIST_HEAD(&xp_node->xpd_head); security_compute_av(state, ssid, tsid, tclass, avd, &xp_node->xp); rcu_read_lock(); return avc_insert(state->avc, ssid, tsid, tclass, avd, xp_node); } static noinline int avc_denied(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 xperm, unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; if (enforcing_enabled(state) && !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; avc_update_node(state->avc, AVC_CALLBACK_GRANT, requested, driver, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } /* * The avc extended permissions logic adds an additional 256 bits of * permissions to an avc node when extended permissions for that node are * specified in the avtab. If the additional 256 permissions is not adequate, * as-is the case with ioctls, then multiple may be chained together and the * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 xperm, struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; u32 denied; struct extended_perms_decision local_xpd; struct extended_perms_decision *xpd = NULL; struct extended_perms_data allowed; struct extended_perms_data auditallow; struct extended_perms_data dontaudit; struct avc_xperms_node local_xp_node; struct avc_xperms_node *xp_node; int rc = 0, rc2; xp_node = &local_xp_node; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) { node = avc_compute_av(state, ssid, tsid, tclass, &avd, xp_node); } else { memcpy(&avd, &node->ae.avd, sizeof(avd)); xp_node = node->ae.xp_node; } /* if extended permissions are not defined, only consider av_decision */ if (!xp_node || !xp_node->xp.len) goto decision; local_xpd.allowed = &allowed; local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; xpd = avc_xperms_decision_lookup(driver, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver * is flagged */ if (!security_xperm_test(xp_node->xp.drivers.p, driver)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); security_compute_xperms_decision(state, ssid, tsid, tclass, driver, &local_xpd); rcu_read_lock(); avc_update_node(state->avc, AVC_CALLBACK_ADD_XPERMS, requested, driver, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); } xpd = &local_xpd; if (!avc_xperms_has_perm(xpd, xperm, XPERMS_ALLOWED)) avd.allowed &= ~requested; decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) rc = avc_denied(state, ssid, tsid, tclass, requested, driver, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); rc2 = avc_xperms_audit(state, ssid, tsid, tclass, requested, &avd, xpd, xperm, rc, ad); if (rc2) return rc2; return rc; } /** * avc_has_perm_noaudit - Check permissions but perform no auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @flags: AVC_STRICT, AVC_NONBLOCKING, or 0 * @avd: access vector decisions * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Return a copy of the decisions * in @avd. Return %0 if all @requested permissions are granted, * -%EACCES if any permissions are denied, or another -errno upon * other errors. This function is typically called by avc_has_perm(), * but may also be called directly to separate permission checking from * auditing, e.g. in cases where a lock must be held for the check but * should be released for the auditing. */ inline int avc_has_perm_noaudit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd) { struct avc_node *node; struct avc_xperms_node xp_node; int rc = 0; u32 denied; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) node = avc_compute_av(state, ssid, tsid, tclass, avd, &xp_node); else memcpy(avd, &node->ae.avd, sizeof(*avd)); denied = requested & ~(avd->allowed); if (unlikely(denied)) rc = avc_denied(state, ssid, tsid, tclass, requested, 0, 0, flags, avd); rcu_read_unlock(); return rc; } /** * avc_has_perm - Check permissions and perform any appropriate auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @auditdata: auxiliary audit data * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Audit the granting or denial of * permissions in accordance with the policy. Return %0 if all @requested * permissions are granted, -%EACCES if any permissions are denied, or * another -errno upon other errors. */ int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, 0, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, auditdata, 0); if (rc2) return rc2; return rc; } int avc_has_perm_flags(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata, int flags) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, (flags & MAY_NOT_BLOCK) ? AVC_NONBLOCKING : 0, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, auditdata, flags); if (rc2) return rc2; return rc; } u32 avc_policy_seqno(struct selinux_state *state) { return state->avc->avc_cache.latest_notif; } void avc_disable(void) { /* * If you are looking at this because you have realized that we are * not destroying the avc_node_cachep it might be easy to fix, but * I don't know the memory barrier semantics well enough to know. It's * possible that some other task dereferenced security_ops when * it still pointed to selinux operations. If that is the case it's * possible that it is about to use the avc and is about to need the * avc_node_cachep. I know I could wrap the security.c security_ops call * in an rcu_lock, but seriously, it's not worth it. Instead I just flush * the cache and get that memory back. */ if (avc_node_cachep) { avc_flush(selinux_state.avc); /* kmem_cache_destroy(avc_node_cachep); */ } } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 | /* * linux/drivers/block/loop.c * * Written by Theodore Ts'o, 3/29/93 * * Copyright 1993 by Theodore Ts'o. Redistribution of this file is * permitted under the GNU General Public License. * * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996 * * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996 * * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997 * * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998 * * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998 * * Loadable modules and other fixes by AK, 1998 * * Make real block number available to downstream transfer functions, enables * CBC (and relatives) mode encryption requiring unique IVs per data block. * Reed H. Petty, rhp@draper.net * * Maximum number of loop devices now dynamic via max_loop module parameter. * Russell Kroll <rkroll@exploits.org> 19990701 * * Maximum number of loop devices when compiled-in now selectable by passing * max_loop=<1-255> to the kernel on boot. * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 * * Completely rewrite request handling to be make_request_fn style and * non blocking, pushing work to a helper thread. Lots of fixes from * Al Viro too. * Jens Axboe <axboe@suse.de>, Nov 2000 * * Support up to 256 loop devices * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 * * Support for falling back on the write file operation when the address space * operations write_begin is not available on the backing filesystem. * Anton Altaparmakov, 16 Feb 2005 * * Still To Fix: * - Advisory locking is ignored here. * - Should use an own CAP_* category instead of CAP_SYS_ADMIN * */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> #include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/suspend.h> #include <linux/freezer.h> #include <linux/mutex.h> #include <linux/writeback.h> #include <linux/completion.h> #include <linux/highmem.h> #include <linux/kthread.h> #include <linux/splice.h> #include <linux/sysfs.h> #include <linux/miscdevice.h> #include <linux/falloc.h> #include <linux/uio.h> #include <linux/ioprio.h> #include <linux/blk-cgroup.h> #include "loop.h" #include <linux/uaccess.h> static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); static int max_part; static int part_shift; static int transfer_xor(struct loop_device *lo, int cmd, struct page *raw_page, unsigned raw_off, struct page *loop_page, unsigned loop_off, int size, sector_t real_block) { char *raw_buf = kmap_atomic(raw_page) + raw_off; char *loop_buf = kmap_atomic(loop_page) + loop_off; char *in, *out, *key; int i, keysize; if (cmd == READ) { in = raw_buf; out = loop_buf; } else { in = loop_buf; out = raw_buf; } key = lo->lo_encrypt_key; keysize = lo->lo_encrypt_key_size; for (i = 0; i < size; i++) *out++ = *in++ ^ key[(i & 511) % keysize]; kunmap_atomic(loop_buf); kunmap_atomic(raw_buf); cond_resched(); return 0; } static int xor_init(struct loop_device *lo, const struct loop_info64 *info) { if (unlikely(info->lo_encrypt_key_size <= 0)) return -EINVAL; return 0; } static struct loop_func_table none_funcs = { .number = LO_CRYPT_NONE, }; static struct loop_func_table xor_funcs = { .number = LO_CRYPT_XOR, .transfer = transfer_xor, .init = xor_init }; /* xfer_funcs[0] is special - its release function is never called */ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = { &none_funcs, &xor_funcs }; static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) { loff_t loopsize; /* Compute loopsize in bytes */ loopsize = i_size_read(file->f_mapping->host); if (offset > 0) loopsize -= offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; if (sizelimit > 0 && sizelimit < loopsize) loopsize = sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. */ return loopsize >> 9; } static loff_t get_loop_size(struct loop_device *lo, struct file *file) { return get_size(lo->lo_offset, lo->lo_sizelimit, file); } static void __loop_update_dio(struct loop_device *lo, bool dio) { struct file *file = lo->lo_backing_file; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; unsigned short sb_bsize = 0; unsigned dio_align = 0; bool use_dio; if (inode->i_sb->s_bdev) { sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev); dio_align = sb_bsize - 1; } /* * We support direct I/O only if lo_offset is aligned with the * logical I/O size of backing device, and the logical block * size of loop is bigger than the backing device's and the loop * needn't transform transfer. * * TODO: the above condition may be loosed in the future, and * direct I/O may be switched runtime at that time because most * of requests in sane applications should be PAGE_SIZE aligned */ if (dio) { if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && !(lo->lo_offset & dio_align) && mapping->a_ops->direct_IO && !lo->transfer) use_dio = true; else use_dio = false; } else { use_dio = false; } if (lo->use_dio == use_dio) return; /* flush dirty pages before changing direct IO */ vfs_fsync(file, 0); /* * The flag of LO_FLAGS_DIRECT_IO is handled similarly with * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup * will get updated by ioctl(LOOP_GET_STATUS) */ if (lo->lo_state == Lo_bound) blk_mq_freeze_queue(lo->lo_queue); lo->use_dio = use_dio; if (use_dio) { blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue); lo->lo_flags |= LO_FLAGS_DIRECT_IO; } else { blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; } if (lo->lo_state == Lo_bound) blk_mq_unfreeze_queue(lo->lo_queue); } /** * loop_set_size() - sets device size and notifies userspace * @lo: struct loop_device to set the size for * @size: new size of the loop device * * Callers must validate that the size passed into this function fits into * a sector_t, eg using loop_validate_size() */ static void loop_set_size(struct loop_device *lo, loff_t size) { if (!set_capacity_and_notify(lo->lo_disk, size)) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } static inline int lo_do_transfer(struct loop_device *lo, int cmd, struct page *rpage, unsigned roffs, struct page *lpage, unsigned loffs, int size, sector_t rblock) { int ret; ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock); if (likely(!ret)) return 0; printk_ratelimited(KERN_ERR "loop: Transfer error at byte offset %llu, length %i.\n", (unsigned long long)rblock << 9, size); return ret; } static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) { struct iov_iter i; ssize_t bw; iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); file_end_write(file); if (likely(bw == bvec->bv_len)) return 0; printk_ratelimited(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n", (unsigned long long)*ppos, bvec->bv_len); if (bw >= 0) bw = -EIO; return bw; } static int lo_write_simple(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec; struct req_iterator iter; int ret = 0; rq_for_each_segment(bvec, rq, iter) { ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos); if (ret < 0) break; cond_resched(); } return ret; } /* * This is the slow, transforming version that needs to double buffer the * data as it cannot do the transformations in place without having direct * access to the destination pages of the backing file. */ static int lo_write_transfer(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec, b; struct req_iterator iter; struct page *page; int ret = 0; page = alloc_page(GFP_NOIO); if (unlikely(!page)) return -ENOMEM; rq_for_each_segment(bvec, rq, iter) { ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page, bvec.bv_offset, bvec.bv_len, pos >> 9); if (unlikely(ret)) break; b.bv_page = page; b.bv_offset = 0; b.bv_len = bvec.bv_len; ret = lo_write_bvec(lo->lo_backing_file, &b, &pos); if (ret < 0) break; } __free_page(page); return ret; } static int lo_read_simple(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec; struct req_iterator iter; struct iov_iter i; ssize_t len; rq_for_each_segment(bvec, rq, iter) { iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; flush_dcache_page(bvec.bv_page); if (len != bvec.bv_len) { struct bio *bio; __rq_for_each_bio(bio, rq) zero_fill_bio(bio); break; } cond_resched(); } return 0; } static int lo_read_transfer(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec, b; struct req_iterator iter; struct iov_iter i; struct page *page; ssize_t len; int ret = 0; page = alloc_page(GFP_NOIO); if (unlikely(!page)) return -ENOMEM; rq_for_each_segment(bvec, rq, iter) { loff_t offset = pos; b.bv_page = page; b.bv_offset = 0; b.bv_len = bvec.bv_len; iov_iter_bvec(&i, READ, &b, 1, b.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) { ret = len; goto out_free_page; } ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page, bvec.bv_offset, len, offset >> 9); if (ret) goto out_free_page; flush_dcache_page(bvec.bv_page); if (len != bvec.bv_len) { struct bio *bio; __rq_for_each_bio(bio, rq) zero_fill_bio(bio); break; } } ret = 0; out_free_page: __free_page(page); return ret; } static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { /* * We use fallocate to manipulate the space mappings used by the image * a.k.a. discard/zerorange. However we do not support this if * encryption is enabled, because it may give an attacker useful * information. */ struct file *file = lo->lo_backing_file; struct request_queue *q = lo->lo_queue; int ret; mode |= FALLOC_FL_KEEP_SIZE; if (!blk_queue_discard(q)) { ret = -EOPNOTSUPP; goto out; } ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) ret = -EIO; out: return ret; } static int lo_req_flush(struct loop_device *lo, struct request *rq) { struct file *file = lo->lo_backing_file; int ret = vfs_fsync(file, 0); if (unlikely(ret && ret != -EINVAL)) ret = -EIO; return ret; } static void lo_complete_rq(struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); goto end_io; } /* * Short READ - if we got some data, advance our request and * retry it. If we got no data, end the rest with EIO. */ if (cmd->ret) { blk_update_request(rq, BLK_STS_OK, cmd->ret); cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { if (cmd->use_aio) { struct bio *bio = rq->bio; while (bio) { zero_fill_bio(bio); bio = bio->bi_next; } } ret = BLK_STS_IOERR; end_io: blk_mq_end_request(rq, ret); } } static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) { struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); if (cmd->css) css_put(cmd->css); cmd->ret = ret; lo_rw_aio_do_completion(cmd); } static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, loff_t pos, bool rw) { struct iov_iter iter; struct req_iterator rq_iter; struct bio_vec *bvec; struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; struct bio_vec tmp; unsigned int offset; int nr_bvec = 0; int ret; rq_for_each_bvec(tmp, rq, rq_iter) nr_bvec++; if (rq->bio != rq->biotail) { bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec), GFP_NOIO); if (!bvec) return -EIO; cmd->bvec = bvec; /* * The bios of the request may be started from the middle of * the 'bvec' because of bio splitting, so we can't directly * copy bio->bi_iov_vec to new bvec. The rq_for_each_bvec * API will take care of all details for us. */ rq_for_each_bvec(tmp, rq, rq_iter) { *bvec = tmp; bvec++; } bvec = cmd->bvec; offset = 0; } else { /* * Same here, this bio may be started from the middle of the * 'bvec' because of bio splitting, so offset from the bvec * must be passed to iov iterator */ offset = bio->bi_iter.bi_bvec_done; bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } atomic_set(&cmd->ref, 2); iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); if (cmd->css) kthread_associate_blkcg(cmd->css); if (rw == WRITE) ret = call_write_iter(file, &cmd->iocb, &iter); else ret = call_read_iter(file, &cmd->iocb, &iter); lo_rw_aio_do_completion(cmd); kthread_associate_blkcg(NULL); if (ret != -EIOCBQUEUED) cmd->iocb.ki_complete(&cmd->iocb, ret, 0); return 0; } static int do_req_filebacked(struct loop_device *lo, struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; /* * lo_write_simple and lo_read_simple should have been covered * by io submit style function like lo_rw_aio(), one blocker * is that lo_read_simple() need to call flush_dcache_page after * the page is written from kernel, and it isn't easy to handle * this in io submit style function which submits all segments * of the req at one time. And direct read IO doesn't need to * run flush_dcache_page(). */ switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); case REQ_OP_WRITE_ZEROES: /* * If the caller doesn't want deallocation, call zeroout to * write zeroes the range. Otherwise, punch them out. */ return lo_fallocate(lo, rq, pos, (rq->cmd_flags & REQ_NOUNMAP) ? FALLOC_FL_ZERO_RANGE : FALLOC_FL_PUNCH_HOLE); case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: if (lo->transfer) return lo_write_transfer(lo, rq, pos); else if (cmd->use_aio) return lo_rw_aio(lo, cmd, pos, WRITE); else return lo_write_simple(lo, rq, pos); case REQ_OP_READ: if (lo->transfer) return lo_read_transfer(lo, rq, pos); else if (cmd->use_aio) return lo_rw_aio(lo, cmd, pos, READ); else return lo_read_simple(lo, rq, pos); default: WARN_ON_ONCE(1); return -EIO; } } static inline void loop_update_dio(struct loop_device *lo) { __loop_update_dio(lo, (lo->lo_backing_file->f_flags & O_DIRECT) | lo->use_dio); } static void loop_reread_partitions(struct loop_device *lo, struct block_device *bdev) { int rc; mutex_lock(&bdev->bd_mutex); rc = bdev_disk_changed(bdev, false); mutex_unlock(&bdev->bd_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); } static inline int is_loop_device(struct file *file) { struct inode *i = file->f_mapping->host; return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR; } static int loop_validate_file(struct file *file, struct block_device *bdev) { struct inode *inode = file->f_mapping->host; struct file *f = file; /* Avoid recursion */ while (is_loop_device(f)) { struct loop_device *l; if (f->f_mapping->host->i_bdev == bdev) return -EBADF; l = f->f_mapping->host->i_bdev->bd_disk->private_data; if (l->lo_state != Lo_bound) { return -EINVAL; } f = l->lo_backing_file; } if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; return 0; } /* * loop_change_fd switched the backing store of a loopback device to * a new file. This is useful for operating system installers to free up * the original file and in High Availability environments to switch to * an alternative location for the content in case of server meltdown. * This can only work if the loop device is used read-only, and if the * new backing store is the same size and type as the old backing store. */ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { struct file *file = NULL, *old_file; int error; bool partscan; error = mutex_lock_killable(&loop_ctl_mutex); if (error) return error; error = -ENXIO; if (lo->lo_state != Lo_bound) goto out_err; /* the loop device has to be read-only */ error = -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) goto out_err; error = -EBADF; file = fget(arg); if (!file) goto out_err; error = loop_validate_file(file, bdev); if (error) goto out_err; old_file = lo->lo_backing_file; error = -EINVAL; /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) goto out_err; /* and ... switch */ blk_mq_freeze_queue(lo->lo_queue); mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping); mapping_set_gfp_mask(file->f_mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; mutex_unlock(&loop_ctl_mutex); /* * We must drop file reference outside of loop_ctl_mutex as dropping * the file ref can take bd_mutex which creates circular locking * dependency. */ fput(old_file); if (partscan) loop_reread_partitions(lo, bdev); return 0; out_err: mutex_unlock(&loop_ctl_mutex); if (file) fput(file); return error; } /* loop sysfs attributes */ static ssize_t loop_attr_show(struct device *dev, char *page, ssize_t (*callback)(struct loop_device *, char *)) { struct gendisk *disk = dev_to_disk(dev); struct loop_device *lo = disk->private_data; return callback(lo, page); } #define LOOP_ATTR_RO(_name) \ static ssize_t loop_attr_##_name##_show(struct loop_device *, char *); \ static ssize_t loop_attr_do_show_##_name(struct device *d, \ struct device_attribute *attr, char *b) \ { \ return loop_attr_show(d, b, loop_attr_##_name##_show); \ } \ static struct device_attribute loop_attr_##_name = \ __ATTR(_name, 0444, loop_attr_do_show_##_name, NULL); static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) { ssize_t ret; char *p = NULL; spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1); spin_unlock_irq(&lo->lo_lock); if (IS_ERR_OR_NULL(p)) ret = PTR_ERR(p); else { ret = strlen(p); memmove(buf, p, ret); buf[ret++] = '\n'; buf[ret] = 0; } return ret; } static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_offset); } static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit); } static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf) { int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR); return sysfs_emit(buf, "%s\n", autoclear ? "1" : "0"); } static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf) { int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN); return sysfs_emit(buf, "%s\n", partscan ? "1" : "0"); } static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf) { int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO); return sysfs_emit(buf, "%s\n", dio ? "1" : "0"); } LOOP_ATTR_RO(backing_file); LOOP_ATTR_RO(offset); LOOP_ATTR_RO(sizelimit); LOOP_ATTR_RO(autoclear); LOOP_ATTR_RO(partscan); LOOP_ATTR_RO(dio); static struct attribute *loop_attrs[] = { &loop_attr_backing_file.attr, &loop_attr_offset.attr, &loop_attr_sizelimit.attr, &loop_attr_autoclear.attr, &loop_attr_partscan.attr, &loop_attr_dio.attr, NULL, }; static struct attribute_group loop_attribute_group = { .name = "loop", .attrs= loop_attrs, }; static void loop_sysfs_init(struct loop_device *lo) { lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj, &loop_attribute_group); } static void loop_sysfs_exit(struct loop_device *lo) { if (lo->sysfs_inited) sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj, &loop_attribute_group); } static void loop_config_discard(struct loop_device *lo) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; u32 granularity, max_discard_sectors; /* * If the backing device is a block device, mirror its zeroing * capability. Set the discard sectors to the block device's zeroing * capabilities because loop discards result in blkdev_issue_zeroout(), * not blkdev_issue_discard(). This maintains consistent behavior with * file-backed loop devices: discarded regions read back as zero. */ if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) { struct request_queue *backingq; backingq = bdev_get_queue(inode->i_bdev); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; granularity = backingq->limits.discard_granularity ?: queue_physical_block_size(backingq); /* * We use punch hole to reclaim the free space used by the * image a.k.a. discard. However we do not support discard if * encryption is enabled, because it may give an attacker * useful information. */ } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) { max_discard_sectors = 0; granularity = 0; } else { max_discard_sectors = UINT_MAX >> 9; granularity = inode->i_sb->s_blocksize; } if (max_discard_sectors) { q->limits.discard_granularity = granularity; blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } else { q->limits.discard_granularity = 0; blk_queue_max_discard_sectors(q, 0); blk_queue_max_write_zeroes_sectors(q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } q->limits.discard_alignment = 0; } static void loop_unprepare_queue(struct loop_device *lo) { kthread_flush_worker(&lo->worker); kthread_stop(lo->worker_task); } static int loop_kthread_worker_fn(void *worker_ptr) { current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; return kthread_worker_fn(worker_ptr); } static int loop_prepare_queue(struct loop_device *lo) { kthread_init_worker(&lo->worker); lo->worker_task = kthread_run(loop_kthread_worker_fn, &lo->worker, "loop%d", lo->lo_number); if (IS_ERR(lo->worker_task)) return -ENOMEM; set_user_nice(lo->worker_task, MIN_NICE); return 0; } static void loop_update_rotational(struct loop_device *lo) { struct file *file = lo->lo_backing_file; struct inode *file_inode = file->f_mapping->host; struct block_device *file_bdev = file_inode->i_sb->s_bdev; struct request_queue *q = lo->lo_queue; bool nonrot = true; /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ if (file_bdev) nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); if (nonrot) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); } static int loop_release_xfer(struct loop_device *lo) { int err = 0; struct loop_func_table *xfer = lo->lo_encryption; if (xfer) { if (xfer->release) err = xfer->release(lo); lo->transfer = NULL; lo->lo_encryption = NULL; module_put(xfer->owner); } return err; } static int loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, const struct loop_info64 *i) { int err = 0; if (xfer) { struct module *owner = xfer->owner; if (!try_module_get(owner)) return -EINVAL; if (xfer->init) err = xfer->init(lo, i); if (err) module_put(owner); else lo->lo_encryption = xfer; } return err; } /** * loop_set_status_from_info - configure device from loop_info * @lo: struct loop_device to configure * @info: struct loop_info64 to configure the device with * * Configures the loop device parameters according to the passed * in loop_info64 configuration. */ static int loop_set_status_from_info(struct loop_device *lo, const struct loop_info64 *info) { int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; err = loop_release_xfer(lo); if (err) return err; if (info->lo_encrypt_type) { unsigned int type = info->lo_encrypt_type; if (type >= MAX_LO_CRYPT) return -EINVAL; xfer = xfer_funcs[type]; if (xfer == NULL) return -EINVAL; } else xfer = NULL; err = loop_init_xfer(lo, xfer, info); if (err) return err; /* Avoid assigning overflow values */ if (info->lo_offset > LLONG_MAX || info->lo_sizelimit > LLONG_MAX) return -EOVERFLOW; lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; lo->lo_crypt_name[LO_NAME_SIZE-1] = 0; if (!xfer) xfer = &none_funcs; lo->transfer = xfer->transfer; lo->ioctl = xfer->ioctl; lo->lo_flags = info->lo_flags; lo->lo_encrypt_key_size = info->lo_encrypt_key_size; lo->lo_init[0] = info->lo_init[0]; lo->lo_init[1] = info->lo_init[1]; if (info->lo_encrypt_key_size) { memcpy(lo->lo_encrypt_key, info->lo_encrypt_key, info->lo_encrypt_key_size); lo->lo_key_owner = uid; } return 0; } static int loop_configure(struct loop_device *lo, fmode_t mode, struct block_device *bdev, const struct loop_config *config) { struct file *file; struct inode *inode; struct address_space *mapping; struct block_device *claimed_bdev = NULL; int error; loff_t size; bool partscan; unsigned short bsize; /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); error = -EBADF; file = fget(config->fd); if (!file) goto out; /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { claimed_bdev = bdev->bd_contains; error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure); if (error) goto out_putf; } error = mutex_lock_killable(&loop_ctl_mutex); if (error) goto out_bdev; error = -EBUSY; if (lo->lo_state != Lo_unbound) goto out_unlock; error = loop_validate_file(file, bdev); if (error) goto out_unlock; mapping = file->f_mapping; inode = mapping->host; if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { error = -EINVAL; goto out_unlock; } if (config->block_size) { error = blk_validate_block_size(config->block_size); if (error) goto out_unlock; } error = loop_set_status_from_info(lo, &config->info); if (error) goto out_unlock; if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; error = loop_prepare_queue(lo); if (error) goto out_unlock; set_device_ro(bdev, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); if (config->block_size) bsize = config->block_size; else if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev) /* In case of direct I/O, match underlying block size */ bsize = bdev_logical_block_size(inode->i_sb->s_bdev); else bsize = 512; blk_queue_logical_block_size(lo->lo_queue, bsize); blk_queue_physical_block_size(lo->lo_queue, bsize); blk_queue_io_min(lo->lo_queue, bsize); loop_config_discard(lo); loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); size = get_loop_size(lo, file); loop_set_size(lo, size); set_blocksize(bdev, S_ISBLK(inode->i_mode) ? block_size(inode->i_bdev) : PAGE_SIZE); lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; if (partscan) lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; /* Grab the block_device to prevent its destruction after we * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); if (claimed_bdev) bd_abort_claiming(bdev, claimed_bdev, loop_configure); return 0; out_unlock: mutex_unlock(&loop_ctl_mutex); out_bdev: if (claimed_bdev) bd_abort_claiming(bdev, claimed_bdev, loop_configure); out_putf: fput(file); out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; } static int __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp = NULL; gfp_t gfp = lo->old_gfp_mask; struct block_device *bdev = lo->lo_device; int err = 0; bool partscan = false; int lo_number; mutex_lock(&loop_ctl_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { err = -ENXIO; goto out_unlock; } filp = lo->lo_backing_file; if (filp == NULL) { err = -EINVAL; goto out_unlock; } if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) blk_queue_write_cache(lo->lo_queue, false, false); /* freeze request queue during the transition */ blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); loop_release_xfer(lo); lo->transfer = NULL; lo->ioctl = NULL; lo->lo_device = NULL; lo->lo_encryption = NULL; lo->lo_offset = 0; lo->lo_sizelimit = 0; lo->lo_encrypt_key_size = 0; memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE); memset(lo->lo_crypt_name, 0, LO_NAME_SIZE); memset(lo->lo_file_name, 0, LO_NAME_SIZE); blk_queue_logical_block_size(lo->lo_queue, 512); blk_queue_physical_block_size(lo->lo_queue, 512); blk_queue_io_min(lo->lo_queue, 512); if (bdev) { bdput(bdev); invalidate_bdev(bdev); bdev->bd_inode->i_mapping->wb_err = 0; } set_capacity(lo->lo_disk, 0); loop_sysfs_exit(lo); if (bdev) { bd_set_nr_sectors(bdev, 0); /* let user-space know about this change */ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; lo_number = lo->lo_number; loop_unprepare_queue(lo); out_unlock: mutex_unlock(&loop_ctl_mutex); if (partscan) { /* * bd_mutex has been held already in release path, so don't * acquire it if this function is called in such case. * * If the reread partition isn't from release path, lo_refcnt * must be at least one and it can only become zero when the * current holder is released. */ if (!release) mutex_lock(&bdev->bd_mutex); err = bdev_disk_changed(bdev, false); if (!release) mutex_unlock(&bdev->bd_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); /* Device is gone, no point in returning error */ err = 0; } /* * lo->lo_state is set to Lo_unbound here after above partscan has * finished. * * There cannot be anybody else entering __loop_clr_fd() as * lo->lo_backing_file is already cleared and Lo_rundown state * protects us from all the other places trying to change the 'lo' * device. */ mutex_lock(&loop_ctl_mutex); lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; lo->lo_state = Lo_unbound; mutex_unlock(&loop_ctl_mutex); /* * Need not hold loop_ctl_mutex to fput backing file. * Calling fput holding loop_ctl_mutex triggers a circular * lock dependency possibility warning as fput can take * bd_mutex which is usually taken before loop_ctl_mutex. */ if (filp) fput(filp); return err; } static int loop_clr_fd(struct loop_device *lo) { int err; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; if (lo->lo_state != Lo_bound) { mutex_unlock(&loop_ctl_mutex); return -ENXIO; } /* * If we've explicitly asked to tear down the loop device, * and it has an elevated reference count, set it for auto-teardown when * the last reference goes away. This stops $!~#$@ udev from * preventing teardown because it decided that it needs to run blkid on * the loopback device whenever they appear. xfstests is notorious for * failing tests because blkid via udev races with a losetup * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d * command to fail with EBUSY. */ if (atomic_read(&lo->lo_refcnt) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; mutex_unlock(&loop_ctl_mutex); return 0; } lo->lo_state = Lo_rundown; mutex_unlock(&loop_ctl_mutex); return __loop_clr_fd(lo, false); } static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; struct block_device *bdev; kuid_t uid = current_uid(); int prev_lo_flags; bool partscan = false; bool size_changed = false; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto out_unlock; } if (lo->lo_state != Lo_bound) { err = -ENXIO; goto out_unlock; } if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { size_changed = true; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); } /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { /* If any pages were dirtied after invalidate_bdev(), try again */ err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; } prev_lo_flags = lo->lo_flags; err = loop_set_status_from_info(lo, info); if (err) goto out_unfreeze; /* Mask out flags that can't be set using LOOP_SET_STATUS. */ lo->lo_flags &= LOOP_SET_STATUS_SETTABLE_FLAGS; /* For those flags, use the previous values instead */ lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS; /* For flags that can't be cleared, use previous values too */ lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_CLEARABLE_FLAGS; if (size_changed) { loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, lo->lo_backing_file); loop_set_size(lo, new_size); } loop_config_discard(lo); /* update dio if lo_offset or transfer is changed */ __loop_update_dio(lo, lo->use_dio); out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) && !(prev_lo_flags & LO_FLAGS_PARTSCAN)) { lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; bdev = lo->lo_device; partscan = true; } out_unlock: mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); return err; } static int loop_get_status(struct loop_device *lo, struct loop_info64 *info) { struct path path; struct kstat stat; int ret; ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; if (lo->lo_state != Lo_bound) { mutex_unlock(&loop_ctl_mutex); return -ENXIO; } memset(info, 0, sizeof(*info)); info->lo_number = lo->lo_number; info->lo_offset = lo->lo_offset; info->lo_sizelimit = lo->lo_sizelimit; info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE); info->lo_encrypt_type = lo->lo_encryption ? lo->lo_encryption->number : 0; if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) { info->lo_encrypt_key_size = lo->lo_encrypt_key_size; memcpy(info->lo_encrypt_key, lo->lo_encrypt_key, lo->lo_encrypt_key_size); } /* Drop loop_ctl_mutex while we call into the filesystem. */ path = lo->lo_backing_file->f_path; path_get(&path); mutex_unlock(&loop_ctl_mutex); ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { info->lo_device = huge_encode_dev(stat.dev); info->lo_inode = stat.ino; info->lo_rdevice = huge_encode_dev(stat.rdev); } path_put(&path); return ret; } static void loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64) { memset(info64, 0, sizeof(*info64)); info64->lo_number = info->lo_number; info64->lo_device = info->lo_device; info64->lo_inode = info->lo_inode; info64->lo_rdevice = info->lo_rdevice; info64->lo_offset = info->lo_offset; info64->lo_sizelimit = 0; info64->lo_encrypt_type = info->lo_encrypt_type; info64->lo_encrypt_key_size = info->lo_encrypt_key_size; info64->lo_flags = info->lo_flags; info64->lo_init[0] = info->lo_init[0]; info64->lo_init[1] = info->lo_init[1]; if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE); else memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE); memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE); } static int loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) { memset(info, 0, sizeof(*info)); info->lo_number = info64->lo_number; info->lo_device = info64->lo_device; info->lo_inode = info64->lo_inode; info->lo_rdevice = info64->lo_rdevice; info->lo_offset = info64->lo_offset; info->lo_encrypt_type = info64->lo_encrypt_type; info->lo_encrypt_key_size = info64->lo_encrypt_key_size; info->lo_flags = info64->lo_flags; info->lo_init[0] = info64->lo_init[0]; info->lo_init[1] = info64->lo_init[1]; if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE); else memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); /* error in case values were truncated */ if (info->lo_device != info64->lo_device || info->lo_rdevice != info64->lo_rdevice || info->lo_inode != info64->lo_inode || info->lo_offset != info64->lo_offset) return -EOVERFLOW; return 0; } static int loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; if (copy_from_user(&info, arg, sizeof (struct loop_info))) return -EFAULT; loop_info64_from_old(&info, &info64); return loop_set_status(lo, &info64); } static int loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg) { struct loop_info64 info64; if (copy_from_user(&info64, arg, sizeof (struct loop_info64))) return -EFAULT; return loop_set_status(lo, &info64); } static int loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_old(&info64, &info); if (!err && copy_to_user(arg, &info, sizeof(info))) err = -EFAULT; return err; } static int loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err && copy_to_user(arg, &info64, sizeof(info64))) err = -EFAULT; return err; } static int loop_set_capacity(struct loop_device *lo) { loff_t size; if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; size = get_loop_size(lo, lo->lo_backing_file); loop_set_size(lo, size); return 0; } static int loop_set_dio(struct loop_device *lo, unsigned long arg) { int error = -ENXIO; if (lo->lo_state != Lo_bound) goto out; __loop_update_dio(lo, !!arg); if (lo->use_dio == !!arg) return 0; error = -EINVAL; out: return error; } static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { int err = 0; if (lo->lo_state != Lo_bound) return -ENXIO; err = blk_validate_block_size(arg); if (err) return err; if (lo->lo_queue->limits.logical_block_size == arg) return 0; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); /* invalidate_bdev should have truncated all the pages */ if (lo->lo_device->bd_inode->i_mapping->nrpages) { err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; } blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); return err; } static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, unsigned long arg) { int err; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; switch (cmd) { case LOOP_SET_CAPACITY: err = loop_set_capacity(lo); break; case LOOP_SET_DIRECT_IO: err = loop_set_dio(lo, arg); break; case LOOP_SET_BLOCK_SIZE: err = loop_set_block_size(lo, arg); break; default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } mutex_unlock(&loop_ctl_mutex); return err; } static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; void __user *argp = (void __user *) arg; int err; switch (cmd) { case LOOP_SET_FD: { /* * Legacy case - pass in a zeroed out struct loop_config with * only the file descriptor set , which corresponds with the * default parameters we'd have used otherwise. */ struct loop_config config; memset(&config, 0, sizeof(config)); config.fd = arg; return loop_configure(lo, mode, bdev, &config); } case LOOP_CONFIGURE: { struct loop_config config; if (copy_from_user(&config, argp, sizeof(config))) return -EFAULT; return loop_configure(lo, mode, bdev, &config); } case LOOP_CHANGE_FD: return loop_change_fd(lo, bdev, arg); case LOOP_CLR_FD: return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { err = loop_set_status_old(lo, argp); } break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { err = loop_set_status64(lo, argp); } break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); case LOOP_SET_CAPACITY: case LOOP_SET_DIRECT_IO: case LOOP_SET_BLOCK_SIZE: if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; fallthrough; default: err = lo_simple_ioctl(lo, cmd, arg); break; } return err; } #ifdef CONFIG_COMPAT struct compat_loop_info { compat_int_t lo_number; /* ioctl r/o */ compat_dev_t lo_device; /* ioctl r/o */ compat_ulong_t lo_inode; /* ioctl r/o */ compat_dev_t lo_rdevice; /* ioctl r/o */ compat_int_t lo_offset; compat_int_t lo_encrypt_type; compat_int_t lo_encrypt_key_size; /* ioctl w/o */ compat_int_t lo_flags; /* ioctl r/o */ char lo_name[LO_NAME_SIZE]; unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ compat_ulong_t lo_init[2]; char reserved[4]; }; /* * Transfer 32-bit compatibility structure in userspace to 64-bit loop info * - noinlined to reduce stack space usage in main part of driver */ static noinline int loop_info64_from_compat(const struct compat_loop_info __user *arg, struct loop_info64 *info64) { struct compat_loop_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; memset(info64, 0, sizeof(*info64)); info64->lo_number = info.lo_number; info64->lo_device = info.lo_device; info64->lo_inode = info.lo_inode; info64->lo_rdevice = info.lo_rdevice; info64->lo_offset = info.lo_offset; info64->lo_sizelimit = 0; info64->lo_encrypt_type = info.lo_encrypt_type; info64->lo_encrypt_key_size = info.lo_encrypt_key_size; info64->lo_flags = info.lo_flags; info64->lo_init[0] = info.lo_init[0]; info64->lo_init[1] = info.lo_init[1]; if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE); else memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE); return 0; } /* * Transfer 64-bit loop info to 32-bit compatibility structure in userspace * - noinlined to reduce stack space usage in main part of driver */ static noinline int loop_info64_to_compat(const struct loop_info64 *info64, struct compat_loop_info __user *arg) { struct compat_loop_info info; memset(&info, 0, sizeof(info)); info.lo_number = info64->lo_number; info.lo_device = info64->lo_device; info.lo_inode = info64->lo_inode; info.lo_rdevice = info64->lo_rdevice; info.lo_offset = info64->lo_offset; info.lo_encrypt_type = info64->lo_encrypt_type; info.lo_encrypt_key_size = info64->lo_encrypt_key_size; info.lo_flags = info64->lo_flags; info.lo_init[0] = info64->lo_init[0]; info.lo_init[1] = info64->lo_init[1]; if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE); else memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); /* error in case values were truncated */ if (info.lo_device != info64->lo_device || info.lo_rdevice != info64->lo_rdevice || info.lo_inode != info64->lo_inode || info.lo_offset != info64->lo_offset || info.lo_init[0] != info64->lo_init[0] || info.lo_init[1] != info64->lo_init[1]) return -EOVERFLOW; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int loop_set_status_compat(struct loop_device *lo, const struct compat_loop_info __user *arg) { struct loop_info64 info64; int ret; ret = loop_info64_from_compat(arg, &info64); if (ret < 0) return ret; return loop_set_status(lo, &info64); } static int loop_get_status_compat(struct loop_device *lo, struct compat_loop_info __user *arg) { struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_compat(&info64, arg); return err; } static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; int err; switch(cmd) { case LOOP_SET_STATUS: err = loop_set_status_compat(lo, (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: err = loop_get_status_compat(lo, (struct compat_loop_info __user *)arg); break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: case LOOP_GET_STATUS64: case LOOP_SET_STATUS64: case LOOP_CONFIGURE: arg = (unsigned long) compat_ptr(arg); fallthrough; case LOOP_SET_FD: case LOOP_CHANGE_FD: case LOOP_SET_BLOCK_SIZE: case LOOP_SET_DIRECT_IO: err = lo_ioctl(bdev, mode, cmd, arg); break; default: err = -ENOIOCTLCMD; break; } return err; } #endif static int lo_open(struct block_device *bdev, fmode_t mode) { struct loop_device *lo; int err; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; lo = bdev->bd_disk->private_data; if (!lo) { err = -ENXIO; goto out; } atomic_inc(&lo->lo_refcnt); out: mutex_unlock(&loop_ctl_mutex); return err; } static void lo_release(struct gendisk *disk, fmode_t mode) { struct loop_device *lo; mutex_lock(&loop_ctl_mutex); lo = disk->private_data; if (atomic_dec_return(&lo->lo_refcnt)) goto out_unlock; if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { if (lo->lo_state != Lo_bound) goto out_unlock; lo->lo_state = Lo_rundown; mutex_unlock(&loop_ctl_mutex); /* * In autoclear mode, stop the loop thread * and remove configuration after last close. */ __loop_clr_fd(lo, true); return; } else if (lo->lo_state == Lo_bound) { /* * Otherwise keep thread (if running) and config, * but flush possible ongoing bios in thread. */ blk_mq_freeze_queue(lo->lo_queue); blk_mq_unfreeze_queue(lo->lo_queue); } out_unlock: mutex_unlock(&loop_ctl_mutex); } static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = lo_compat_ioctl, #endif }; /* * And now the modules code and kernel interface. */ static int max_loop; module_param(max_loop, int, 0444); MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); int loop_register_transfer(struct loop_func_table *funcs) { unsigned int n = funcs->number; if (n >= MAX_LO_CRYPT || xfer_funcs[n]) return -EINVAL; xfer_funcs[n] = funcs; return 0; } static int unregister_transfer_cb(int id, void *ptr, void *data) { struct loop_device *lo = ptr; struct loop_func_table *xfer = data; mutex_lock(&loop_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); mutex_unlock(&loop_ctl_mutex); return 0; } int loop_unregister_transfer(int number) { unsigned int n = number; struct loop_func_table *xfer; if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL) return -EINVAL; xfer_funcs[n] = NULL; idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer); return 0; } EXPORT_SYMBOL(loop_register_transfer); EXPORT_SYMBOL(loop_unregister_transfer); static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); struct loop_device *lo = rq->q->queuedata; blk_mq_start_request(rq); if (lo->lo_state != Lo_bound) return BLK_STS_IOERR; switch (req_op(rq)) { case REQ_OP_FLUSH: case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: cmd->use_aio = false; break; default: cmd->use_aio = lo->use_dio; break; } /* always use the first bio's css */ #ifdef CONFIG_BLK_CGROUP if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) { cmd->css = &bio_blkcg(rq->bio)->css; css_get(cmd->css); } else #endif cmd->css = NULL; kthread_queue_work(&lo->worker, &cmd->work); return BLK_STS_OK; } static void loop_handle_cmd(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); const bool write = op_is_write(req_op(rq)); struct loop_device *lo = rq->q->queuedata; int ret = 0; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { ret = -EIO; goto failed; } ret = do_req_filebacked(lo, rq); failed: /* complete non-aio request */ if (!cmd->use_aio || ret) { if (ret == -EOPNOTSUPP) cmd->ret = ret; else cmd->ret = ret ? -EIO : 0; if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } } static void loop_queue_work(struct kthread_work *work) { struct loop_cmd *cmd = container_of(work, struct loop_cmd, work); loop_handle_cmd(cmd); } static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); kthread_init_work(&cmd->work, loop_queue_work); return 0; } static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, .init_request = loop_init_request, .complete = lo_complete_rq, }; static int loop_add(struct loop_device **l, int i) { struct loop_device *lo; struct gendisk *disk; int err; err = -ENOMEM; lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; lo->lo_state = Lo_unbound; /* allocate id, if @id >= 0, we're requesting that specific id */ if (i >= 0) { err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL); if (err == -ENOSPC) err = -EEXIST; } else { err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); } if (err < 0) goto out_free_dev; i = err; err = -ENOMEM; lo->tag_set.ops = &loop_mq_ops; lo->tag_set.nr_hw_queues = 1; lo->tag_set.queue_depth = 128; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING | BLK_MQ_F_NO_SCHED; lo->tag_set.driver_data = lo; err = blk_mq_alloc_tag_set(&lo->tag_set); if (err) goto out_free_idr; lo->lo_queue = blk_mq_init_queue(&lo->tag_set); if (IS_ERR(lo->lo_queue)) { err = PTR_ERR(lo->lo_queue); goto out_cleanup_tags; } lo->lo_queue->queuedata = lo; blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS); /* * By default, we do buffer IO, so it doesn't make sense to enable * merge because the I/O submitted to backing file is handled page by * page. For directio mode, merge does help to dispatch bigger request * to underlayer disk. We will enable merge once directio is enabled. */ blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); err = -ENOMEM; disk = lo->lo_disk = alloc_disk(1 << part_shift); if (!disk) goto out_free_queue; /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its * setup. Userspace can always add and remove partitions from all * devices. The needed partition minors are allocated from the * extended minor space, the main loop device numbers will continue * to match the loop minors, regardless of the number of partitions * used. * * If max_part is given, partition scanning is globally enabled for * all loop devices. The minors for the main loop devices will be * multiples of max_part. * * Note: Global-for-all-devices, set-only-at-init, read-only module * parameteters like 'max_loop' and 'max_part' make things needlessly * complicated, are too static, inflexible and may surprise * userspace tools. Parameters like this in general should be avoided. */ if (!part_shift) disk->flags |= GENHD_FL_NO_PART_SCAN; disk->flags |= GENHD_FL_EXT_DEVT; atomic_set(&lo->lo_refcnt, 0); lo->lo_number = i; spin_lock_init(&lo->lo_lock); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; disk->fops = &lo_fops; disk->private_data = lo; disk->queue = lo->lo_queue; sprintf(disk->disk_name, "loop%d", i); add_disk(disk); *l = lo; return lo->lo_number; out_free_queue: blk_cleanup_queue(lo->lo_queue); out_cleanup_tags: blk_mq_free_tag_set(&lo->tag_set); out_free_idr: idr_remove(&loop_index_idr, i); out_free_dev: kfree(lo); out: return err; } static void loop_remove(struct loop_device *lo) { del_gendisk(lo->lo_disk); blk_cleanup_queue(lo->lo_queue); blk_mq_free_tag_set(&lo->tag_set); put_disk(lo->lo_disk); kfree(lo); } static int find_free_cb(int id, void *ptr, void *data) { struct loop_device *lo = ptr; struct loop_device **l = data; if (lo->lo_state == Lo_unbound) { *l = lo; return 1; } return 0; } static int loop_lookup(struct loop_device **l, int i) { struct loop_device *lo; int ret = -ENODEV; if (i < 0) { int err; err = idr_for_each(&loop_index_idr, &find_free_cb, &lo); if (err == 1) { *l = lo; ret = lo->lo_number; } goto out; } /* lookup and return a specific i */ lo = idr_find(&loop_index_idr, i); if (lo) { *l = lo; ret = lo->lo_number; } out: return ret; } static struct kobject *loop_probe(dev_t dev, int *part, void *data) { struct loop_device *lo; struct kobject *kobj; int err; mutex_lock(&loop_ctl_mutex); err = loop_lookup(&lo, MINOR(dev) >> part_shift); if (err < 0) err = loop_add(&lo, MINOR(dev) >> part_shift); if (err < 0) kobj = NULL; else kobj = get_disk_and_module(lo->lo_disk); mutex_unlock(&loop_ctl_mutex); *part = 0; return kobj; } static long loop_control_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { struct loop_device *lo; int ret; ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; ret = -ENOSYS; switch (cmd) { case LOOP_CTL_ADD: ret = loop_lookup(&lo, parm); if (ret >= 0) { ret = -EEXIST; break; } ret = loop_add(&lo, parm); break; case LOOP_CTL_REMOVE: ret = loop_lookup(&lo, parm); if (ret < 0) break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; break; } lo->lo_disk->private_data = NULL; idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; case LOOP_CTL_GET_FREE: ret = loop_lookup(&lo, -1); if (ret >= 0) break; ret = loop_add(&lo, -1); } mutex_unlock(&loop_ctl_mutex); return ret; } static const struct file_operations loop_ctl_fops = { .open = nonseekable_open, .unlocked_ioctl = loop_control_ioctl, .compat_ioctl = loop_control_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice loop_misc = { .minor = LOOP_CTRL_MINOR, .name = "loop-control", .fops = &loop_ctl_fops, }; MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR); MODULE_ALIAS("devname:loop-control"); static int __init loop_init(void) { int i, nr; unsigned long range; struct loop_device *lo; int err; part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); /* * Adjust max_part according to part_shift as it is exported * to user space so that user can decide correct minor number * if [s]he want to create more devices. * * Note that -1 is required because partition 0 is reserved * for the whole disk. */ max_part = (1UL << part_shift) - 1; } if ((1UL << part_shift) > DISK_MAX_PARTS) { err = -EINVAL; goto err_out; } if (max_loop > 1UL << (MINORBITS - part_shift)) { err = -EINVAL; goto err_out; } /* * If max_loop is specified, create that many devices upfront. * This also becomes a hard limit. If max_loop is not specified, * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module * init time. Loop devices can be requested on-demand with the * /dev/loop-control interface, or be instantiated by accessing * a 'dead' device node. */ if (max_loop) { nr = max_loop; range = max_loop << part_shift; } else { nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT; range = 1UL << MINORBITS; } err = misc_register(&loop_misc); if (err < 0) goto err_out; if (register_blkdev(LOOP_MAJOR, "loop")) { err = -EIO; goto misc_out; } blk_register_region(MKDEV(LOOP_MAJOR, 0), range, THIS_MODULE, loop_probe, NULL, NULL); /* pre-create number of devices given by config or max_loop */ mutex_lock(&loop_ctl_mutex); for (i = 0; i < nr; i++) loop_add(&lo, i); mutex_unlock(&loop_ctl_mutex); printk(KERN_INFO "loop: module loaded\n"); return 0; misc_out: misc_deregister(&loop_misc); err_out: return err; } static int loop_exit_cb(int id, void *ptr, void *data) { struct loop_device *lo = ptr; loop_remove(lo); return 0; } static void __exit loop_exit(void) { unsigned long range; range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; mutex_lock(&loop_ctl_mutex); idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); idr_destroy(&loop_index_idr); blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); unregister_blkdev(LOOP_MAJOR, "loop"); misc_deregister(&loop_misc); mutex_unlock(&loop_ctl_mutex); } module_init(loop_init); module_exit(loop_exit); #ifndef MODULE static int __init max_loop_setup(char *str) { max_loop = simple_strtol(str, NULL, 0); return 1; } __setup("max_loop=", max_loop_setup); #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_INTERNAL_H #define BLK_INTERNAL_H #include <linux/idr.h> #include <linux/blk-mq.h> #include <linux/part_stat.h> #include <linux/blk-crypto.h> #include <xen/xen.h> #include "blk-crypto-internal.h" #include "blk-mq.h" #include "blk-mq-sched.h" /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) extern struct dentry *blk_debugfs_root; struct blk_flush_queue { unsigned int flush_pending_idx:1; unsigned int flush_running_idx:1; blk_status_t rq_status; unsigned long flush_pending_since; struct list_head flush_queue[2]; struct list_head flush_data_in_flight; struct request *flush_rq; struct lock_class_key key; spinlock_t mq_flush_lock; }; extern struct kmem_cache *blk_requestq_cachep; extern struct kobj_type blk_queue_ktype; extern struct ida blk_queue_ida; static inline struct blk_flush_queue * blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) { return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq; } static inline void __blk_get_queue(struct request_queue *q) { kobject_get(&q->kobj); } bool is_flush_rq(struct request *req); struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, gfp_t flags); void blk_free_flush_queue(struct blk_flush_queue *q); void blk_freeze_queue(struct request_queue *q); static inline bool biovec_phys_mergeable(struct request_queue *q, struct bio_vec *vec1, struct bio_vec *vec2) { unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset; phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset; if (addr1 + vec1->bv_len != addr2) return false; if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page)) return false; if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask)) return false; return true; } static inline bool __bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { return (offset & queue_virt_boundary(q)) || ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. */ static inline bool bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { if (!queue_virt_boundary(q)) return false; return __bvec_gap_to_prev(q, bprv, offset); } static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, unsigned int nr_segs) { rq->nr_phys_segments = nr_segs; rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; rq->ioprio = bio_prio(bio); if (bio->bi_disk) rq->rq_disk = bio->bi_disk; } #ifdef CONFIG_BLK_DEV_INTEGRITY void blk_flush_integrity(void); bool __bio_integrity_endio(struct bio *); void bio_integrity_free(struct bio *bio); static inline bool bio_integrity_endio(struct bio *bio) { if (bio_integrity(bio)) return __bio_integrity_endio(bio); return true; } bool blk_integrity_merge_rq(struct request_queue *, struct request *, struct request *); bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { struct bio_integrity_payload *bip = bio_integrity(req->bio); struct bio_integrity_payload *bip_next = bio_integrity(next); return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } static inline bool integrity_req_gap_front_merge(struct request *req, struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_integrity_payload *bip_next = bio_integrity(req->bio); return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } void blk_integrity_add(struct gendisk *); void blk_integrity_del(struct gendisk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline bool blk_integrity_merge_rq(struct request_queue *rq, struct request *r1, struct request *r2) { return true; } static inline bool blk_integrity_merge_bio(struct request_queue *rq, struct request *r, struct bio *b) { return true; } static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { return false; } static inline bool integrity_req_gap_front_merge(struct request *req, struct bio *bio) { return false; } static inline void blk_flush_integrity(void) { } static inline bool bio_integrity_endio(struct bio *bio) { return true; } static inline void bio_integrity_free(struct bio *bio) { } static inline void blk_integrity_add(struct gendisk *disk) { } static inline void blk_integrity_del(struct gendisk *disk) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ unsigned long blk_rq_timeout(unsigned long timeout); void blk_add_timer(struct request *req); bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **same_queue_rq); bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); void blk_account_io_start(struct request *req); void blk_account_io_done(struct request *req, u64 now); /* * Plug flush limits */ #define BLK_MAX_REQUEST_COUNT 32 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) /* * Internal elevator interface */ #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) void blk_insert_flush(struct request *rq); void elevator_init_mq(struct request_queue *q); int elevator_switch_mq(struct request_queue *q, struct elevator_type *new_e); void __elevator_exit(struct request_queue *, struct elevator_queue *); int elv_register_queue(struct request_queue *q, bool uevent); void elv_unregister_queue(struct request_queue *q); static inline void elevator_exit(struct request_queue *q, struct elevator_queue *e) { lockdep_assert_held(&q->sysfs_lock); blk_mq_sched_free_requests(q); __elevator_exit(q, e); } struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); ssize_t part_timeout_store(struct device *, struct device_attribute *, const char *, size_t); void __blk_queue_split(struct bio **bio, unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); int blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); unsigned int blk_recalc_rq_segments(struct request *rq); void blk_rq_set_mixed_merge(struct request *rq); bool blk_rq_merge_ok(struct request *rq, struct bio *bio); enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); int blk_dev_init(void); /* * Contribute to IO statistics IFF: * * a) it's attached to a gendisk, and * b) the queue had IO stats enabled when this request was started */ static inline bool blk_do_io_stat(struct request *rq) { return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT); } static inline void req_set_nomerge(struct request_queue *q, struct request *req) { req->cmd_flags |= REQ_NOMERGE; if (req == q->last_merge) q->last_merge = NULL; } /* * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size * is defined as 'unsigned int', meantime it has to aligned to with logical * block size which is the minimum accepted unit by hardware. */ static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) { return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; } /* * The max bio size which is aligned to q->limits.discard_granularity. This * is a hint to split large discard bio in generic block layer, then if device * driver needs to split the discard bio into smaller ones, their bi_size can * be very probably and easily aligned to discard_granularity of the device's * queue. */ static inline unsigned int bio_aligned_discard_max_sectors( struct request_queue *q) { return round_down(UINT_MAX, q->limits.discard_granularity) >> SECTOR_SHIFT; } /* * Internal io_context interface */ void get_io_context(struct io_context *ioc); struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q); struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, gfp_t gfp_mask); void ioc_clear_queue(struct request_queue *q); int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node); /* * Internal throttling interface */ #ifdef CONFIG_BLK_DEV_THROTTLING extern int blk_throtl_init(struct request_queue *q); extern void blk_throtl_exit(struct request_queue *q); extern void blk_throtl_register_queue(struct request_queue *q); extern void blk_throtl_charge_bio_split(struct bio *bio); bool blk_throtl_bio(struct bio *bio); #else /* CONFIG_BLK_DEV_THROTTLING */ static inline int blk_throtl_init(struct request_queue *q) { return 0; } static inline void blk_throtl_exit(struct request_queue *q) { } static inline void blk_throtl_register_queue(struct request_queue *q) { } static inline void blk_throtl_charge_bio_split(struct bio *bio) { } static inline bool blk_throtl_bio(struct bio *bio) { return false; } #endif /* CONFIG_BLK_DEV_THROTTLING */ #ifdef CONFIG_BLK_DEV_THROTTLING_LOW extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page); extern ssize_t blk_throtl_sample_time_store(struct request_queue *q, const char *page, size_t count); extern void blk_throtl_bio_endio(struct bio *bio); extern void blk_throtl_stat_add(struct request *rq, u64 time); #else static inline void blk_throtl_bio_endio(struct bio *bio) { } static inline void blk_throtl_stat_add(struct request *rq, u64 time) { } #endif #ifdef CONFIG_BOUNCE extern int init_emergency_isa_pool(void); extern void blk_queue_bounce(struct request_queue *q, struct bio **bio); #else static inline int init_emergency_isa_pool(void) { return 0; } static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) { } #endif /* CONFIG_BOUNCE */ #ifdef CONFIG_BLK_CGROUP_IOLATENCY extern int blk_iolatency_init(struct request_queue *q); #else static inline int blk_iolatency_init(struct request_queue *q) { return 0; } #endif struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); #ifdef CONFIG_BLK_DEV_ZONED void blk_queue_free_zone_bitmaps(struct request_queue *q); #else static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} #endif struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); int blk_alloc_devt(struct hd_struct *part, dev_t *devt); void blk_free_devt(dev_t devt); void blk_invalidate_devt(dev_t devt); char *disk_name(struct gendisk *hd, int partno, char *buf); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 void delete_partition(struct hd_struct *part); int bdev_add_partition(struct block_device *bdev, int partno, sector_t start, sector_t length); int bdev_del_partition(struct block_device *bdev, int partno); int bdev_resize_partition(struct block_device *bdev, int partno, sector_t start, sector_t length); int disk_expand_part_tbl(struct gendisk *disk, int target); int hd_ref_init(struct hd_struct *part); /* no need to get/put refcount of part0 */ static inline int hd_struct_try_get(struct hd_struct *part) { if (part->partno) return percpu_ref_tryget_live(&part->ref); return 1; } static inline void hd_struct_put(struct hd_struct *part) { if (part->partno) percpu_ref_put(&part->ref); } static inline void hd_free_part(struct hd_struct *part) { free_percpu(part->dkstats); kfree(part->info); percpu_ref_exit(&part->ref); } /* * Any access of part->nr_sects which is not protected by partition * bd_mutex or gendisk bdev bd_mutex, should be done using this * accessor function. * * Code written along the lines of i_size_read() and i_size_write(). * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption * on. */ static inline sector_t part_nr_sects_read(struct hd_struct *part) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) sector_t nr_sects; unsigned seq; do { seq = read_seqcount_begin(&part->nr_sects_seq); nr_sects = part->nr_sects; } while (read_seqcount_retry(&part->nr_sects_seq, seq)); return nr_sects; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) sector_t nr_sects; preempt_disable(); nr_sects = part->nr_sects; preempt_enable(); return nr_sects; #else return part->nr_sects; #endif } /* * Should be called with mutex lock held (typically bd_mutex) of partition * to provide mutual exlusion among writers otherwise seqcount might be * left in wrong state leaving the readers spinning infinitely. */ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&part->nr_sects_seq); part->nr_sects = size; write_seqcount_end(&part->nr_sects_seq); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); part->nr_sects = size; preempt_enable(); #else part->nr_sects = size; #endif } int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); #endif /* BLK_INTERNAL_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages not added to the page allocator when onlining a section because * they were excluded via the online_page_callback() or because they are * PG_hwpoison. * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - Pages part of an offline section (struct pages of offline sections should * not be trusted as they will be initialized when first onlined). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_uptodate tells whether the page's contents is valid. When a read * completes, the page becomes uptodate, unless a disk I/O error happened. * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_error is set to indicate that an I/O error occurred on this page. * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the *_dontuse flags. Use the macros. Otherwise you'll break * locked- and dirty-page accounting. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ PG_head, /* A head page */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PG_uncached, /* Page has been mapped as uncached */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_64BIT PG_arch_2, #endif __NR_PAGEFLAGS, /* Filesystems */ PG_checked = PG_owner_priv_1, /* SwapBacked */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, /* Compound pages. Stored in first tail page's flags */ PG_double_map = PG_workingset, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, }; #ifndef __GENERATING_BOUNDS_H struct page; /* forward declaration */ static inline struct page *compound_head(struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return (struct page *) (head - 1); return page; } static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; } static __always_inline int PageCompound(struct page *page) { return test_bit(PG_head, &page->flags) || PageTail(page); } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return page->flags == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_ONLY_HEAD: * for compound page, callers only ever operate on the head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_ONLY_HEAD(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(PageTail(page), page); \ PF_POISONED_CHECK(page); }) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname, policy) \ static __always_inline int Page##uname(struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) #define TESTSCFLAG_FALSE(uname) \ TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) __SETPAGEFLAG(Referenced, referenced, PF_HEAD) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause releasepage() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY) __CLEARPAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #else PAGEFLAG_FALSE(HighMem) #endif #ifdef CONFIG_SWAP static __always_inline int PageSwapCache(struct page *page) { #ifdef CONFIG_THP_SWAP page = compound_head(page); #endif return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); } SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else PAGEFLAG_FALSE(SwapCache) #endif PAGEFLAG(Unevictable, unevictable, PF_HEAD) __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) #ifdef CONFIG_MMU PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) TESTSCFLAG_FALSE(Mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(Uncached) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) extern bool take_page_off_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) TESTPAGEFLAG(Young, young, PF_ANY) SETPAGEFLAG(Young, young, PF_ANY) TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then page->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then page->mapping points a struct address_space. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline int PageAnon(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline int __PageMovable(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline int PageKsm(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } #else TESTPAGEFLAG_FALSE(Ksm) #endif u64 stable_page_flags(struct page *page); static inline int PageUptodate(struct page *page) { int ret; page = compound_head(page); ret = test_bit(PG_uptodate, &(page)->flags); /* * Must ensure that the data we read out of the page is loaded * _after_ we've loaded page->flags to check for PageUptodate. * We can skip the barrier if the page is not uptodate, because * we wouldn't be reading anything from it. * * See SetPageUptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static __always_inline void __SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); __set_bit(PG_uptodate, &page->flags); } static __always_inline void SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the page * uptodate are actually visible before PageUptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, &page->flags); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) int test_clear_page_writeback(struct page *page); int __test_set_page_writeback(struct page *page, bool keep_write); #define test_set_page_writeback(page) \ __test_set_page_writeback(page, false) #define test_set_page_writeback_keepwrite(page) \ __test_set_page_writeback(page, true) static inline void set_page_writeback(struct page *page) { test_set_page_writeback(page); } static inline void set_page_writeback_keepwrite(struct page *page) { test_set_page_writeback_keepwrite(page); } __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); bool page_huge_active(struct page *page); #else TESTPAGEFLAG_FALSE(Huge) TESTPAGEFLAG_FALSE(HeadHuge) static inline bool page_huge_active(struct page *page) { return 0; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(struct page *page) { return PageCompound(page); } /* * PageTransCompoundMap is the same as PageTransCompound, but it also * guarantees the primary MMU has the entire compound page mapped * through pmd_trans_huge, which in turn guarantees the secondary MMUs * can also map the entire compound page. This allows the secondary * MMUs to call get_user_pages() only once for each compound page and * to immediately map the entire compound page with a single secondary * MMU fault. If there will be a pmd split later, the secondary MMUs * will get an update through the MMU notifier invalidation through * split_huge_pmd(). * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the * MMU notifier, otherwise it may result in page->_mapcount check false * positives. * * We have to treat page cache THP differently since every subpage of it * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE * mapped in the current process so comparing subpage's _mapcount to * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { struct page *head; if (!PageTransCompound(page)) return 0; if (PageAnon(page)) return atomic_read(&page->_mapcount) < 0; head = compound_head(page); /* File THP is PMD mapped and not PTE mapped */ return atomic_read(&page->_mapcount) == atomic_read(compound_mapcount_ptr(head)); } /* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransTail(struct page *page) { return PageTail(page); } /* * PageDoubleMap indicates that the compound page is mapped with PTEs as well * as PMDs. * * This is required for optimization of rmap operations for THP: we can postpone * per small page mapcount accounting (and its overhead from atomic operations) * until the first PMD split. * * For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up * by one. This reference will go away with last compound_mapcount. * * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). */ PAGEFLAG(DoubleMap, double_map, PF_SECOND) TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) PAGEFLAG_FALSE(DoubleMap) TESTSCFLAG_FALSE(DoubleMap) #endif /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and * low bits so that an underflow or overflow of page_mapcount() won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 /* Reserve 0x0000007f to catch underflows of page_mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_kmemcg 0x00000200 #define PG_table 0x00000400 #define PG_guard 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) static inline int page_has_type(struct page *page) { return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; } #define PAGE_TYPE_OPS(uname, lname) \ static __always_inline int Page##uname(struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free pages, * allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require to re-set the pages PageOffline() and not giving them to the * buddy via online_page_callback_t. */ PAGE_TYPE_OPS(Offline, offline) /* * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on * pages allocated with __GFP_ACCOUNT. It gets cleared on page free. */ PAGE_TYPE_OPS(Kmemcg, kmemcg) /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard) extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); /* * If network-based swap is enabled, sl*b must keep track of whether pages * were allocated from pfmemalloc reserves. */ static inline int PageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); return PageActive(page); } static inline void SetPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); SetPageActive(page); } static inline void __ClearPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); __ClearPageActive(page); } static inline void ClearPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); ClearPageActive(page); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_slab | 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ (((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * page_has_private - Determine if page has private stuff * @page: The page to be checked * * Determine if a page has private stuff, indicating that release routines * should be invoked upon it. */ static inline int page_has_private(struct page *page) { return !!(page->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_ONLY_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 | /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/processor.h> static inline int phys_addr_valid(resource_size_t addr) { #ifdef CONFIG_PHYS_ADDR_T_64BIT return !(addr >> boot_cpu_data.x86_phys_bits); #else return 1; #endif } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001 */ /* * This handles all read/write requests to block devices */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/blk-pm.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kernel_stat.h> #include <linux/string.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/task_io_accounting_ops.h> #include <linux/fault-inject.h> #include <linux/list_sort.h> #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> #include <linux/blk-cgroup.h> #include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> #include <linux/psi.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-pm.h" #include "blk-rq-qos.h" struct dentry *blk_debugfs_root; EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd */ static struct workqueue_struct *kblockd_workqueue; /** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); /** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); /** * blk_queue_flag_test_and_set - atomically test and set a queue flag * @flag: flag to be set * @q: request queue * * Returns the previous value of @flag - 0 if the flag was not set and 1 if * the flag was already set. */ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) { return test_and_set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = ktime_get_ns(); rq->part = NULL; blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), REQ_OP_NAME(SCSI_OUT), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT), }; #undef REQ_OP_NAME /** * blk_op_str - Return string XXX in the REQ_OP_XXX. * @op: REQ_OP_XXX. * * Description: Centralize block layer function to convert REQ_OP_XXX into * string format. Useful in the debugging and tracing bio or request. For * invalid REQ_OP_XXX it returns string "UNKNOWN". */ inline const char *blk_op_str(unsigned int op) { const char *op_str = "UNKNOWN"; if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op]; return op_str; } EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; const char *name; } blk_errors[] = { [BLK_STS_OK] = { 0, "" }, [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, [BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" }, [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, /* zone device specific errors */ [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; blk_status_t errno_to_blk_status(int errno) { int i; for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; } return BLK_STS_IOERR; } EXPORT_SYMBOL_GPL(errno_to_blk_status); int blk_status_to_errno(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno; } EXPORT_SYMBOL_GPL(blk_status_to_errno); static void print_req_error(struct request *req, blk_status_t status, const char *caller) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return; printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", caller, blk_errors[idx].name, req->rq_disk ? req->rq_disk->disk_name : "?", blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)), req->cmd_flags & ~REQ_OP_MASK, req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, blk_status_t error) { if (error) bio->bi_status = error; if (unlikely(rq->rq_flags & RQF_QUIET)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, nbytes); if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. */ if (bio->bi_iter.bi_size) bio->bi_status = BLK_STS_IOERR; else bio->bi_iter.bi_sector = rq->__sector; } /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->rq_disk ? rq->rq_disk->disk_name : "?", (unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); /** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */ void blk_set_pm_only(struct request_queue *q) { atomic_inc(&q->pm_only); } EXPORT_SYMBOL_GPL(blk_set_pm_only); void blk_clear_pm_only(struct request_queue *q) { int pm_only; pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_clear_pm_only); /** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue kobject. When this reaches 0 * we'll have blk_release_queue() called. * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } EXPORT_SYMBOL(blk_put_queue); void blk_set_queue_dying(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_DYING, q); /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ blk_freeze_queue_start(q); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_set_queue_dying); /** * blk_cleanup_queue - shutdown a request queue * @q: request queue to shutdown * * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and * put it. All future requests will be failed immediately with -ENODEV. * * Context: can sleep */ void blk_cleanup_queue(struct request_queue *q) { /* cannot be called from atomic context */ might_sleep(); WARN_ON_ONCE(blk_queue_registered(q)); /* mark @q DYING, no new request or merges will be allowed afterwards */ blk_set_queue_dying(q); blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); /* * Drain all requests queued before DYING marking. Set DEAD flag to * prevent that blk_mq_run_hw_queues() accesses the hardware queues * after draining finished. */ blk_freeze_queue(q); rq_qos_exit(q); blk_queue_flag_set(QUEUE_FLAG_DEAD, q); /* for synchronous bio-based driver finish in-flight integrity i/o */ blk_flush_integrity(); /* @q won't process any more request, flush async actions */ del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); blk_sync_queue(q); if (queue_is_mq(q)) blk_mq_exit_queue(q); /* * In theory, request pool of sched_tags belongs to request queue. * However, the current implementation requires tag_set for freeing * requests, so free the pool now. * * Queue has become frozen, there can't be any in-queue requests, so * it is safe to free requests now. */ mutex_lock(&q->sysfs_lock); if (q->elevator) blk_mq_sched_free_requests(q); mutex_unlock(&q->sysfs_lock); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; while (true) { bool success = false; rcu_read_lock(); if (percpu_ref_tryget_live(&q->q_usage_counter)) { /* * The code that increments the pm_only counter is * responsible for ensuring that that counter is * globally visible before the queue is unfrozen. */ if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) || !blk_queue_pm_only(q)) { success = true; } else { percpu_ref_put(&q->q_usage_counter); } } rcu_read_unlock(); if (success) return 0; if (flags & BLK_MQ_REQ_NOWAIT) return -EBUSY; /* * read pair of barrier in blk_freeze_queue_start(), * we need to order reading __PERCPU_REF_DEAD flag of * .q_usage_counter and reading .mq_freeze_depth or * queue dying flag, otherwise the following wait may * never return if the two reads are reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } } static inline int bio_queue_enter(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; bool nowait = bio->bi_opf & REQ_NOWAIT; int ret; ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0); if (unlikely(ret)) { if (nowait && !blk_queue_dying(q)) bio_wouldblock_error(bio); else bio_io_error(bio); } return ret; } void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); } static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); wake_up_all(&q->mq_freeze_wq); } static void blk_rq_timed_out_timer(struct timer_list *t) { struct request_queue *q = from_timer(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } static void blk_timeout_work(struct work_struct *work) { } struct request_queue *blk_alloc_queue(int node_id) { struct request_queue *q; int ret; q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return NULL; q->last_merge = NULL; q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL); if (q->id < 0) goto fail_q; ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (ret) goto fail_id; q->backing_dev_info = bdi_alloc(node_id); if (!q->backing_dev_info) goto fail_split; q->stats = blk_alloc_queue_stats(); if (!q->stats) goto fail_stats; q->node = node_id; atomic_set(&q->nr_active_requests_shared_sbitmap, 0); timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); #endif kobject_init(&q->kobj, &blk_queue_ktype); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) goto fail_bdi; if (blkcg_init_queue(q)) goto fail_ref; blk_queue_dma_alignment(q, 511); blk_set_default_limits(&q->limits); q->nr_requests = BLKDEV_MAX_RQ; return q; fail_ref: percpu_ref_exit(&q->q_usage_counter); fail_bdi: blk_free_queue_stats(q->stats); fail_stats: bdi_put(q->backing_dev_info); fail_split: bioset_exit(&q->bio_split); fail_id: ida_simple_remove(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } EXPORT_SYMBOL(blk_alloc_queue); /** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */ bool blk_get_queue(struct request_queue *q) { if (likely(!blk_queue_dying(q))) { __blk_get_queue(q); return true; } return false; } EXPORT_SYMBOL(blk_get_queue); /** * blk_get_request - allocate a request * @q: request queue to allocate a request for * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. */ struct request *blk_get_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct request *req; WARN_ON_ONCE(op & REQ_NOWAIT); WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); req = blk_mq_alloc_request(q, op, flags); if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) q->mq_ops->initialize_rq_fn(req); return req; } EXPORT_SYMBOL(blk_get_request); void blk_put_request(struct request *req) { blk_mq_free_request(req); } EXPORT_SYMBOL(blk_put_request); static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; pr_info_ratelimited("attempt to access beyond end of device\n" "%s: rw=%d, want=%llu, limit=%llu\n", bio_devname(bio, b), bio->bi_opf, bio_end_sector(bio), maxsector); } #ifdef CONFIG_FAIL_MAKE_REQUEST static DECLARE_FAULT_ATTR(fail_make_request); static int __init setup_fail_make_request(char *str) { return setup_fault_attr(&fail_make_request, str); } __setup("fail_make_request=", setup_fail_make_request); static bool should_fail_request(struct hd_struct *part, unsigned int bytes) { return part->make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool should_fail_request(struct hd_struct *part, unsigned int bytes) { return false; } #endif /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) { const int op = bio_op(bio); if (part->policy && op_is_write(op)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; pr_warn("Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false; } return false; } static noinline int should_fail_bio(struct bio *bio) { if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) return -EIO; return 0; } ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); /* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) { unsigned int nr_sectors = bio_sectors(bio); if (nr_sectors && maxsector && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { handle_bad_sector(bio, maxsector); return -EIO; } return 0; } /* * Remap block n of partition p to block n+start(p) of the disk. */ static inline int blk_partition_remap(struct bio *bio) { struct hd_struct *p; int ret = -EIO; rcu_read_lock(); p = __disk_get_part(bio->bi_disk, bio->bi_partno); if (unlikely(!p)) goto out; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) goto out; if (unlikely(bio_check_ro(bio, p))) goto out; if (bio_sectors(bio)) { if (bio_check_eod(bio, part_nr_sects_read(p))) goto out; bio->bi_iter.bi_sector += p->start_sect; trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), bio->bi_iter.bi_sector - p->start_sect); } bio->bi_partno = 0; ret = 0; out: rcu_read_unlock(); return ret; } /* * Check write append to a zoned block device. */ static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { sector_t pos = bio->bi_iter.bi_sector; int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ if (!blk_queue_is_zoned(q)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ if (pos & (blk_queue_zone_sectors(q) - 1) || !blk_queue_zone_is_seq(q, pos)) return BLK_STS_IOERR; /* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR; /* Make sure the BIO is small enough and will not get split */ if (nr_sectors > q->limits.max_zone_append_sectors) return BLK_STS_IOERR; bio->bi_opf |= REQ_NOMERGE; return BLK_STS_OK; } static noinline_for_stack bool submit_bio_checks(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; blk_status_t status = BLK_STS_IOERR; struct blk_plug *plug; might_sleep(); plug = blk_mq_plug(q, bio); if (plug && plug->nowait) bio->bi_opf |= REQ_NOWAIT; /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) goto not_supported; if (should_fail_bio(bio)) goto end_io; if (bio->bi_partno) { if (unlikely(blk_partition_remap(bio))) goto end_io; } else { if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; } /* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf) && !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) bio->bi_opf &= ~REQ_HIPRI; switch (bio_op(bio)) { case REQ_OP_DISCARD: if (!blk_queue_discard(q)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!blk_queue_secure_erase(q)) goto not_supported; break; case REQ_OP_WRITE_SAME: if (!q->limits.max_write_same_sectors) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; case REQ_OP_ZONE_RESET_ALL: if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q)) goto not_supported; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; default: break; } /* * Various block parts want %current->io_context, so allocate it up * front rather than dealing with lots of pain to allocate it only * where needed. This may fail and the block layer knows how to live * with it. */ if (unlikely(!current->io_context)) create_task_io_context(current, GFP_ATOMIC, q->node); if (blk_throtl_bio(bio)) return false; blk_cgroup_bio_start(bio); blkcg_bio_issue_init(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(q, bio); /* Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); } return true; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); return false; } static blk_qc_t __submit_bio(struct bio *bio) { struct gendisk *disk = bio->bi_disk; blk_qc_t ret = BLK_QC_T_NONE; if (blk_crypto_bio_prep(&bio)) { if (!disk->fops->submit_bio) return blk_mq_submit_bio(bio); ret = disk->fops->submit_bio(bio); } blk_queue_exit(disk->queue); return ret; } /* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio of the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio_bio, but that haven't been processed yet. */ static blk_qc_t __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; blk_qc_t ret = BLK_QC_T_NONE; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; do { struct request_queue *q = bio->bi_disk->queue; struct bio_list lower, same; if (unlikely(bio_queue_enter(bio) != 0)) continue; /* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); ret = __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bio->bi_disk->queue) bio_list_add(&same, bio); else bio_list_add(&lower, bio); /* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; return ret; } static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; blk_qc_t ret = BLK_QC_T_NONE; current->bio_list = bio_list; do { struct gendisk *disk = bio->bi_disk; if (unlikely(bio_queue_enter(bio) != 0)) continue; if (!blk_crypto_bio_prep(&bio)) { blk_queue_exit(disk->queue); ret = BLK_QC_T_NONE; continue; } ret = blk_mq_submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; return ret; } /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */ blk_qc_t submit_bio_noacct(struct bio *bio) { if (!submit_bio_checks(bio)) return BLK_QC_T_NONE; /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submited by a ->submit_bio method while * it is active, and then process them after it returned. */ if (current->bio_list) { bio_list_add(¤t->bio_list[0], bio); return BLK_QC_T_NONE; } if (!bio->bi_disk->fops->submit_bio) return __submit_bio_noacct_mq(bio); return __submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio_noacct); /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be send to the device described by the bi_disk and bi_partno fields. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has * been called. */ blk_qc_t submit_bio(struct bio *bio) { if (blkcg_punt_bio_submit(bio)) return BLK_QC_T_NONE; /* * If it's a regular read/write or a barrier with data attached, * go through the normal accounting stuff before submission. */ if (bio_has_data(bio)) { unsigned int count; if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) count = queue_logical_block_size(bio->bi_disk->queue) >> 9; else count = bio_sectors(bio); if (op_is_write(bio_op(bio))) { count_vm_events(PGPGOUT, count); } else { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } if (unlikely(block_dump)) { char b[BDEVNAME_SIZE]; printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", current->comm, task_pid_nr(current), op_is_write(bio_op(bio)) ? "WRITE" : "READ", (unsigned long long)bio->bi_iter.bi_sector, bio_devname(bio, b), count); } } /* * If we're reading data that is part of the userspace workingset, count * submission time as memory stall. When the device is congested, or * the submitting cgroup IO-throttled, submission can be a significant * part of overall IO time. */ if (unlikely(bio_op(bio) == REQ_OP_READ && bio_flagged(bio, BIO_WORKINGSET))) { unsigned long pflags; blk_qc_t ret; psi_memstall_enter(&pflags); ret = submit_bio_noacct(bio); psi_memstall_leave(&pflags); return ret; } return submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** * blk_cloned_rq_check_limits - Helper function to check a cloned request * for the new queue limits * @q: the queue * @rq: the request being checked * * Description: * @rq may have been made based on weaker limitations of upper-level queues * in request stacking drivers, and it may violate the limitation of @q. * Since the block layer and the underlying device driver trust @rq * after it is inserted to @q, it should be checked against @q before * the insertion using this generic function. * * Request stacking drivers like request-based dm may change the queue * limits when retrying requests on other queues. Those requests need * to be checked against the new queue limits again during dispatch. */ static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q, struct request *rq) { unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * queue's settings related to segment counting like q->bounce_pfn * may differ from that of other stacking queues. * Recalculate it to check the request correctly on this queue's * limitation. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > queue_max_segments(q)) { printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n", __func__, rq->nr_phys_segments, queue_max_segments(q)); return BLK_STS_IOERR; } return BLK_STS_OK; } /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @q: the queue to submit the request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { blk_status_t ret; ret = blk_cloned_rq_check_limits(q, rq); if (ret != BLK_STS_OK) return ret; if (rq->rq_disk && should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) return BLK_STS_IOERR; if (blk_queue_io_stat(q)) blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ return blk_mq_request_issue_directly(rq, true); } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_err_bytes - determine number of bytes till the next failure boundary * @rq: request to examine * * Description: * A request could be merge of IOs which require different failure * handling. This function determines the number of bytes which * can be failed from the beginning of the request without * crossing into area which need to be retried further. * * Return: * The number of bytes to fail. */ unsigned int blk_rq_err_bytes(const struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; unsigned int bytes = 0; struct bio *bio; if (!(rq->rq_flags & RQF_MIXED_MERGE)) return blk_rq_bytes(rq); /* * Currently the only 'mixing' which can happen is between * different fastfail types. We can safely fail portions * which have all the failfast bits that the first one has - * the ones which are at least as eager to fail as the first * one. */ for (bio = rq->bio; bio; bio = bio->bi_next) { if ((bio->bi_opf & ff) != ff) break; bytes += bio->bi_iter.bi_size; } /* this could lead to infinite loop */ BUG_ON(blk_rq_bytes(rq) && !bytes); return bytes; } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) { unsigned long stamp; again: stamp = READ_ONCE(part->stamp); if (unlikely(stamp != now)) { if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->partno) { part = &part_to_disk(part)->part0; goto again; } } static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; part_stat_lock(); part = req->part; part_stat_add(part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } void blk_account_io_done(struct request *req, u64 now) { /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the * containing request is enough. */ if (req->part && blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; part_stat_lock(); part = req->part; update_io_ticks(part, jiffies, true); part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); hd_struct_put(part); } } void blk_account_io_start(struct request *rq) { if (!blk_do_io_stat(rq)) return; rq->part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); part_stat_lock(); update_io_ticks(rq->part, jiffies, false); part_stat_unlock(); } static unsigned long __part_start_io_acct(struct hd_struct *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); part_stat_lock(); update_io_ticks(part, now, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); return now; } unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, struct bio *bio) { *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio)); } EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { return __part_start_io_acct(&disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); static void __part_end_io_acct(struct hd_struct *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); update_io_ticks(part, now, true); part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); } void part_end_io_acct(struct hd_struct *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); hd_struct_put(part); } EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { __part_end_io_acct(&disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); /** * blk_update_request - Special helper function for request stacking drivers * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * This special helper function is only for request stacking drivers * (e.g. request-based dm) so that they can handle partial completion. * Actual device drivers should use blk_mq_end_request instead. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both * blk_rq_bytes() and in blk_update_request(). * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { int total_bytes; trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes); if (!req->bio) return false; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) req->q->integrity.profile->complete_fn(req, nr_bytes); #endif /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req)) __blk_crypto_rq_put_keyslot(req); if (unlikely(error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET))) print_req_error(req, error, __func__); blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (bio_bytes == bio->bi_iter.bi_size) req->bio = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); req_bio_endio(req, bio, bio_bytes, error); total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE /** * rq_flush_dcache_pages - Helper function to flush all pages in a request * @rq: the request to be flushed * * Description: * Flush all pages in @rq. */ void rq_flush_dcache_pages(struct request *rq) { struct req_iterator iter; struct bio_vec bvec; rq_for_each_segment(bvec, rq, iter) flush_dcache_page(bvec.bv_page); } EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); #endif /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */ int blk_lld_busy(struct request_queue *q) { if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; } EXPORT_SYMBOL_GPL(blk_lld_busy); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio, *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_clone_fast(bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) goto free_and_out; if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } bio = NULL; } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: if (bio) bio_put(bio); blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); int kblockd_schedule_work(struct work_struct *work) { return queue_work(kblockd_workqueue, work); } EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */ void blk_start_plug(struct blk_plug *plug) { struct task_struct *tsk = current; /* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return; INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); plug->rq_count = 0; plug->multiple_queues = false; plug->nowait = false; /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug; } EXPORT_SYMBOL(blk_start_plug); static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } } } struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size) { struct blk_plug *plug = current->plug; struct blk_plug_cb *cb; if (!plug) return NULL; list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb; /* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb; } EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { flush_plug_callbacks(plug, from_schedule); if (!list_empty(&plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); } /** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */ void blk_finish_plug(struct blk_plug *plug) { if (plug != current->plug) return; blk_flush_plug_list(plug, false); current->plug = NULL; } EXPORT_SYMBOL(blk_finish_plug); void blk_io_schedule(void) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) io_schedule_timeout(timeout); else io_schedule(); } EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n"); blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); blk_debugfs_root = debugfs_create_dir("block", NULL); return 0; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Supervisor Mode Access Prevention support * * Copyright (C) 2012 Intel Corporation * Author: H. Peter Anvin <hpa@linux.intel.com> */ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H #include <asm/nops.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" #define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #else /* __ASSEMBLY__ */ #ifdef CONFIG_X86_SMAP static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_CLAC, X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_STAC, X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) { unsigned long flags; asm volatile ("# smap_save\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "pushf; pop %0; " __ASM_CLAC "\n\t" "1:" : "=rm" (flags) : : "memory", "cc"); return flags; } static __always_inline void smap_restore(unsigned long flags) { asm volatile ("# smap_restore\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "push %0; popf\n\t" "1:" : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ static inline void clac(void) { } static inline void stac(void) { } static inline unsigned long smap_save(void) { return 0; } static inline void smap_restore(unsigned long flags) { } #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _LINUX_KPROBES_H #define _LINUX_KPROBES_H /* * Kernel Probes (KProbes) * include/linux/kprobes.h * * Copyright (C) IBM Corporation, 2002, 2004 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation ( includes suggestions from * Rusty Russell). * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes * interface to access function arguments. * 2005-May Hien Nguyen <hien@us.ibm.com> and Jim Keniston * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/bug.h> #include <linux/percpu.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/ftrace.h> #include <asm/kprobes.h> #ifdef CONFIG_KPROBES /* kprobe_status settings */ #define KPROBE_HIT_ACTIVE 0x00000001 #define KPROBE_HIT_SS 0x00000002 #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 #else /* CONFIG_KPROBES */ #include <asm-generic/kprobes.h> typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; }; #endif /* CONFIG_KPROBES */ struct kprobe; struct pt_regs; struct kretprobe; struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, int trapnr); typedef int (*kretprobe_handler_t) (struct kretprobe_instance *, struct pt_regs *); struct kprobe { struct hlist_node hlist; /* list of kprobes for multi-handler support */ struct list_head list; /*count the number of times this probe was temporarily disarmed */ unsigned long nmissed; /* location of the probe point */ kprobe_opcode_t *addr; /* Allow user to indicate symbol name of the probe point */ const char *symbol_name; /* Offset into the symbol */ unsigned int offset; /* Called before addr is executed. */ kprobe_pre_handler_t pre_handler; /* Called after addr is executed, unless... */ kprobe_post_handler_t post_handler; /* * ... called if executing addr causes a fault (eg. page fault). * Return 1 if it handled fault, otherwise kernel will see it. */ kprobe_fault_handler_t fault_handler; /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; /* copy of the original instruction */ struct arch_specific_insn ainsn; /* * Indicates various status flags. * Protected by kprobe_mutex after this kprobe is registered. */ u32 flags; }; /* Kprobe status flags */ #define KPROBE_FLAG_GONE 1 /* breakpoint has already gone */ #define KPROBE_FLAG_DISABLED 2 /* probe is temporarily disabled */ #define KPROBE_FLAG_OPTIMIZED 4 /* * probe is really optimized. * NOTE: * this flag is only for optimized_kprobe. */ #define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */ /* Has this kprobe gone ? */ static inline int kprobe_gone(struct kprobe *p) { return p->flags & KPROBE_FLAG_GONE; } /* Is this kprobe disabled ? */ static inline int kprobe_disabled(struct kprobe *p) { return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE); } /* Is this kprobe really running optimized path ? */ static inline int kprobe_optimized(struct kprobe *p) { return p->flags & KPROBE_FLAG_OPTIMIZED; } /* Is this kprobe uses ftrace ? */ static inline int kprobe_ftrace(struct kprobe *p) { return p->flags & KPROBE_FLAG_FTRACE; } /* * Function-return probe - * Note: * User needs to provide a handler function, and initialize maxactive. * maxactive - The maximum number of instances of the probed function that * can be active concurrently. * nmissed - tracks the number of times the probed function's return was * ignored, due to maxactive being too low. * */ struct kretprobe { struct kprobe kp; kretprobe_handler_t handler; kretprobe_handler_t entry_handler; int maxactive; int nmissed; size_t data_size; struct hlist_head free_instances; raw_spinlock_t lock; }; #define KRETPROBE_MAX_DATA_SIZE 4096 struct kretprobe_instance { union { struct hlist_node hlist; struct rcu_head rcu; }; struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; void *fp; char data[]; }; struct kretprobe_blackpoint { const char *name; void *addr; }; struct kprobe_blacklist_entry { struct list_head list; unsigned long start_addr; unsigned long end_addr; }; #ifdef CONFIG_KPROBES DECLARE_PER_CPU(struct kprobe *, current_kprobe); DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); /* * For #ifdef avoidance: */ static inline int kprobes_built_in(void) { return 1; } extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); #ifdef CONFIG_KRETPROBES extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); extern int arch_trampoline_kprobe(struct kprobe *p); /* If the trampoline handler called from a kprobe, use this version */ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer); static nokprobe_inline unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer) { unsigned long ret; /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never runs in kprobe handler, no kprobe must * be running at this point. */ kprobe_busy_begin(); ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer); kprobe_busy_end(); return ret; } #else /* CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { } static inline int arch_trampoline_kprobe(struct kprobe *p) { return 0; } #endif /* CONFIG_KRETPROBES */ extern struct kretprobe_blackpoint kretprobe_blacklist[]; #ifdef CONFIG_KPROBES_SANITY_TEST extern int init_test_probes(void); #else static inline int init_test_probes(void) { return 0; } #endif /* CONFIG_KPROBES_SANITY_TEST */ extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); extern int arch_init_kprobes(void); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); extern bool arch_kprobe_on_func_entry(unsigned long offset); extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); extern int kprobe_add_ksym_blacklist(unsigned long entry); extern int kprobe_add_area_blacklist(unsigned long start, unsigned long end); struct kprobe_insn_cache { struct mutex mutex; void *(*alloc)(void); /* allocate insn page */ void (*free)(void *); /* free insn page */ const char *sym; /* symbol for insn pages */ struct list_head pages; /* list of kprobe_insn_page */ size_t insn_size; /* size of instruction slot */ int nr_garbage; }; #ifdef __ARCH_WANT_KPROBES_INSN_SLOT extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c); extern void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty); /* sleep-less address checking routine */ extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr); #define DEFINE_INSN_CACHE_OPS(__name) \ extern struct kprobe_insn_cache kprobe_##__name##_slots; \ \ static inline kprobe_opcode_t *get_##__name##_slot(void) \ { \ return __get_insn_slot(&kprobe_##__name##_slots); \ } \ \ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\ { \ __free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \ } \ \ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ { \ return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \ } #define KPROBE_INSN_PAGE_SYM "kprobe_insn_page" #define KPROBE_OPTINSN_PAGE_SYM "kprobe_optinsn_page" int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, unsigned long *value, char *type, char *sym); #else /* __ARCH_WANT_KPROBES_INSN_SLOT */ #define DEFINE_INSN_CACHE_OPS(__name) \ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ { \ return 0; \ } #endif DEFINE_INSN_CACHE_OPS(insn); #ifdef CONFIG_OPTPROBES /* * Internal structure for direct jump optimized probe */ struct optimized_kprobe { struct kprobe kp; struct list_head list; /* list for optimizing queue */ struct arch_optimized_insn optinsn; }; /* Architecture dependent functions for direct jump optimization */ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *orig); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr); extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); #ifdef CONFIG_SYSCTL extern int sysctl_kprobes_optimization; extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif extern void wait_for_kprobe_optimizer(void); bool optprobe_queued_unopt(struct optimized_kprobe *op); bool kprobe_disarmed(struct kprobe *p); #else static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); #endif int arch_check_ftrace_location(struct kprobe *p); /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); /* kprobe_running() will just return the current_kprobe on this CPU */ static inline struct kprobe *kprobe_running(void) { return (__this_cpu_read(current_kprobe)); } static inline void reset_current_kprobe(void) { __this_cpu_write(current_kprobe, NULL); } static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) { return this_cpu_ptr(&kprobe_ctlblk); } kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void kprobe_free_init_mem(void); int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); void free_insn_page(void *page); int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym); #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) { return 0; } static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { return 0; } static inline struct kprobe *get_kprobe(void *addr) { return NULL; } static inline struct kprobe *kprobe_running(void) { return NULL; } static inline int register_kprobe(struct kprobe *p) { return -ENOSYS; } static inline int register_kprobes(struct kprobe **kps, int num) { return -ENOSYS; } static inline void unregister_kprobe(struct kprobe *p) { } static inline void unregister_kprobes(struct kprobe **kps, int num) { } static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } static inline int register_kretprobes(struct kretprobe **rps, int num) { return -ENOSYS; } static inline void unregister_kretprobe(struct kretprobe *rp) { } static inline void unregister_kretprobes(struct kretprobe **rps, int num) { } static inline void kprobe_flush_task(struct task_struct *tk) { } static inline void kprobe_free_init_mem(void) { } static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; } static inline int enable_kprobe(struct kprobe *kp) { return -ENOSYS; } static inline bool within_kprobe_blacklist(unsigned long addr) { return true; } static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } #endif /* CONFIG_KPROBES */ static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); } static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } #ifndef CONFIG_KPROBES static inline bool is_kprobe_insn_slot(unsigned long addr) { return false; } #endif #ifndef CONFIG_OPTPROBES static inline bool is_kprobe_optinsn_slot(unsigned long addr) { return false; } #endif /* Returns true if kprobes handled the fault */ static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs, unsigned int trap) { if (!kprobes_built_in()) return false; if (user_mode(regs)) return false; /* * To be potentially processing a kprobe fault and to be allowed * to call kprobe_running(), we have to be non-preemptible. */ if (preemptible()) return false; if (!kprobe_running()) return false; return kprobe_fault_handler(regs, trap); } #endif /* _LINUX_KPROBES_H */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/uaccess.h> #include <linux/nospec.h> /* out-of-line parts */ #ifndef INLINE_COPY_FROM_USER unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } EXPORT_SYMBOL(_copy_from_user); #endif #ifndef INLINE_COPY_TO_USER unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (likely(access_ok(to, n))) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } EXPORT_SYMBOL(_copy_to_user); #endif /** * check_zeroed_user: check if a userspace buffer only contains zero bytes * @from: Source address, in userspace. * @size: Size of buffer. * * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for * userspace addresses (and is more efficient because we don't care where the * first non-zero byte is). * * Returns: * * 0: There were non-zero bytes present in the buffer. * * 1: The buffer was full of zero bytes. * * -EFAULT: access to userspace failed. */ int check_zeroed_user(const void __user *from, size_t size) { unsigned long val; uintptr_t align = (uintptr_t) from % sizeof(unsigned long); if (unlikely(size == 0)) return 1; from -= align; size += align; if (!user_read_access_begin(from, size)) return -EFAULT; unsafe_get_user(val, (unsigned long __user *) from, err_fault); if (align) val &= ~aligned_byte_mask(align); while (size > sizeof(unsigned long)) { if (unlikely(val)) goto done; from += sizeof(unsigned long); size -= sizeof(unsigned long); unsafe_get_user(val, (unsigned long __user *) from, err_fault); } if (size < sizeof(unsigned long)) val &= aligned_byte_mask(size); done: user_read_access_end(); return (val == 0); err_fault: user_read_access_end(); return -EFAULT; } EXPORT_SYMBOL(check_zeroed_user); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | /* SPDX-License-Identifier: GPL-2.0 */ /* * memory buffer pool support */ #ifndef _LINUX_MEMPOOL_H #define _LINUX_MEMPOOL_H #include <linux/wait.h> #include <linux/compiler.h> struct kmem_cache; typedef void * (mempool_alloc_t)(gfp_t gfp_mask, void *pool_data); typedef void (mempool_free_t)(void *element, void *pool_data); typedef struct mempool_s { spinlock_t lock; int min_nr; /* nr of elements at *elements */ int curr_nr; /* Current nr of elements at *elements */ void **elements; void *pool_data; mempool_alloc_t *alloc; mempool_free_t *free; wait_queue_head_t wait; } mempool_t; static inline bool mempool_initialized(mempool_t *pool) { return pool->elements != NULL; } void mempool_exit(mempool_t *pool); int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id); int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int nid); extern int mempool_resize(mempool_t *pool, int new_min_nr); extern void mempool_destroy(mempool_t *pool); extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc; extern void mempool_free(void *element, mempool_t *pool); /* * A mempool_alloc_t and mempool_free_t that get the memory from * a slab cache that is passed in through pool_data. * Note: the slab cache may not have a ctor function. */ void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); static inline int mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc) { return mempool_init(pool, min_nr, mempool_alloc_slab, mempool_free_slab, (void *) kc); } static inline mempool_t * mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) { return mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab, (void *) kc); } /* * a mempool_alloc_t and a mempool_free_t to kmalloc and kfree the * amount of memory specified by pool_data */ void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kfree(void *element, void *pool_data); static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size) { return mempool_init(pool, min_nr, mempool_kmalloc, mempool_kfree, (void *) size); } static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) { return mempool_create(min_nr, mempool_kmalloc, mempool_kfree, (void *) size); } /* * A mempool_alloc_t and mempool_free_t for a simple page allocator that * allocates pages of the order specified by pool_data */ void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data); void mempool_free_pages(void *element, void *pool_data); static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order) { return mempool_init(pool, min_nr, mempool_alloc_pages, mempool_free_pages, (void *)(long)order); } static inline mempool_t *mempool_create_page_pool(int min_nr, int order) { return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages, (void *)(long)order); } #endif /* _LINUX_MEMPOOL_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/buffer_head.h * * Everything to do with buffer_heads. */ #ifndef _LINUX_BUFFER_HEAD_H #define _LINUX_BUFFER_HEAD_H #include <linux/types.h> #include <linux/fs.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/wait.h> #include <linux/atomic.h> #ifdef CONFIG_BLOCK enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ BH_Lock, /* Is locked */ BH_Req, /* Has been submitted for I/O */ BH_Mapped, /* Has a disk mapping */ BH_New, /* Disk mapping was newly created by get_block */ BH_Async_Read, /* Is under end_buffer_async_read I/O */ BH_Async_Write, /* Is under end_buffer_async_write I/O */ BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_Meta, /* Buffer contains metadata */ BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_Defer_Completion, /* Defer AIO completion to workqueue */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities */ }; #define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; struct address_space; typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); /* * Historically, a buffer_head was used to map a single block * within a page, and of course as the unit of I/O through the * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within * a page (via a page_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { unsigned long b_state; /* buffer state bitmap (see above) */ struct buffer_head *b_this_page;/* circular list of page's buffers */ struct page *b_page; /* the page this bh is mapped to */ sector_t b_blocknr; /* start block number */ size_t b_size; /* size of mapping */ char *b_data; /* pointer to data within the page */ struct block_device *b_bdev; bh_end_io_t *b_end_io; /* I/O completion */ void *b_private; /* reserved for b_end_io */ struct list_head b_assoc_buffers; /* associated with another mapping */ struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to * serialise IO completion of other * buffers in the page */ }; /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. * To avoid reset buffer flags that are already set, because that causes * a costly cache line transition, check the flag first. */ #define BUFFER_FNS(bit, name) \ static __always_inline void set_buffer_##name(struct buffer_head *bh) \ { \ if (!test_bit(BH_##bit, &(bh)->b_state)) \ set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline void clear_buffer_##name(struct buffer_head *bh) \ { \ clear_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int buffer_##name(const struct buffer_head *bh) \ { \ return test_bit(BH_##bit, &(bh)->b_state); \ } /* * test_set_buffer_foo() and test_clear_buffer_foo() */ #define TAS_BUFFER_FNS(bit, name) \ static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \ { \ return test_and_set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ { \ return test_and_clear_bit(BH_##bit, &(bh)->b_state); \ } \ /* * Emit the buffer bitops functions. Note that there are also functions * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) BUFFER_FNS(Req, req) TAS_BUFFER_FNS(Req, req) BUFFER_FNS(Mapped, mapped) BUFFER_FNS(New, new) BUFFER_FNS(Async_Read, async_read) BUFFER_FNS(Async_Write, async_write) BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) static __always_inline void set_buffer_uptodate(struct buffer_head *bh) { /* * If somebody else already set this uptodate, they will * have done the memory barrier, and a reader will thus * see *some* valid buffer state. * * Any other serialization (with IO errors or whatever that * might clear the bit) has to come from other state (eg BH_Lock). */ if (test_bit(BH_Uptodate, &bh->b_state)) return; /* * make it consistent with folio_mark_uptodate * pairs with smp_load_acquire in buffer_uptodate */ smp_mb__before_atomic(); set_bit(BH_Uptodate, &bh->b_state); } static __always_inline void clear_buffer_uptodate(struct buffer_head *bh) { clear_bit(BH_Uptodate, &bh->b_state); } static __always_inline int buffer_uptodate(const struct buffer_head *bh) { /* * make it consistent with folio_test_uptodate * pairs with smp_mb__before_atomic in set_buffer_uptodate */ return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0; } #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ ({ \ BUG_ON(!PagePrivate(page)); \ ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback); /* * Declarations */ void mark_buffer_dirty(struct buffer_head *bh); void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); int try_to_free_buffers(struct page *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); /* Things to do with buffers at mapping->private_list */ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode); int inode_has_buffers(struct inode *); void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) { clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1); } void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); void ll_rw_block(int, int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); void write_dirty_buffer(struct buffer_head *bh, int op_flags); int submit_bh(int, int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); extern int buffer_heads_over_limit; /* * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int nobh_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); void buffer_init(void); /* * inline definitions */ static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); } static inline void put_bh(struct buffer_head *bh) { smp_mb__before_atomic(); atomic_dec(&bh->b_count); } static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } static inline void bforget(struct buffer_head *bh) { if (bh) __bforget(bh); } static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_bread_unmovable(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void sb_breadahead(struct super_block *sb, sector_t block) { __breadahead(sb->s_bdev, block, sb->s_blocksize); } static inline void sb_breadahead_unmovable(struct super_block *sb, sector_t block) { __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { return __find_get_block(sb->s_bdev, block, sb->s_blocksize); } static inline void map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block) { set_buffer_mapped(bh); bh->b_bdev = sb->s_bdev; bh->b_blocknr = block; bh->b_size = sb->s_blocksize; } static inline void wait_on_buffer(struct buffer_head *bh) { might_sleep(); if (buffer_locked(bh)) __wait_on_buffer(bh); } static inline int trylock_buffer(struct buffer_head *bh) { return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state)); } static inline void lock_buffer(struct buffer_head *bh) { might_sleep(); if (!trylock_buffer(bh)) __lock_buffer(bh); } static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, 0); } static inline struct buffer_head *__getblk(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * * Reads a specified block, and returns buffer head that contains it. * The page cache is allocated from movable area so that it can be migrated. * It returns NULL if the block was unreadable. */ static inline struct buffer_head * __bread(struct block_device *bdev, sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } extern int __set_page_dirty_buffers(struct page *page); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} static inline int try_to_free_buffers(struct page *page) { return 1; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk> */ #include <linux/mm.h> #include <linux/swap.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/uio.h> #include <linux/iocontext.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/cgroup.h> #include <linux/blk-cgroup.h> #include <linux/highmem.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" /* * Test patch to inline a certain number of bi_io_vec's inside the bio * itself, to shrink a bio data allocation from two mempool calls to one */ #define BIO_INLINE_VECS 4 /* * if you change this list, also change bvec_alloc or things will * break badly! cannot be bigger than what you can fit into an * unsigned short */ #define BV(x, n) { .nr_vecs = x, .name = "biovec-"#n } static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = { BV(1, 1), BV(4, 4), BV(16, 16), BV(64, 64), BV(128, 128), BV(BIO_MAX_PAGES, max), }; #undef BV /* * fs_bio_set is the bio_set containing bio and iovec memory pools used by * IO code that does not need private memory pools. */ struct bio_set fs_bio_set; EXPORT_SYMBOL(fs_bio_set); /* * Our slab pool management */ struct bio_slab { struct kmem_cache *slab; unsigned int slab_ref; unsigned int slab_size; char name[12]; }; static DEFINE_MUTEX(bio_slab_lock); static struct bio_slab *bio_slabs; static unsigned int bio_slab_nr, bio_slab_max; static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) { unsigned int sz = sizeof(struct bio) + extra_size; struct kmem_cache *slab = NULL; struct bio_slab *bslab, *new_bio_slabs; unsigned int new_bio_slab_max; unsigned int i, entry = -1; mutex_lock(&bio_slab_lock); i = 0; while (i < bio_slab_nr) { bslab = &bio_slabs[i]; if (!bslab->slab && entry == -1) entry = i; else if (bslab->slab_size == sz) { slab = bslab->slab; bslab->slab_ref++; break; } i++; } if (slab) goto out_unlock; if (bio_slab_nr == bio_slab_max && entry == -1) { new_bio_slab_max = bio_slab_max << 1; new_bio_slabs = krealloc(bio_slabs, new_bio_slab_max * sizeof(struct bio_slab), GFP_KERNEL); if (!new_bio_slabs) goto out_unlock; bio_slab_max = new_bio_slab_max; bio_slabs = new_bio_slabs; } if (entry == -1) entry = bio_slab_nr++; bslab = &bio_slabs[entry]; snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry); slab = kmem_cache_create(bslab->name, sz, ARCH_KMALLOC_MINALIGN, SLAB_HWCACHE_ALIGN, NULL); if (!slab) goto out_unlock; bslab->slab = slab; bslab->slab_ref = 1; bslab->slab_size = sz; out_unlock: mutex_unlock(&bio_slab_lock); return slab; } static void bio_put_slab(struct bio_set *bs) { struct bio_slab *bslab = NULL; unsigned int i; mutex_lock(&bio_slab_lock); for (i = 0; i < bio_slab_nr; i++) { if (bs->bio_slab == bio_slabs[i].slab) { bslab = &bio_slabs[i]; break; } } if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n")) goto out; WARN_ON(!bslab->slab_ref); if (--bslab->slab_ref) goto out; kmem_cache_destroy(bslab->slab); bslab->slab = NULL; out: mutex_unlock(&bio_slab_lock); } unsigned int bvec_nr_vecs(unsigned short idx) { return bvec_slabs[--idx].nr_vecs; } void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx) { if (!idx) return; idx--; BIO_BUG_ON(idx >= BVEC_POOL_NR); if (idx == BVEC_POOL_MAX) { mempool_free(bv, pool); } else { struct biovec_slab *bvs = bvec_slabs + idx; kmem_cache_free(bvs->slab, bv); } } struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx, mempool_t *pool) { struct bio_vec *bvl; /* * see comment near bvec_array define! */ switch (nr) { case 1: *idx = 0; break; case 2 ... 4: *idx = 1; break; case 5 ... 16: *idx = 2; break; case 17 ... 64: *idx = 3; break; case 65 ... 128: *idx = 4; break; case 129 ... BIO_MAX_PAGES: *idx = 5; break; default: return NULL; } /* * idx now points to the pool we want to allocate from. only the * 1-vec entry pool is mempool backed. */ if (*idx == BVEC_POOL_MAX) { fallback: bvl = mempool_alloc(pool, gfp_mask); } else { struct biovec_slab *bvs = bvec_slabs + *idx; gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO); /* * Make this allocation restricted and don't dump info on * allocation failures, since we'll fallback to the mempool * in case of failure. */ __gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; /* * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM * is set, retry with the 1-entry mempool */ bvl = kmem_cache_alloc(bvs->slab, __gfp_mask); if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) { *idx = BVEC_POOL_MAX; goto fallback; } } (*idx)++; return bvl; } void bio_uninit(struct bio *bio) { #ifdef CONFIG_BLK_CGROUP if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; } #endif if (bio_integrity(bio)) bio_integrity_free(bio); bio_crypt_free_ctx(bio); } EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; void *p; bio_uninit(bio); if (bs) { bvec_free(&bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio)); /* * If we have front padding, adjust the bio pointer before freeing */ p = bio; p -= bs->front_pad; mempool_free(p, &bs->bio_pool); } else { /* Bio was allocated by bio_kmalloc() */ kfree(bio); } } /* * Users of this function have their own bio allocation. Subsequently, * they must remember to pair any call to bio_init() with bio_uninit() * when IO has completed, or when the bio is released. */ void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs) { memset(bio, 0, sizeof(*bio)); atomic_set(&bio->__bi_remaining, 1); atomic_set(&bio->__bi_cnt, 1); bio->bi_io_vec = table; bio->bi_max_vecs = max_vecs; } EXPORT_SYMBOL(bio_init); /** * bio_reset - reinitialize a bio * @bio: bio to reset * * Description: * After calling bio_reset(), @bio will be in the same state as a freshly * allocated bio returned bio bio_alloc_bioset() - the only fields that are * preserved are the ones that are initialized by bio_alloc_bioset(). See * comment in struct bio. */ void bio_reset(struct bio *bio) { unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS); bio_uninit(bio); memset(bio, 0, BIO_RESET_BYTES); bio->bi_flags = flags; atomic_set(&bio->__bi_remaining, 1); } EXPORT_SYMBOL(bio_reset); static struct bio *__bio_chain_endio(struct bio *bio) { struct bio *parent = bio->bi_private; if (bio->bi_status && !parent->bi_status) parent->bi_status = bio->bi_status; bio_put(bio); return parent; } static void bio_chain_endio(struct bio *bio) { bio_endio(__bio_chain_endio(bio)); } /** * bio_chain - chain bio completions * @bio: the target bio * @parent: the parent bio of @bio * * The caller won't have a bi_end_io called when @bio completes - instead, * @parent's bi_end_io won't be called until both @parent and @bio have * completed; the chained bio will also be freed when it completes. * * The caller must not set bi_private or bi_end_io in @bio. */ void bio_chain(struct bio *bio, struct bio *parent) { BUG_ON(bio->bi_private || bio->bi_end_io); bio->bi_private = parent; bio->bi_end_io = bio_chain_endio; bio_inc_remaining(parent); } EXPORT_SYMBOL(bio_chain); static void bio_alloc_rescue(struct work_struct *work) { struct bio_set *bs = container_of(work, struct bio_set, rescue_work); struct bio *bio; while (1) { spin_lock(&bs->rescue_lock); bio = bio_list_pop(&bs->rescue_list); spin_unlock(&bs->rescue_lock); if (!bio) break; submit_bio_noacct(bio); } } static void punt_bios_to_rescuer(struct bio_set *bs) { struct bio_list punt, nopunt; struct bio *bio; if (WARN_ON_ONCE(!bs->rescue_workqueue)) return; /* * In order to guarantee forward progress we must punt only bios that * were allocated from this bio_set; otherwise, if there was a bio on * there for a stacking driver higher up in the stack, processing it * could require allocating bios from this bio_set, and doing that from * our own rescuer would be bad. * * Since bio lists are singly linked, pop them all instead of trying to * remove from the middle of the list: */ bio_list_init(&punt); bio_list_init(&nopunt); while ((bio = bio_list_pop(¤t->bio_list[0]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); current->bio_list[0] = nopunt; bio_list_init(&nopunt); while ((bio = bio_list_pop(¤t->bio_list[1]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); current->bio_list[1] = nopunt; spin_lock(&bs->rescue_lock); bio_list_merge(&bs->rescue_list, &punt); spin_unlock(&bs->rescue_lock); queue_work(bs->rescue_workqueue, &bs->rescue_work); } /** * bio_alloc_bioset - allocate a bio for I/O * @gfp_mask: the GFP_* mask given to the slab allocator * @nr_iovecs: number of iovecs to pre-allocate * @bs: the bio_set to allocate from. * * Description: * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is * backed by the @bs's mempool. * * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will * always be able to allocate a bio. This is due to the mempool guarantees. * To make this work, callers must never allocate more than 1 bio at a time * from this pool. Callers that need to allocate more than 1 bio must always * submit the previously allocated bio for IO before attempting to allocate * a new one. Failure to do so can cause deadlocks under memory pressure. * * Note that when running under submit_bio_noacct() (i.e. any block * driver), bios are not submitted until after you return - see the code in * submit_bio_noacct() that converts recursion into iteration, to prevent * stack overflows. * * This would normally mean allocating multiple bios under * submit_bio_noacct() would be susceptible to deadlocks, but we have * deadlock avoidance code that resubmits any blocked bios from a rescuer * thread. * * However, we do not guarantee forward progress for allocations from other * mempools. Doing multiple allocations from the same mempool under * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * * RETURNS: * Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, struct bio_set *bs) { gfp_t saved_gfp = gfp_mask; unsigned front_pad; unsigned inline_vecs; struct bio_vec *bvl = NULL; struct bio *bio; void *p; if (!bs) { if (nr_iovecs > UIO_MAXIOV) return NULL; p = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask); front_pad = 0; inline_vecs = nr_iovecs; } else { /* should not use nobvec bioset for nr_iovecs > 0 */ if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_iovecs > 0)) return NULL; /* * submit_bio_noacct() converts recursion to iteration; this * means if we're running beneath it, any bios we allocate and * submit will not be submitted (and thus freed) until after we * return. * * This exposes us to a potential deadlock if we allocate * multiple bios from the same bio_set() while running * underneath submit_bio_noacct(). If we were to allocate * multiple bios (say a stacking block driver that was splitting * bios), we would deadlock if we exhausted the mempool's * reserve. * * We solve this, and guarantee forward progress, with a rescuer * workqueue per bio_set. If we go to allocate and there are * bios on current->bio_list, we first try the allocation * without __GFP_DIRECT_RECLAIM; if that fails, we punt those * bios we would be blocking to the rescuer workqueue before * we retry with the original gfp_flags. */ if (current->bio_list && (!bio_list_empty(¤t->bio_list[0]) || !bio_list_empty(¤t->bio_list[1])) && bs->rescue_workqueue) gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(&bs->bio_pool, gfp_mask); if (!p && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; p = mempool_alloc(&bs->bio_pool, gfp_mask); } front_pad = bs->front_pad; inline_vecs = BIO_INLINE_VECS; } if (unlikely(!p)) return NULL; bio = p + front_pad; bio_init(bio, NULL, 0); if (nr_iovecs > inline_vecs) { unsigned long idx = 0; bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool); if (!bvl && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool); } if (unlikely(!bvl)) goto err_free; bio->bi_flags |= idx << BVEC_POOL_OFFSET; } else if (nr_iovecs) { bvl = bio->bi_inline_vecs; } bio->bi_pool = bs; bio->bi_max_vecs = nr_iovecs; bio->bi_io_vec = bvl; return bio; err_free: mempool_free(p, &bs->bio_pool); return NULL; } EXPORT_SYMBOL(bio_alloc_bioset); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) { unsigned long flags; struct bio_vec bv; struct bvec_iter iter; __bio_for_each_segment(bv, bio, iter, start) { char *data = bvec_kmap_irq(&bv, &flags); memset(data, 0, bv.bv_len); flush_dcache_page(bv.bv_page); bvec_kunmap_irq(data, &flags); } } EXPORT_SYMBOL(zero_fill_bio_iter); /** * bio_truncate - truncate the bio to small size of @new_size * @bio: the bio to be truncated * @new_size: new size for truncating the bio * * Description: * Truncate the bio to new size of @new_size. If bio_op(bio) is * REQ_OP_READ, zero the truncated part. This function should only * be used for handling corner cases, such as bio eod. */ void bio_truncate(struct bio *bio, unsigned new_size) { struct bio_vec bv; struct bvec_iter iter; unsigned int done = 0; bool truncated = false; if (new_size >= bio->bi_iter.bi_size) return; if (bio_op(bio) != REQ_OP_READ) goto exit; bio_for_each_segment(bv, bio, iter) { if (done + bv.bv_len > new_size) { unsigned offset; if (!truncated) offset = new_size - done; else offset = 0; zero_user(bv.bv_page, bv.bv_offset + offset, bv.bv_len - offset); truncated = true; } done += bv.bv_len; } exit: /* * Don't touch bvec table here and make it really immutable, since * fs bio user has to retrieve all pages via bio_for_each_segment_all * in its .end_bio() callback. * * It is enough to truncate bio by updating .bi_size since we can make * correct bvec with the updated .bi_size for drivers. */ bio->bi_iter.bi_size = new_size; } /** * guard_bio_eod - truncate a BIO to fit the block device * @bio: bio to truncate * * This allows us to do IO even on the odd last sectors of a device, even if the * block size is some multiple of the physical sector size. * * We'll just truncate the bio to the size of the device, and clear the end of * the buffer head manually. Truly out-of-range accesses will turn into actual * I/O errors, this only handles the "we need to be able to do I/O at the final * sector" case. */ void guard_bio_eod(struct bio *bio) { sector_t maxsector; struct hd_struct *part; rcu_read_lock(); part = __disk_get_part(bio->bi_disk, bio->bi_partno); if (part) maxsector = part_nr_sects_read(part); else maxsector = get_capacity(bio->bi_disk); rcu_read_unlock(); if (!maxsector) return; /* * If the *whole* IO is past the end of the device, * let it through, and the IO layer will turn it into * an EIO. */ if (unlikely(bio->bi_iter.bi_sector >= maxsector)) return; maxsector -= bio->bi_iter.bi_sector; if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) return; bio_truncate(bio, maxsector << 9); } /** * bio_put - release a reference to a bio * @bio: bio to release reference to * * Description: * Put a reference to a &struct bio, either one you have gotten with * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it. **/ void bio_put(struct bio *bio) { if (!bio_flagged(bio, BIO_REFFED)) bio_free(bio); else { BIO_BUG_ON(!atomic_read(&bio->__bi_cnt)); /* * last put frees it */ if (atomic_dec_and_test(&bio->__bi_cnt)) bio_free(bio); } } EXPORT_SYMBOL(bio_put); /** * __bio_clone_fast - clone a bio that shares the original bio's biovec * @bio: destination bio * @bio_src: bio to clone * * Clone a &bio. Caller will own the returned bio, but not * the actual data it points to. Reference count of returned * bio will be one. * * Caller must ensure that @bio_src is not freed before @bio. */ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) { BUG_ON(bio->bi_pool && BVEC_POOL_IDX(bio)); /* * most users will be overriding ->bi_disk with a new target, * so we don't set nor calculate new physical/hw segment counts here */ bio->bi_disk = bio_src->bi_disk; bio->bi_partno = bio_src->bi_partno; bio_set_flag(bio, BIO_CLONED); if (bio_flagged(bio_src, BIO_THROTTLED)) bio_set_flag(bio, BIO_THROTTLED); bio->bi_opf = bio_src->bi_opf; bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; bio_clone_blkg_association(bio, bio_src); blkcg_bio_issue_init(bio); } EXPORT_SYMBOL(__bio_clone_fast); /** * bio_clone_fast - clone a bio that shares the original bio's biovec * @bio: bio to clone * @gfp_mask: allocation priority * @bs: bio_set to allocate from * * Like __bio_clone_fast, only also allocates the returned bio */ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) { struct bio *b; b = bio_alloc_bioset(gfp_mask, 0, bs); if (!b) return NULL; __bio_clone_fast(b, bio); if (bio_crypt_clone(b, bio, gfp_mask) < 0) goto err_put; if (bio_integrity(bio) && bio_integrity_clone(b, bio, gfp_mask) < 0) goto err_put; return b; err_put: bio_put(b); return NULL; } EXPORT_SYMBOL(bio_clone_fast); const char *bio_devname(struct bio *bio, char *buf) { return disk_name(bio->bi_disk, bio->bi_partno, buf); } EXPORT_SYMBOL(bio_devname); static inline bool page_is_mergeable(const struct bio_vec *bv, struct page *page, unsigned int len, unsigned int off, bool *same_page) { size_t bv_end = bv->bv_offset + bv->bv_len; phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1; phys_addr_t page_addr = page_to_phys(page); if (vec_end_addr + 1 != page_addr + off) return false; if (xen_domain() && !xen_biovec_phys_mergeable(bv, page)) return false; *same_page = ((vec_end_addr & PAGE_MASK) == page_addr); if (*same_page) return true; return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE); } /* * Try to merge a page into a segment, while obeying the hardware segment * size limit. This is not for normal read/write bios, but for passthrough * or Zone Append operations that we can't split. */ static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio, struct page *page, unsigned len, unsigned offset, bool *same_page) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset; phys_addr_t addr2 = page_to_phys(page) + offset + len - 1; if ((addr1 | mask) != (addr2 | mask)) return false; if (len > queue_max_segment_size(q) - bv->bv_len) return false; return __bio_try_merge_page(bio, page, len, offset, same_page); } /** * bio_add_hw_page - attempt to add a page to a bio with hw constraints * @q: the target queue * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset * @max_sectors: maximum number of sectors that can be added * @same_page: return if the segment has been merged inside the same page * * Add a page to a bio while respecting the hardware max_sectors, max_segment * and gap limitations. */ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page) { struct bio_vec *bvec; if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors) return 0; if (bio->bi_vcnt > 0) { if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page)) return len; /* * If the queue doesn't support SG gaps and adding this segment * would create a gap, disallow it. */ bvec = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (bvec_gap_to_prev(q, bvec, offset)) return 0; } if (bio_full(bio, len)) return 0; if (bio->bi_vcnt >= queue_max_segments(q)) return 0; bvec = &bio->bi_io_vec[bio->bi_vcnt]; bvec->bv_page = page; bvec->bv_len = len; bvec->bv_offset = offset; bio->bi_vcnt++; bio->bi_iter.bi_size += len; return len; } /** * bio_add_pc_page - attempt to add page to passthrough bio * @q: the target queue * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset * * Attempt to add a page to the bio_vec maplist. This can fail for a * number of reasons, such as the bio being full or target block device * limitations. The target block device must allow bio's up to PAGE_SIZE, * so it is always possible to add a single page to an empty bio. * * This should only be used by passthrough bios. */ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; return bio_add_hw_page(q, bio, page, len, offset, queue_max_hw_sectors(q), &same_page); } EXPORT_SYMBOL(bio_add_pc_page); /** * __bio_try_merge_page - try appending data to an existing bvec. * @bio: destination bio * @page: start page to add * @len: length of the data to add * @off: offset of the data relative to @page * @same_page: return if the segment has been merged inside the same page * * Try to add the data at @page + @off to the last bvec of @bio. This is a * useful optimisation for file systems with a block size smaller than the * page size. * * Warn if (@len, @off) crosses pages in case that @same_page is true. * * Return %true on success or %false on failure. */ bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool *same_page) { if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return false; if (bio->bi_vcnt > 0) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { if (bio->bi_iter.bi_size > UINT_MAX - len) { *same_page = false; return false; } bv->bv_len += len; bio->bi_iter.bi_size += len; return true; } } return false; } EXPORT_SYMBOL_GPL(__bio_try_merge_page); /** * __bio_add_page - add page(s) to a bio in a new segment * @bio: destination bio * @page: start page to add * @len: length of the data to add, may cross pages * @off: offset of the data relative to @page, may cross pages * * Add the data at @page + @off to @bio as a new bvec. The caller must ensure * that @bio has space for another bvec. */ void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); bv->bv_page = page; bv->bv_offset = off; bv->bv_len = len; bio->bi_iter.bi_size += len; bio->bi_vcnt++; if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page))) bio_set_flag(bio, BIO_WORKINGSET); } EXPORT_SYMBOL_GPL(__bio_add_page); /** * bio_add_page - attempt to add page(s) to bio * @bio: destination bio * @page: start page to add * @len: vec entry length, may cross pages * @offset: vec entry offset relative to @page, may cross pages * * Attempt to add page(s) to the bio_vec maplist. This will only fail * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. */ int bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) { if (bio_full(bio, len)) return 0; __bio_add_page(bio, page, len, offset); } return len; } EXPORT_SYMBOL(bio_add_page); void bio_release_pages(struct bio *bio, bool mark_dirty) { struct bvec_iter_all iter_all; struct bio_vec *bvec; if (bio_flagged(bio, BIO_NO_PAGE_REF)) return; bio_for_each_segment_all(bvec, bio, iter_all) { if (mark_dirty) set_page_dirty_lock(bvec->bv_page); put_page(bvec->bv_page); } } EXPORT_SYMBOL_GPL(bio_release_pages); static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter) { const struct bio_vec *bv = iter->bvec; unsigned int len; size_t size; if (WARN_ON_ONCE(iter->iov_offset > bv->bv_len)) return -EINVAL; len = min_t(size_t, bv->bv_len - iter->iov_offset, iter->count); size = bio_add_page(bio, bv->bv_page, len, bv->bv_offset + iter->iov_offset); if (unlikely(size != len)) return -EINVAL; iov_iter_advance(iter, size); return 0; } static void bio_put_pages(struct page **pages, size_t size, size_t off) { size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE); for (i = 0; i < nr; i++) put_page(pages[i]); } #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. * For multi-segment *iter, this function only adds pages from the * next non-empty segment of the iov iterator. */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; bool same_page = false; ssize_t size, left; unsigned len, i; size_t offset; /* * Move page array up in the allocated memory for the bio vecs as far as * possible so that we can start filling biovecs from the beginning * without overwriting the temporary page array. */ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; for (left = size, i = 0; left > 0; left -= len, i++) { struct page *page = pages[i]; len = min_t(size_t, PAGE_SIZE - offset, left); if (__bio_try_merge_page(bio, page, len, offset, &same_page)) { if (same_page) put_page(page); } else { if (WARN_ON_ONCE(bio_full(bio, len))) { bio_put_pages(pages + i, left, offset); return -EINVAL; } __bio_add_page(bio, page, len, offset); } offset = 0; } iov_iter_advance(iter, size); return 0; } static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter) { unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct request_queue *q = bio->bi_disk->queue; unsigned int max_append_sectors = queue_max_zone_append_sectors(q); struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; ssize_t size, left; unsigned len, i; size_t offset; int ret = 0; /* * Move page array up in the allocated memory for the bio vecs as far as * possible so that we can start filling biovecs from the beginning * without overwriting the temporary page array. */ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; for (left = size, i = 0; left > 0; left -= len, i++) { struct page *page = pages[i]; bool same_page = false; len = min_t(size_t, PAGE_SIZE - offset, left); if (bio_add_hw_page(q, bio, page, len, offset, max_append_sectors, &same_page) != len) { bio_put_pages(pages + i, left, offset); ret = -EINVAL; break; } if (same_page) put_page(page); offset = 0; } iov_iter_advance(iter, size - left); return ret; } /** * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be added * * This takes either an iterator pointing to user memory, or one pointing to * kernel pages (BVEC iterator). If we're adding user pages, we pin them and * map them into the kernel. On IO completion, the caller should put those * pages. If we're adding kernel pages, and the caller told us it's safe to * do so, we just have to add the pages to the bio directly. We don't grab an * extra reference to those pages (the user should already have that), and we * don't put the page on IO completion. The caller needs to check if the bio is * flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be * released. * * The function tries, but does not guarantee, to pin as many pages as * fit into the bio, or are requested in @iter, whatever is smaller. If * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { const bool is_bvec = iov_iter_is_bvec(iter); int ret; if (WARN_ON_ONCE(bio->bi_vcnt)) return -EINVAL; do { if (bio_op(bio) == REQ_OP_ZONE_APPEND) { if (WARN_ON_ONCE(is_bvec)) return -EINVAL; ret = __bio_iov_append_get_pages(bio, iter); } else { if (is_bvec) ret = __bio_iov_bvec_add_pages(bio, iter); else ret = __bio_iov_iter_get_pages(bio, iter); } } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); if (is_bvec) bio_set_flag(bio, BIO_NO_PAGE_REF); return bio->bi_vcnt ? 0 : ret; } EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) { complete(bio->bi_private); } /** * submit_bio_wait - submit a bio, and wait until it completes * @bio: The &struct bio which describes the I/O * * Simple wrapper around submit_bio(). Returns 0 on success, or the error from * bio_endio() on failure. * * WARNING: Unlike to how submit_bio() is usually used, this function does not * result in bio reference to be consumed. The caller must drop the reference * on his own. */ int submit_bio_wait(struct bio *bio) { DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map); unsigned long hang_check; bio->bi_private = &done; bio->bi_end_io = submit_bio_wait_endio; bio->bi_opf |= REQ_SYNC; submit_bio(bio); /* Prevent hang_check timer from firing at us during very long I/O */ hang_check = sysctl_hung_task_timeout_secs; if (hang_check) while (!wait_for_completion_io_timeout(&done, hang_check * (HZ/2))) ; else wait_for_completion_io(&done); return blk_status_to_errno(bio->bi_status); } EXPORT_SYMBOL(submit_bio_wait); /** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance * @bytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will * be updated on the last bvec as well. * * @bio will then represent the remaining, uncompleted portion of the io. */ void bio_advance(struct bio *bio, unsigned bytes) { if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); bio_crypt_advance(bio, bytes); bio_advance_iter(bio, &bio->bi_iter, bytes); } EXPORT_SYMBOL(bio_advance); void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter) { struct bio_vec src_bv, dst_bv; void *src_p, *dst_p; unsigned bytes; while (src_iter->bi_size && dst_iter->bi_size) { src_bv = bio_iter_iovec(src, *src_iter); dst_bv = bio_iter_iovec(dst, *dst_iter); bytes = min(src_bv.bv_len, dst_bv.bv_len); src_p = kmap_atomic(src_bv.bv_page); dst_p = kmap_atomic(dst_bv.bv_page); memcpy(dst_p + dst_bv.bv_offset, src_p + src_bv.bv_offset, bytes); kunmap_atomic(dst_p); kunmap_atomic(src_p); flush_dcache_page(dst_bv.bv_page); bio_advance_iter(src, src_iter, bytes); bio_advance_iter(dst, dst_iter, bytes); } } EXPORT_SYMBOL(bio_copy_data_iter); /** * bio_copy_data - copy contents of data buffers from one bio to another * @src: source bio * @dst: destination bio * * Stops when it reaches the end of either @src or @dst - that is, copies * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios). */ void bio_copy_data(struct bio *dst, struct bio *src) { struct bvec_iter src_iter = src->bi_iter; struct bvec_iter dst_iter = dst->bi_iter; bio_copy_data_iter(dst, &dst_iter, src, &src_iter); } EXPORT_SYMBOL(bio_copy_data); /** * bio_list_copy_data - copy contents of data buffers from one chain of bios to * another * @src: source bio list * @dst: destination bio list * * Stops when it reaches the end of either the @src list or @dst list - that is, * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of * bios). */ void bio_list_copy_data(struct bio *dst, struct bio *src) { struct bvec_iter src_iter = src->bi_iter; struct bvec_iter dst_iter = dst->bi_iter; while (1) { if (!src_iter.bi_size) { src = src->bi_next; if (!src) break; src_iter = src->bi_iter; } if (!dst_iter.bi_size) { dst = dst->bi_next; if (!dst) break; dst_iter = dst->bi_iter; } bio_copy_data_iter(dst, &dst_iter, src, &src_iter); } } EXPORT_SYMBOL(bio_list_copy_data); void bio_free_pages(struct bio *bio) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) __free_page(bvec->bv_page); } EXPORT_SYMBOL(bio_free_pages); /* * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * * The problem is that we cannot run set_page_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * * We special-case compound pages here: normally this means reads into hugetlb * pages. The logic in here doesn't really work right for compound pages * because the VM does not uniformly chase down the head page in all cases. * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't * handle them at all. So we skip compound pages here at an early stage. * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. * But other code (eg, flusher threads) could clean the pages if they are mapped * pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the * deferred bio dirtying paths. */ /* * bio_set_pages_dirty() will mark all the bio's pages as dirty. */ void bio_set_pages_dirty(struct bio *bio) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { set_page_dirty_lock(bvec->bv_page); } } /* * bio_check_pages_dirty() will check that all the BIO's pages are still dirty. * If they are, then fine. If, however, some pages are clean then they must * have been written out during the direct-IO read. So we take another ref on * the BIO and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from * here on. It will run one put_page() against each page and will run one * bio_put() against the BIO. */ static void bio_dirty_fn(struct work_struct *work); static DECLARE_WORK(bio_dirty_work, bio_dirty_fn); static DEFINE_SPINLOCK(bio_dirty_lock); static struct bio *bio_dirty_list; /* * This runs in process context */ static void bio_dirty_fn(struct work_struct *work) { struct bio *bio, *next; spin_lock_irq(&bio_dirty_lock); next = bio_dirty_list; bio_dirty_list = NULL; spin_unlock_irq(&bio_dirty_lock); while ((bio = next) != NULL) { next = bio->bi_private; bio_release_pages(bio, true); bio_put(bio); } } void bio_check_pages_dirty(struct bio *bio) { struct bio_vec *bvec; unsigned long flags; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { if (!PageDirty(bvec->bv_page)) goto defer; } bio_release_pages(bio, false); bio_put(bio); return; defer: spin_lock_irqsave(&bio_dirty_lock, flags); bio->bi_private = bio_dirty_list; bio_dirty_list = bio; spin_unlock_irqrestore(&bio_dirty_lock, flags); schedule_work(&bio_dirty_work); } static inline bool bio_remaining_done(struct bio *bio) { /* * If we're not chaining, then ->__bi_remaining is always 1 and * we always end io on the first invocation. */ if (!bio_flagged(bio, BIO_CHAIN)) return true; BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); if (atomic_dec_and_test(&bio->__bi_remaining)) { bio_clear_flag(bio, BIO_CHAIN); return true; } return false; } /** * bio_endio - end I/O on a bio * @bio: bio * * Description: * bio_endio() will end I/O on the whole bio. bio_endio() is the preferred * way to end I/O on a bio. No one should call bi_end_io() directly on a * bio unless they own it and thus know that it has an end_io function. * * bio_endio() can be called several times on a bio that has been chained * using bio_chain(). The ->bi_end_io() function will only be called the * last time. At this point the BLK_TA_COMPLETE tracing event will be * generated if BIO_TRACE_COMPLETION is set. **/ void bio_endio(struct bio *bio) { again: if (!bio_remaining_done(bio)) return; if (!bio_integrity_endio(bio)) return; if (bio->bi_disk && bio_flagged(bio, BIO_TRACKED)) rq_qos_done_bio(bio->bi_disk->queue, bio); /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that * save/restore bi_end_io) - however, we want to avoid unbounded * recursion and blowing the stack. Tail call optimization would * handle this, but compiling with frame pointers also disables * gcc's sibling call optimization. */ if (bio->bi_end_io == bio_chain_endio) { bio = __bio_chain_endio(bio); goto again; } if (bio->bi_disk && bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_complete(bio->bi_disk->queue, bio); bio_clear_flag(bio, BIO_TRACE_COMPLETION); } blk_throtl_bio_endio(bio); /* release cgroup info */ bio_uninit(bio); if (bio->bi_end_io) bio->bi_end_io(bio); } EXPORT_SYMBOL(bio_endio); /** * bio_split - split a bio * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Allocates and returns a new bio which represents @sectors from the start of * @bio, and updates @bio to represent the remaining sectors. * * Unless this is a discard request the newly allocated bio will point * to @bio's bi_io_vec. It is the caller's responsibility to ensure that * neither @bio nor @bs are freed before the split bio. */ struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { struct bio *split; BUG_ON(sectors <= 0); BUG_ON(sectors >= bio_sectors(bio)); /* Zone append commands cannot be split */ if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND)) return NULL; split = bio_clone_fast(bio, gfp, bs); if (!split) return NULL; split->bi_iter.bi_size = sectors << 9; if (bio_integrity(split)) bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); return split; } EXPORT_SYMBOL(bio_split); /** * bio_trim - trim a bio * @bio: bio to trim * @offset: number of sectors to trim from the front of @bio * @size: size we want to trim @bio to, in sectors */ void bio_trim(struct bio *bio, int offset, int size) { /* 'bio' is a cloned bio which we need to trim to match * the given offset and size. */ size <<= 9; if (offset == 0 && size == bio->bi_iter.bi_size) return; bio_advance(bio, offset << 9); bio->bi_iter.bi_size = size; if (bio_integrity(bio)) bio_integrity_trim(bio); } EXPORT_SYMBOL_GPL(bio_trim); /* * create memory pools for biovec's in a bio_set. * use the global biovec slabs created for general use. */ int biovec_init_pool(mempool_t *pool, int pool_entries) { struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX; return mempool_init_slab_pool(pool, pool_entries, bp->slab); } /* * bioset_exit - exit a bioset initialized with bioset_init() * * May be called on a zeroed but uninitialized bioset (i.e. allocated with * kzalloc()). */ void bioset_exit(struct bio_set *bs) { if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); bs->rescue_workqueue = NULL; mempool_exit(&bs->bio_pool); mempool_exit(&bs->bvec_pool); bioset_integrity_free(bs); if (bs->bio_slab) bio_put_slab(bs); bs->bio_slab = NULL; } EXPORT_SYMBOL(bioset_exit); /** * bioset_init - Initialize a bio_set * @bs: pool to initialize * @pool_size: Number of bio and bio_vecs to cache in the mempool * @front_pad: Number of bytes to allocate in front of the returned bio * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS * and %BIOSET_NEED_RESCUER * * Description: * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller * to ask for a number of bytes to be allocated in front of the bio. * Front pad allocation is useful for embedding the bio inside * another structure, to avoid allocating extra data to go with the bio. * Note that the bio must be embedded at the END of that structure always, * or things will break badly. * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast(). * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to * dispatch queued requests when the mempool runs out of space. * */ int bioset_init(struct bio_set *bs, unsigned int pool_size, unsigned int front_pad, int flags) { unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); bs->front_pad = front_pad; spin_lock_init(&bs->rescue_lock); bio_list_init(&bs->rescue_list); INIT_WORK(&bs->rescue_work, bio_alloc_rescue); bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad); if (!bs->bio_slab) return -ENOMEM; if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab)) goto bad; if ((flags & BIOSET_NEED_BVECS) && biovec_init_pool(&bs->bvec_pool, pool_size)) goto bad; if (!(flags & BIOSET_NEED_RESCUER)) return 0; bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); if (!bs->rescue_workqueue) goto bad; return 0; bad: bioset_exit(bs); return -ENOMEM; } EXPORT_SYMBOL(bioset_init); /* * Initialize and setup a new bio_set, based on the settings from * another bio_set. */ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) { int flags; flags = 0; if (src->bvec_pool.min_nr) flags |= BIOSET_NEED_BVECS; if (src->rescue_workqueue) flags |= BIOSET_NEED_RESCUER; return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags); } EXPORT_SYMBOL(bioset_init_from_src); static void __init biovec_init_slabs(void) { int i; for (i = 0; i < BVEC_POOL_NR; i++) { int size; struct biovec_slab *bvs = bvec_slabs + i; if (bvs->nr_vecs <= BIO_INLINE_VECS) { bvs->slab = NULL; continue; } size = bvs->nr_vecs * sizeof(struct bio_vec); bvs->slab = kmem_cache_create(bvs->name, size, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } } static int __init init_bio(void) { bio_slab_max = 2; bio_slab_nr = 0; bio_slabs = kcalloc(bio_slab_max, sizeof(struct bio_slab), GFP_KERNEL); BUILD_BUG_ON(BIO_FLAG_LAST > BVEC_POOL_OFFSET); if (!bio_slabs) panic("bio: can't allocate bios\n"); bio_integrity_init(); biovec_init_slabs(); if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS)) panic("bio: can't allocate bios\n"); if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE)) panic("bio: can't create integrity pool\n"); return 0; } subsys_initcall(init_bio); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BITMAP_H #define __LINUX_BITMAP_H #ifndef __ASSEMBLY__ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/types.h> struct device; /* * bitmaps provide bit arrays that consume one or more unsigned * longs. The bitmap interface and available operations are listed * here, in bitmap.h * * Function implementations generic to all architectures are in * lib/bitmap.c. Functions implementations that are architecture * specific are in various include/asm-<arch>/bitops.h headers * and other arch/<arch> specific files. * * See lib/bitmap.c for more details. */ /** * DOC: bitmap overview * * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * * The generated code is more efficient when nbits is known at * compile-time and at most BITS_PER_LONG. * * :: * * bitmap_zero(dst, nbits) *dst = 0UL * bitmap_fill(dst, nbits) *dst = ~0UL * bitmap_copy(dst, src, nbits) *dst = *src * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) * bitmap_complement(dst, src, nbits) *dst = ~(*src) * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? * bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2? * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region * bitmap_next_set_region(map, &start, &end, nbits) Find next set region * bitmap_for_each_clear_region(map, rs, re, start, end) * Iterate over all clear regions * bitmap_for_each_set_region(map, rs, re, start, end) * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long * boundary will be zeroed or filled as well. Consider to use * bitmap_clear() or bitmap_set() to make explicit zeroing or filling * respectively. */ /** * DOC: bitmap bitops * * Also the following operations in asm/bitops.h apply to bitmaps.:: * * set_bit(bit, addr) *addr |= bit * clear_bit(bit, addr) *addr &= ~bit * change_bit(bit, addr) *addr ^= bit * test_bit(bit, addr) Is bit set in *addr? * test_and_set_bit(bit, addr) Set bit and return old value * test_and_clear_bit(bit, addr) Clear bit and return old value * test_and_change_bit(bit, addr) Change bit and return old value * find_first_zero_bit(addr, nbits) Position first zero bit in *addr * find_first_bit(addr, nbits) Position first set bit in *addr * find_next_zero_bit(addr, nbits, bit) * Position next zero bit in *addr >= bit * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit * find_next_and_bit(addr1, addr2, nbits, bit) * Same as find_next_bit, but in * (*addr1 & *addr2) * */ /** * DOC: declare bitmap * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used * to declare an array named 'name' of just enough unsigned longs to * contain all bit positions from 0 to 'bits' - 1. */ /* * Allocation and deallocation of bitmap. * Provided in lib/bitmap.c to avoid circular dependency. */ extern unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); extern unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); extern void bitmap_free(const unsigned long *bitmap); /* Managed variants of the above. */ unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags); /* * lib/bitmap.c provides these functions: */ extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits); extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); extern void __bitmap_set(unsigned long *map, unsigned int start, int len); extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset); /** * bitmap_find_next_zero_area - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ static inline unsigned long bitmap_find_next_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); } extern int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits); extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits); extern int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits); extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else #define bitmap_copy_le bitmap_copy #endif extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); extern int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) /* * The static inlines below do not handle constant nbits==0 correctly, * so make such users (should any ever turn up) call the out-of-line * versions. */ #define small_const_nbits(nbits) \ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) #define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = bitmap_size(nbits); memcpy(dst, src, len); } /* * Copy bitmap and clear tail bits in last word. */ static inline void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } static inline void bitmap_copy_and_extend(unsigned long *to, const unsigned long *from, unsigned int count, unsigned int size) { unsigned int copy = BITS_TO_LONGS(count); memcpy(to, from, copy * sizeof(long)); if (count % BITS_PER_LONG) to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); } /* * On 32-bit systems bitmaps are represented as u32 arrays internally, and * therefore conversion is not needed when copying data from/to arrays of u32. */ #if BITS_PER_LONG == 64 extern void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits); extern void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr32(bitmap, buf, nbits) \ bitmap_copy_clear_tail((unsigned long *) (bitmap), \ (const unsigned long *) (buf), (nbits)) #define bitmap_to_arr32(buf, bitmap, nbits) \ bitmap_copy_clear_tail((unsigned long *) (buf), \ (const unsigned long *) (bitmap), (nbits)) #endif static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; else __bitmap_or(dst, src1, src2, nbits); } static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; else __bitmap_xor(dst, src1, src2, nbits); } static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); else __bitmap_complement(dst, src, nbits); } #ifdef __LITTLE_ENDIAN #define BITMAP_MEM_ALIGNMENT 8 #else #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) static inline int bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) return !memcmp(src1, src2, nbits / 8); return __bitmap_equal(src1, src2, nbits); } /** * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ static inline bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } static inline int bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; else return __bitmap_intersects(src1, src2, nbits); } static inline int bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); else return __bitmap_subset(src1, src2, nbits); } static inline int bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); return find_first_bit(src, nbits) == nbits; } static inline int bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); return find_first_zero_bit(src, nbits) == nbits; } static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight(src, nbits); } static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0xff, nbits / 8); else __bitmap_set(map, start, nbits); } static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0, nbits / 8); else __bitmap_clear(map, start, nbits); } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; else __bitmap_shift_right(dst, src, shift, nbits); } static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); else __bitmap_shift_left(dst, src, shift, nbits); } static inline void bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); else __bitmap_replace(dst, old, new, mask, nbits); } static inline void bitmap_next_clear_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_zero_bit(bitmap, end, *rs); *re = find_next_bit(bitmap, end, *rs + 1); } static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); } /* * Bitmap region iterators. Iterates over the bitmap between [@start, @end). * @rs and @re should be integer variables and will be set to start and end * index of the current clear or set region. */ #define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ for ((rs) = (start), \ bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ (rs) < (re); \ (rs) = (re) + 1, \ bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) #define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ for ((rs) = (start), \ bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ (rs) < (re); \ (rs) = (re) + 1, \ bitmap_next_set_region((bitmap), &(rs), &(re), (end))) /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value * * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit * integers in 32-bit environment, and 64-bit integers in 64-bit one. * * There are four combinations of endianness and length of the word in linux * ABIs: LE64, BE64, LE32 and BE32. * * On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in * bitmaps and therefore don't require any special handling. * * On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory * prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the * other hand is represented as an array of 32-bit words and the position of * bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that * word. For example, bit #42 is located at 10th position of 2nd word. * It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit * values in memory as it usually does. But for BE we need to swap hi and lo * words manually. * * With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and * lo parts of u64. For LE32 it does nothing, and for BE environment it swaps * hi and lo words, as is expected by bitmap. */ #if __BITS_PER_LONG == 64 #define BITMAP_FROM_U64(n) (n) #else #define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \ ((unsigned long) ((u64)(n) >> 32)) #endif /** * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap * @dst: destination bitmap * * In 32-bit Big Endian kernel, when using ``(u32 *)(&val)[*]`` * to read u64 mask, we will get the wrong word. * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) { dst[0] = mask & ULONG_MAX; if (sizeof(mask) > sizeof(unsigned long)) dst[1] = mask >> 32; } /** * bitmap_get_value8 - get an 8-bit value within a memory region * @map: address to the bitmap memory region * @start: bit offset of the 8-bit value; must be a multiple of 8 * * Returns the 8-bit value located at the @start bit offset within the @src * memory region. */ static inline unsigned long bitmap_get_value8(const unsigned long *map, unsigned long start) { const size_t index = BIT_WORD(start); const unsigned long offset = start % BITS_PER_LONG; return (map[index] >> offset) & 0xFF; } /** * bitmap_set_value8 - set an 8-bit value within a memory region * @map: address to the bitmap memory region * @value: the 8-bit value; values wider than 8 bits may clobber bitmap * @start: bit offset of the 8-bit value; must be a multiple of 8 */ static inline void bitmap_set_value8(unsigned long *map, unsigned long value, unsigned long start) { const size_t index = BIT_WORD(start); const unsigned long offset = start % BITS_PER_LONG; map[index] &= ~(0xFFUL << offset); map[index] |= value << offset; } #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #ifdef __KERNEL__ #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/memremap.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; struct bdi_writeback; struct pt_regs; extern int sysctl_page_lock_unfairness; void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) { max_mapnr = limit; } #else static inline void set_max_mapnr(unsigned long limit) { } #endif extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; extern int page_cluster; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern const int mmap_rnd_bits_max; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> #include <asm/processor.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * It's defined as noop for arcitectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 80 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statments if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, or 80 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 80); switch (sizeof(struct page)) { case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE BIT(31) /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #ifdef CONFIG_PPC # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI #elif defined(CONFIG_ARM64) # define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ # define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_ARM64_MTE) # define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ # define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #else #define VM_STACK VM_GROWSDOWN #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask is used to clear all the VMA flags used by mlock */ #define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ extern pgprot_t protection_map[16]; /** * Fault flag definitions. * * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two * fault flags correctly. Currently there can be three legal combinations: * * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and * this is the first try * * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and * we've already tried at least once * * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry * * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never * be used. Note that page faults can be allowed to retry for multiple times, * in which case we'll have an initial fault with flags (a) then later on * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. */ #define FAULT_FLAG_WRITE 0x01 #define FAULT_FLAG_MKWRITE 0x02 #define FAULT_FLAG_ALLOW_RETRY 0x04 #define FAULT_FLAG_RETRY_NOWAIT 0x08 #define FAULT_FLAG_KILLABLE 0x10 #define FAULT_FLAG_TRIED 0x20 #define FAULT_FLAG_USER 0x40 #define FAULT_FLAG_REMOTE 0x80 #define FAULT_FLAG_INSTRUCTION 0x100 #define FAULT_FLAG_INTERRUPTIBLE 0x200 /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(unsigned int flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { struct vm_area_struct *vma; /* Target VMA */ unsigned int flags; /* FAULT_FLAG_xxx flags */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() calls * alloc_set_pte() from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* page entry size for vm->huge_fault() */ enum page_entry_size { PE_SIZE_PTE = 0, PE_SIZE_PMD, PE_SIZE_PUD, }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*split)(struct vm_area_struct * area, unsigned long addr); int (*mremap)(struct vm_area_struct * area); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); void (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } static inline bool is_shared_maywrite(vm_flags_t vm_flags) { return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == (VM_SHARED | VM_MAYWRITE); } static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline int get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifndef is_ioremap_addr #define is_ioremap_addr(x) is_vmalloc_addr(x) #endif #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif extern void *kvmalloc_node(size_t size, gfp_t flags, int node); static inline void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } static inline void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc(bytes, flags); } static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; } /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * * Must be called only for compound pages or any their tail sub-pages. */ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); return head_compound_mapcount(page); } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } int __page_mapcount(struct page *page); /* * Mapcount of 0-order page; when compound sub-page, includes * compound_mapcount(). * * Result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). * They use this place in struct page differently. */ static inline int page_mapcount(struct page *page) { if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); int page_trans_huge_mapcount(struct page *page, int *total_mapcount); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } static inline int page_trans_huge_mapcount(struct page *page, int *total_mapcount) { int mapcount = page_mapcount(page); if (total_mapcount) *total_mapcount = mapcount; return mapcount; } #endif static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. * These are _only_ valid on the head of a compound page. */ typedef void compound_page_dtor(struct page *); /* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */ enum compound_dtor_id { NULL_COMPOUND_DTOR, COMPOUND_PAGE_DTOR, #ifdef CONFIG_HUGETLB_PAGE HUGETLB_PAGE_DTOR, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE TRANSHUGE_PAGE_DTOR, #endif NR_COMPOUND_DTORS, }; extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) { VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); page[1].compound_dtor = compound_dtor; } static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) { if (!PageHead(page)) return 0; return page[1].compound_order; } static inline bool hpage_pincount_available(struct page *page) { /* * Can the page->hpage_pinned_refcount field be used? That field is in * the 3rd page of the compound page, so the smallest (2-page) compound * pages cannot support it. */ page = compound_head(page); return PageCompound(page) && compound_order(page) > 1; } static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); } static inline int compound_pincount(struct page *page) { VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); page = compound_head(page); return head_compound_pincount(page); } static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; page[1].compound_nr = 1U << order; } /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; return page[1].compound_nr; } /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } void free_compound_page(struct page *page); #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } #endif #ifdef CONFIG_DEV_PAGEMAP_OPS void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: return true; default: break; } return false; } void put_devmap_managed_page(struct page *page); #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool page_is_devmap_managed(struct page *page) { return false; } static inline void put_devmap_managed_page(struct page *page) { } #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } /* 127: arbitrary random number, small enough to assemble well */ #define page_ref_zero_or_close_to_overflow(page) \ ((unsigned int) page_ref_count(page) + 127u <= 127u) static inline void get_page(struct page *page) { page = compound_head(page); /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); page_ref_inc(page); } bool __must_check try_grab_page(struct page *page, unsigned int flags); static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } static inline void put_page(struct page *page) { page = compound_head(page); /* * For devmap managed pages we need to catch refcount transition from * 2 to 1, when refcount reach one it means the page is free and we * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); return; } if (put_page_testzero(page)) __put_page(page); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in page_cache_get_speculative() * and page_cache_gup_pin_speculative() provides safe operation for * get_user_pages and page_mkclean and other calls that race to set up page * table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); /** * page_maybe_dma_pinned() - report if a page is pinned for DMA. * * This function checks if a page has been pinned via a call to * pin_user_pages*(). * * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal page references". * * False positives are OK, because: a) it's unlikely for a page to get that many * refcounts, and b) all the callers of this routine are expected to be able to * deal gracefully with a false positive. * * For huge pages, the result will be exactly correct. That's because we have * more tracking data available: the 3rd struct page in the compound page is * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * @page: pointer to page to be queried. * @Return: True, if it is likely that the page has been "dma-pinned". * False, if the page is definitely not dma-pinned. */ static inline bool page_maybe_dma_pinned(struct page *page) { if (hpage_pincount_available(page)) return compound_pincount(page) > 0; /* * page_ref_count() is signed. If that refcount overflows, then * page_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the signed bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)page_ref_count(compound_head(page))) >= GUP_PIN_COUNTING_BIAS; } #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS extern int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { struct page *p = (struct page *)page; return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif #ifdef CONFIG_NUMA_BALANCING static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) { return page->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int page_cpupid_last(struct page *page) { return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } extern int page_cpupid_xchg_last(struct page *page, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_KASAN_SW_TAGS /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag; tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { tag ^= 0xff; page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } static inline void page_kasan_tag_reset(struct page *page) { page_kasan_tag_set(page, 0xff); } #else static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } #ifdef CONFIG_MEMCG static inline struct mem_cgroup *page_memcg(struct page *page) { return page->mem_cgroup; } static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { WARN_ON_ONCE(!rcu_read_lock_held()); return READ_ONCE(page->mem_cgroup); } #else static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { WARN_ON_ONCE(!rcu_read_lock_held()); return NULL; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); extern struct address_space *page_mapping(struct page *page); extern struct address_space *__page_file_mapping(struct page *); static inline struct address_space *page_file_mapping(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_mapping(page); return page->mapping; } extern pgoff_t __page_file_index(struct page *page); /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } bool page_mapped(struct page *page); struct address_space *page_mapping(struct page *page); struct address_space *page_mapping_file(struct page *page); /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(struct page *page) { /* * Page index cannot be this large so this must be * a pfmemalloc page. */ return page->index == -1UL; } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->index = -1UL; } static inline void clear_page_pfmemalloc(struct page *page) { page->index = 0; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) /* * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ struct page *single_page; /* Locked page to be unmapped */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); /* Container for pinned pfns / pages */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, unsigned int gup_flags, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); static inline unsigned int frame_vector_count(struct frame_vector *vec) { return vec->nr_frames; } static inline struct page **frame_vector_pages(struct frame_vector *vec) { if (vec->is_pfns) { int err = frame_vector_to_pages(vec); if (err) return ERR_PTR(err); } return (struct page **)(vec->ptrs); } static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) { if (!vec->is_pfns) frame_vector_to_pfns(vec); return (unsigned long *)(vec->ptrs); } struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); int get_kernel_page(unsigned long start, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_dirtied(struct page *page, struct address_space *mapping); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); void __cancel_dirty_page(struct page *page); static inline void cancel_dirty_page(struct page *page) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (PageDirty(page)) __cancel_dirty_page(page); } int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* Whether we should allow dirty bit accounting */ #define MM_CP_DIRTY_ACCT (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP (1UL << 2) /* do wp */ #define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */ #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { long val = atomic_long_read(&mm->rss_stat.count[member]); #ifdef SPLIT_RSS_COUNTING /* * counter is updated in asynchronous manner and may go to minus. * But it's never be expected number for users. */ if (val < 0) val = 0; #endif return (unsigned long)val; } void mm_trace_rss_stat(struct mm_struct *mm, int member, long count); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_inc_return(&mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_dec_return(&mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } /* Optimized variant when page is already known not to be PageAnon */ static inline int mm_counter_file(struct page *page) { if (PageSwapBacked(page)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct page *page) { if (PageAnon(page)) return MM_ANONPAGES; return mm_counter_file(page); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss; } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *maxrss = hiwater_rss; } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm); #else static inline void sync_mm_rss(struct mm_struct *mm) { } #endif #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pte_t *ptep; __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); return ptep; } #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct page *page) { return true; } static inline void ptlock_free(struct page *page) { } static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_page(*pmd)); } static inline bool ptlock_init(struct page *page) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page); if (!ptlock_alloc(page)) return false; spin_lock_init(ptlock_ptr(page)); return true; } #else /* !USE_SPLIT_PTE_PTLOCKS */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ static inline void pgtable_init(void) { ptlock_cache_init(); pgtable_cache_init(); } static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; __SetPageTable(page); inc_zone_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_pte_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); dec_zone_page_state(page, NR_PAGETABLE); } #define pte_offset_map_lock(mm, pmd, address, ptlp) \ ({ \ spinlock_t *__ptl = pte_lockptr(mm, pmd); \ pte_t *__pte = pte_offset_map(pmd, address); \ *(ptlp) = __ptl; \ spin_lock(__ptl); \ __pte; \ }) #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_to_page(pmd)); } static inline bool pmd_ptlock_init(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE page->pmd_huge_pte = NULL; #endif return ptlock_init(page); } static inline void pmd_ptlock_free(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON_PAGE(page->pmd_huge_pte, page); #endif ptlock_free(page); } #define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pmd_ptlock_init(struct page *page) { return true; } static inline void pmd_ptlock_free(struct page *page) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } static inline bool pgtable_pmd_page_ctor(struct page *page) { if (!pmd_ptlock_init(page)) return false; __SetPageTable(page); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE atomic_set(&page->pt_share_count, 0); #endif inc_zone_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_pmd_page_dtor(struct page *page) { pmd_ptlock_free(page); __ClearPageTable(page); dec_zone_page_state(page, NR_PAGETABLE); } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } extern void __init pagecache_init(void); extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); #ifdef CONFIG_HIGHMEM /* * Free a highmem page into the buddy system, adjusting totalhigh_pages * and totalram_pages. */ extern void free_highmem_page(struct page *page); #endif extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) { ClearPageReserved(page); init_page_count(page); __free_page(page); } static inline void free_reserved_page(struct page *page) { __free_reserved_page(page); adjust_managed_page_count(page, 1); } static inline void mark_page_reserved(struct page *page) { SetPageReserved(page); adjust_managed_page_count(page, -1); } /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel"); } static inline unsigned long get_num_physpages(void) { int nid; unsigned long phys_pages = 0; for_each_online_node(nid) phys_pages += node_present_pages(nid); return phys_pages; } /* * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); #ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); /* there is a per-arch backend function. */ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(unsigned int flags, nodemask_t *nodemask); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); #ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES extern unsigned long arch_reserved_kernel_pages(void); #endif extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* page_alloc.c */ extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) \ for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) \ for (avc = anon_vma_interval_tree_iter_first(root, start, last); \ avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand); static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { return __vma_adjust(vma, start, end, pgoff, insert, NULL); } extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, struct rb_node **, struct rb_node *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { if (rlim < RLIM_INFINITY) { if (((new - start) + (end_data - start_data)) > rlim) return -ENOSPC; } return 0; } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); /* This is an obsolete alternative to _install_special_mapping. */ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { /* Ignore errors */ (void) __mm_populate(addr, len, 1); } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* These take the mm semaphore themselves */ extern int __must_check vm_brk(unsigned long, unsigned long); extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); struct vm_unmapped_area_info { #define VM_UNMAPPED_AREA_TOPDOWN 1 unsigned long flags; unsigned long length; unsigned long low_limit; unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); /* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ extern int expand_downwards(struct vm_area_struct *vma, unsigned long address); #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /* Look up the first VMA which intersects the interval start_addr..end_addr-1, NULL if none. Assume start_addr < end_addr. */ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr) { struct vm_area_struct * vma = find_vma(mm,start_addr); if (vma && end_addr <= vma->vm_start) vma = NULL; return vma; } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long vm_start = vma->vm_start; if (vma->vm_flags & VM_GROWSDOWN) { vm_start -= stack_guard_gap; if (vm_start > vma->vm_start) vm_start = 0; } return vm_start; } static inline unsigned long vm_end_gap(struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; if (vma->vm_flags & VM_GROWSUP) { vm_end += stack_guard_gap; if (vm_end < vma->vm_end) vm_end = -PAGE_SIZE; } return vm_end; } static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { struct vm_area_struct *vma = find_vma(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; return vma; } static inline bool range_in_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { int err = vm_insert_page(vma, addr, page); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } #ifndef io_remap_pfn_range static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); } #endif static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) return VM_FAULT_OOM; return VM_FAULT_SIGBUS; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ #define FOLL_POPULATE 0x40 /* fault in page */ #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ #define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ #define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time * period _often_ under userspace control. This is in contrast to * iov_iter_get_pages(), whose usages are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm * users like RDMA and V4L2 only establish mappings which coordinate usage with * the filesystem. Ideas for this coordination include revoking the longterm * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was * added after the problem with filesystems was found FS DAX VMAs are * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. * Currently only get_user_pages() and get_user_pages_fast() support this flag * and calls to get_user_pages_[un]locked are specifically not allowed. This * is due to an incompatibility with the FS DAX check and * FAULT_FLAG_ALLOW_RETRY. * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. * * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, * but an additional pin counting system) will be invoked. This is intended for * anything that gets a page reference and then touches page data (for example, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has * its own acquire and release mechanisms: * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based * calls applied to them, and that's perfectly OK. This is a constraint on the * callers, not on the pages.) * * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/core-api/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; return 0; } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); #else static inline bool page_poisoning_enabled(void) { return false; } static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif #ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON DECLARE_STATIC_KEY_TRUE(init_on_alloc); #else DECLARE_STATIC_KEY_FALSE(init_on_alloc); #endif static inline bool want_init_on_alloc(gfp_t flags) { if (static_branch_unlikely(&init_on_alloc) && !page_poisoning_enabled()) return true; return flags & __GFP_ZERO; } #ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON DECLARE_STATIC_KEY_TRUE(init_on_free); #else DECLARE_STATIC_KEY_FALSE(init_on_free); #endif static inline bool want_init_on_free(void) { return static_branch_unlikely(&init_on_free) && !page_poisoning_enabled(); } #ifdef CONFIG_DEBUG_PAGEALLOC extern void init_debug_pagealloc(void); #else static inline void init_debug_pagealloc(void) {} #endif extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled_early; } /* * For use in fast paths after init_debug_pagealloc() has run, or when a * false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; return static_branch_unlikely(&_debug_pagealloc_enabled); } #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) extern void __kernel_map_pages(struct page *page, int numpages, int enable); /* * When called in DEBUG_PAGEALLOC context, the call should most likely be * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static() */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) { __kernel_map_pages(page, numpages, enable); } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); #endif /* CONFIG_HIBERNATION */ #else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ #endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #endif void drop_slab(void); void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); /* * Error handlers for various types of pages. */ enum mf_result { MF_IGNORED, /* Error: cannot be handled */ MF_FAILED, /* Error: handling failed */ MF_DELAYED, /* Will be handled later */ MF_RECOVERED, /* Successfully recovered */ }; enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_NON_PMD_HUGE, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, MF_MSG_DIRTY_MLOCKED_LRU, MF_MSG_CLEAN_MLOCKED_LRU, MF_MSG_DIRTY_UNEVICTABLE_LRU, MF_MSG_CLEAN_UNEVICTABLE_LRU, MF_MSG_DIRTY_LRU, MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page); extern long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? * @vma: Pointer to the struct vm_area_struct to consider * * Whether transhuge page-table entries are considered "special" following * the definition in vm_normal_page(). * * Return: true if transhuge page-table entries should be considered special, * false otherwise. */ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) { return vma_is_dax(vma) || (vma->vm_file && (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #ifdef CONFIG_DEBUG_PAGEALLOC extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { return _debug_guardpage_minorder; } static inline bool debug_guardpage_enabled(void) { return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(struct page *page) { if (!debug_guardpage_enabled()) return false; return PageGuard(page); } #else static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } #endif /* CONFIG_DEBUG_PAGEALLOC */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { return !memcmp_pages(page1, page2); } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif extern int sysctl_nr_trim_pages; static inline bool is_write_sealed(int seals) { return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); } /** * is_readonly_sealed - Checks whether write-sealed but mapped read-only, * in which case writes should be disallowing moving * forwards. * @seals: the seals to check * @vm_flags: the VMA flags to check * * Returns whether readonly sealed, in which case writess should be disallowed * going forward. */ static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) { /* * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as * MAP_SHARED and read-only, take care to not allow mprotect to * revert protections on such mappings. Do this only for shared * mappings. For private mappings, don't need to mask * VM_MAYWRITE as we still want them to be COW-writable. */ if (is_write_sealed(seals) && ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) return true; return false; } /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. * @seals: the seals to check * @vma: the vma to operate on * * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { if (!is_write_sealed(seals)) return 0; /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * write seals are active. */ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) return -EPERM; return 0; } #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include "workqueue_internal.h" enum { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 24, }; /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * X: During normal operation, modification requires pool->lock and should * be done only from local cpu. Either disabling preemption on local * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* X: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* X: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct completion *detach_completion; /* all workers detached */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ /* * The current concurrency level. As it's likely to be accessed * from other CPUs during try_to_wake_up(), put it in a separate * cacheline. */ atomic_t nr_running ____cacheline_aligned_in_smp; /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; /* * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ /* * Release of unbound pwq is punted to system_wq. See put_pwq() * and pwq_unbound_release_workfn() for details. pool_workqueue * itself is also RCU protected so that the first pwq can be * determined without grabbing wq->mutex. */ struct work_struct unbound_release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_FLAG_BITS); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ int saved_max_active; /* WQ: saved pwq max_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */ }; static struct kmem_cache *pwq_cache; static cpumask_var_t *wq_numa_possible_cpumask; /* possible CPUs of each node */ static bool wq_disable_numa; module_param_named(disable_numa, wq_disable_numa, bool, 0444); /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; struct workqueue_struct *system_wq __read_mostly; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __read_mostly; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __read_mostly; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { destroy_timer_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assing it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } /** * unbound_pwq_by_node - return the unbound pool_workqueue for the given node * @wq: the target workqueue * @node: the node ID * * This must be called with any of wq_pool_mutex, wq->mutex or RCU * read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * Return: The unbound pool_workqueue for @node. */ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { assert_rcu_or_wq_mutex_or_pool_mutex(wq); /* * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a * delayed item is pending. The plan is to keep CPU -> NODE * mapping valid and stable across CPU on/offlines. Once that * happens, this workaround can be removed. */ if (unlikely(node == NUMA_NO_NODE)) return wq->dfl_pwq; return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(struct work_struct *work) { return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() * and clear_work_data() can be used to set the pwq, pool or clear * work->data. These functions should only be called while the work is * owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. * * %WORK_OFFQ_CANCELING is used to mark a work item which is being * canceled. While being canceled, a work item may have its PENDING set * but stay off timer and worklist for arbitrarily long and nobody should * try to steal the PENDING bit. */ static inline void set_work_data(struct work_struct *work, unsigned long data, unsigned long flags) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | flags | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long extra_flags) { set_work_data(work, (unsigned long)pwq, WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id) { set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, WORK_STRUCT_PENDING); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static void clear_work_data(struct work_struct *work) { smp_wmb(); /* see set_work_pool_and_clear_pending() */ set_work_data(work, WORK_STRUCT_NO_POOL, 0); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } /** * get_work_pool_id - return the worker pool ID a given work is associated with * @work: the work item of interest * * Return: The worker_pool ID @work was last associated with. * %WORK_OFFQ_POOL_NONE if none. */ static int get_work_pool_id(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } static void mark_work_canceling(struct work_struct *work) { unsigned long pool_id = get_work_pool_id(work); pool_id <<= WORK_OFFQ_POOL_SHIFT; set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); } static bool work_is_canceling(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ static bool __need_more_worker(struct worker_pool *pool) { return !atomic_read(&pool->nr_running); } /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && __need_more_worker(pool); } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && atomic_read(&pool->nr_running) <= 1; } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /* * Wake up functions. */ /* Return the first idle worker. Safe with preemption disabled */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * wake_up_worker - wake up an idle worker * @pool: worker pool to wake worker from * * Wake up the first idle worker of @pool. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void wake_up_worker(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); if (likely(worker)) wake_up_process(worker->task); } /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!worker->sleeping) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); preempt_enable(); worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. Preemption needs to be disabled to protect ->sleeping * assignment. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *next, *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (worker->sleeping) return; worker->sleeping = 1; raw_spin_lock_irq(&pool->lock); /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. * * NOT_RUNNING is clear. This means that we're bound to and * running on the local cpu w/ rq lock held and preemption * disabled, which in turn means that none else could be * manipulating idle_list, so dereferencing idle_list without pool * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && !list_empty(&pool->worklist)) { next = first_idle_worker(pool); if (next) wake_up_process(next->task); } raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * raw_spin_lock_irq(pool->lock) */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; WARN_ON_ONCE(worker->task != current); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { atomic_dec(&pool->nr_running); } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * raw_spin_lock_irq(pool->lock) */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; WARN_ON_ONCE(worker->task != current); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&pool->nr_running); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to * be scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. * * If @nextp is not NULL, it's updated to point to the next work of * the last scheduled work. This allows move_linked_works() to be * nested inside outer list_for_each_entry_safe(). * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND))) return; /* * @pwq can't be released under pool->lock, bounce to * pwq_unbound_release_workfn(). This never recurses on the same * pool->lock as this path is taken only for unbound workqueues and * the release work item is scheduled on a per-cpu workqueue. To * avoid lockdep warning, unbound pool->locks are given lockdep * subclass of 1 in get_unbound_pool(). */ schedule_work(&pwq->unbound_release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static void pwq_activate_inactive_work(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); pwq->nr_active++; } static void pwq_activate_first_inactive(struct pool_workqueue *pwq) { struct work_struct *work = list_first_entry(&pwq->inactive_works, struct work_struct, entry); pwq_activate_inactive_work(work); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @color: color of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) { /* uncolored work items don't participate in flushing or nr_active */ if (color == WORK_NO_COLOR) goto out_put; pwq->nr_in_flight[color]--; pwq->nr_active--; if (!list_empty(&pwq->inactive_works)) { /* one down, submit an inactive one */ if (pwq->nr_active < pwq->max_active) pwq_activate_first_inactive(pwq); } /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @is_dwork: @work is a delayed_work * @flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * -ENOENT if someone else is canceling @work, this state may persist * for arbitrarily long * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, unsigned long *flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*flags); /* try to steal the timer if it exists */ if (is_dwork) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If del_timer() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(del_timer(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { debug_work_deactivate(work); /* * An inactive work item cannot be grabbed directly because * it might have linked NO_COLOR work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) pwq_activate_inactive_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, get_work_color(work)); /* work->data points to pwq iff queued, point to pool */ set_work_pool_and_keep_pending(work, pool->id); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*flags); if (work_is_canceling(work)) return -ENOENT; cpu_relax(); return -EAGAIN; } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { struct worker_pool *pool = pwq->pool; /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); /* * Ensure either wq_worker_sleeping() sees the above * list_add_tail() or we see zero nr_running to avoid workers lying * around lazily while there are works to be processed. */ smp_mb(); if (__need_more_worker(pool)) wake_up_worker(pool); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { static bool printed_dbg_warning; int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else if (!printed_dbg_warning) { pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n"); printed_dbg_warning = true; } if (cpumask_empty(wq_unbound_cpumask)) return cpu; new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; } __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool; struct list_head *worklist; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (wq->flags & WQ_UNBOUND) { if (req_cpu == WORK_CPU_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); } else { if (req_cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); } /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. */ last_pool = get_work_pool(work); if (last_pool && last_pool != pwq->pool) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pwq->pool->lock); } } else { raw_spin_lock(&pwq->pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have * raced with pwq release and it could already be dead. If its * refcnt is zero, repeat pwq selection. Note that pwqs never die * without another pwq replacing it in the numa_pwq_tbl or while * work items are executing on it, so the retrying is guaranteed to * make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pwq->pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); if (likely(pwq->nr_active < pwq->max_active)) { trace_workqueue_activate_work(work); pwq->nr_active++; worklist = &pwq->pool->worklist; if (list_empty(worklist)) pwq->pool->watchdog_ts = jiffies; } else { work_flags |= WORK_STRUCT_INACTIVE; worklist = &pwq->inactive_works; } debug_work_activate(work); insert_work(pwq, work, worklist, work_flags); out: raw_spin_unlock(&pwq->pool->lock); rcu_read_unlock(); } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long flags; local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * workqueue_select_cpu_near - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int workqueue_select_cpu_near(int node) { int cpu; /* No point in doing this if NUMA isn't enabled for workqueues */ if (!wq_numa_enabled) return WORK_CPU_UNBOUND; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { int cpu = workqueue_select_cpu_near(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (unlikely(cpu != WORK_CPU_UNBOUND)) add_timer_on(timer, cpu); else add_timer(timer); } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long flags; /* read the comment in __queue_work() */ local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long flags; int ret; do { ret = try_to_grab_pending(&dwork->work, true, &flags); } while (unlikely(ret == -EAGAIN)); if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { rwork->wq = wq; call_rcu(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* * Sanity check nr_running. Because unbind_workers() releases * pool->lock between setting %WORKER_UNBOUND and zapping * nr_running, the warning may trigger spuriously. Check iff * unbind is not in progress. */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && pool->nr_workers == pool->nr_idle && atomic_read(&pool->nr_running)); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag * definition for details. */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; mutex_lock(&wq_pool_attach_mutex); list_del(&worker->node); worker->pool = NULL; if (list_empty(&pool->workers)) detach_completion = pool->detach_completion; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); if (detach_completion) complete(detach_completion); } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker = NULL; int id = -1; char id_buf[16]; /* ID is needed to determine kthread name */ id = ida_simple_get(&pool->worker_ida, 0, 0, GFP_KERNEL); if (id < 0) goto fail; worker = alloc_worker(pool->node); if (!worker) goto fail; worker->id = id; if (pool->cpu >= 0) snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, pool->attrs->nice < 0 ? "H" : ""); else snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "kworker/%s", id_buf); if (IS_ERR(worker->task)) goto fail; set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool->attrs->cpumask); /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: if (id >= 0) ida_simple_remove(&pool->worker_ida, id); kfree(worker); return NULL; } /** * destroy_worker - destroy a workqueue worker * @worker: worker to be destroyed * * Destroy @worker and adjust @pool stats accordingly. The worker should * be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void destroy_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; list_del_init(&worker->entry); worker->flags |= WORKER_DIE; wake_up_process(worker->task); } static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } destroy_worker(worker); } raw_spin_unlock_irq(&pool->lock); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } del_timer_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE; int work_color; struct worker *collision; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* * A single work shouldn't be executed concurrently by * multiple workers on a single cpu. Check whether anyone is * already processing the work. If so, defer the work to the * currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, NULL); return; } /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; work_color = get_work_color(work); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(cpu_intensive)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Wake up another worker if necessary. The condition is always * false for normal per-cpu workers since nr_running would always * be >= 1 at this point. This is used to chain execution of the * pending work items for WORKER_NOT_RUNNING workers such as the * UNBOUND and CPU_INTENSIVE ones. */ if (need_more_worker(pool)) wake_up_worker(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id); raw_spin_unlock_irq(&pool->lock); lock_map_acquire(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); lock_map_release(&pwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" " last function: %ps\n", current->comm, preempt_count(), task_pid_nr(current), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ cond_resched(); raw_spin_lock_irq(&pool->lock); /* clear cpu intensive status */ if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; pwq_dec_nr_in_flight(pwq, work_color); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { while (!list_empty(&worker->scheduled)) { struct work_struct *work = list_first_entry(&worker->scheduled, struct work_struct, entry); process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&worker->entry)); set_pf_worker(false); set_task_comm(worker->task, "kworker/dying"); ida_simple_remove(&pool->worker_ida, worker->id); worker_detach_from_pool(worker); kfree(worker); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); pool->watchdog_ts = jiffies; if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) { /* optimization path, not strictly necessary */ process_one_work(worker, work); if (unlikely(!list_empty(&worker->scheduled))) process_scheduled_works(worker); } else { move_linked_works(work, &worker->scheduled, NULL); process_scheduled_works(worker); } } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; bool first = true; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { if (first) pool->watchdog_ts = jiffies; move_linked_works(work, scheduled, &n); } first = false; } if (!list_empty(scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Put the reference grabbed by send_mayday(). @pool won't * go away while we're still attached to it. */ put_pwq(pwq); /* * Leave this pool. If need_more_worker() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ if (need_more_worker(pool)) wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * * %current is trying to flush the whole @target_wq or @target_work on it. * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not * reclaiming memory or running on a workqueue which doesn't have * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to * a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work) { work_func_t target_func = target_work ? target_work->func : NULL; struct worker *worker; if (target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { struct list_head *head; unsigned int linked = 0; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. */ INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) head = worker->scheduled.next; else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ linked = *bits & WORK_STRUCT_LINKED; __set_bit(WORK_STRUCT_LINKED_BIT, bits); } debug_work_activate(&barr->work); insert_work(pwq, &barr->work, head, work_color_to_flags(WORK_NO_COLOR) | linked); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } for_each_pwq(pwq, wq) { struct worker_pool *pool = pwq->pool; raw_spin_lock_irq(&pool->lock); if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } raw_spin_unlock_irq(&pool->lock); } if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } /** * flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map), }; int next_color; if (WARN_ON(!wq_online)) return; lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = !pwq->nr_active && list_empty(&pwq->inactive_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: drain_workqueue() isn't complete after %u tries\n", wq->name, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; might_sleep(); rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } check_flush_dependency(pwq->wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) { lock_map_acquire(&pwq->wq->lockdep_map); lock_map_release(&pwq->wq->lockdep_map); } rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return true; } else { return false; } } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); struct cwt_wait { wait_queue_entry_t wait; struct work_struct *work; }; static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); if (cwait->work != key) return 0; return autoremove_wake_function(wait, mode, sync, key); } static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) { static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); /* * If someone else is already canceling, wait for it to * finish. flush_work() doesn't work for PREEMPT_NONE * because we may get scheduled between @work's completion * and the other canceling task resuming and clearing * CANCELING - flush_work() will return false immediately * as @work is no longer busy, try_to_grab_pending() will * return -ENOENT as @work is still being canceled and the * other canceling task won't be able to clear CANCELING as * we're hogging the CPU. * * Let's wait for completion using a waitqueue. As this * may lead to the thundering herd problem, use a custom * wake function which matches @work along with exclusive * wait and wakeup. */ if (unlikely(ret == -ENOENT)) { struct cwt_wait cwait; init_wait(&cwait.wait); cwait.wait.func = cwt_wakefn; cwait.work = work; prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, TASK_UNINTERRUPTIBLE); if (work_is_canceling(work)) schedule(); finish_wait(&cancel_waitq, &cwait.wait); } } while (unlikely(ret < 0)); /* tell other tasks trying to grab @work to back off */ mark_work_canceling(work); local_irq_restore(flags); /* * This allows canceling during early boot. We know that @work * isn't executing. */ if (wq_online) __flush_work(work, true); clear_work_data(work); /* * Paired with prepare_to_wait() above so that either * waitqueue_active() is visible here or !work_is_canceling() is * visible there. */ smp_mb(); if (waitqueue_active(&cancel_waitq)) __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); return ret; } /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself or migrates to * another workqueue. On return from this function, @work is * guaranteed to be not pending or executing on any CPU. * * cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use cancel_delayed_work_sync() instead. * * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. * * Return: * %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_timer(work, false); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static bool __cancel_work(struct work_struct *work, bool is_dwork) { unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); } while (unlikely(ret == -EAGAIN)); if (unlikely(ret < 0)) return false; set_work_pool_and_clear_pending(work, get_work_pool_id(work)); local_irq_restore(flags); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, false); } EXPORT_SYMBOL(cancel_work); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_timer(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; get_online_cpus(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); put_online_cpus(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); /* * Unlike hash and equality test, this function doesn't ignore * ->no_numa as it is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears ->no_numa after copying. */ to->no_numa = from->no_numa; } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (!cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); wq_free_lockdep(wq); if (!(wq->flags & WQ_UNBOUND)) free_percpu(wq->cpu_pwqs); else free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /* This returns with the lock held on success (pool manager is inactive). */ static bool wq_manager_inactive(struct worker_pool *pool) { raw_spin_lock_irq(&pool->lock); if (pool->flags & POOL_MANAGER_ACTIVE) { raw_spin_unlock_irq(&pool->lock); return false; } return true; } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { DECLARE_COMPLETION_ONSTACK(detach_completion); struct worker *worker; lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * Because of how wq_manager_inactive() works, we will hold the * spinlock after a successful wait. */ rcuwait_wait_event(&manager_wait, wq_manager_inactive(pool), TASK_UNINTERRUPTIBLE); pool->flags |= POOL_MANAGER_ACTIVE; while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); mutex_lock(&wq_pool_attach_mutex); if (!list_empty(&pool->workers)) pool->detach_completion = &detach_completion; mutex_unlock(&wq_pool_attach_mutex); if (pool->detach_completion) wait_for_completion(pool->detach_completion); /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int node; int target_node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* if cpumask is contained inside a NUMA node, we belong to that node */ if (wq_numa_enabled) { for_each_node(node) { if (cpumask_subset(attrs->cpumask, wq_numa_possible_cpumask[node])) { target_node = node; break; } } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node); if (!pool || init_worker_pool(pool) < 0) goto fail; lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); pool->node = target_node; /* * no_numa isn't a worker_pool attribute, always clear it. See * 'struct workqueue_attrs' comments for detail. */ pool->attrs->no_numa = false; if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } static void rcu_free_pwq(struct rcu_head *rcu) { kmem_cache_free(pwq_cache, container_of(rcu, struct pool_workqueue, rcu)); } /* * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt * and needs to be destroyed. */ static void pwq_unbound_release_workfn(struct work_struct *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * when @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) return; mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); mutex_unlock(&wq->mutex); } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /** * pwq_adjust_max_active - update a pwq's max_active to the current setting * @pwq: target pool_workqueue * * If @pwq isn't freezing, set @pwq->max_active to the associated * workqueue's saved_max_active and activate inactive work items * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. */ static void pwq_adjust_max_active(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; bool freezable = wq->flags & WQ_FREEZABLE; unsigned long flags; /* for @wq->saved_max_active */ lockdep_assert_held(&wq->mutex); /* fast exit for non-freezable wqs */ if (!freezable && pwq->max_active == wq->saved_max_active) return; /* this function can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, flags); /* * During [un]freezing, the caller is responsible for ensuring that * this function is called at least once after @workqueue_freezing * is updated and visible. */ if (!freezable || !workqueue_freezing) { bool kick = false; pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->inactive_works) && pwq->nr_active < pwq->max_active) { pwq_activate_first_inactive(pwq); kick = true; } /* * Need to kick a worker after thawed or an unbound wq's * max_active is bumped. In realtime scenarios, always kicking a * worker will cause interference on the isolated cpu cores, so * let's kick iff work items were activated. */ if (kick) wake_up_worker(pwq->pool); } else { pwq->max_active = 0; } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); } /* initialize newly alloced @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* sync max_active to the current setting */ pwq_adjust_max_active(pwq); /* link in @pwq */ list_add_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } /** * wq_calc_node_cpumask - calculate a wq_attrs' cpumask for the specified node * @attrs: the wq_attrs of the default pwq of the target workqueue * @node: the target NUMA node * @cpu_going_down: if >= 0, the CPU to consider as offline * @cpumask: outarg, the resulting cpumask * * Calculate the cpumask a workqueue with @attrs should use on @node. If * @cpu_going_down is >= 0, that cpu is considered offline during * calculation. The result is stored in @cpumask. * * If NUMA affinity is not enabled, @attrs->cpumask is always used. If * enabled and @node has online CPUs requested by @attrs, the returned * cpumask is the intersection of the possible CPUs of @node and * @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @node stays * stable. * * Return: %true if the resulting @cpumask is different from @attrs->cpumask, * %false if equal. */ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) { if (!wq_numa_enabled || attrs->no_numa) goto use_dfl; /* does @node have any online CPUs @attrs wants? */ cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask); if (cpu_going_down >= 0) cpumask_clear_cpu(cpu_going_down, cpumask); if (cpumask_empty(cpumask)) goto use_dfl; /* yeap, return possible CPUs in @node that @attrs wants */ cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]); if (cpumask_empty(cpumask)) { pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); return false; } return !cpumask_equal(cpumask, attrs->cpumask); use_dfl: cpumask_copy(cpumask, attrs->cpumask); return false; } /* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, int node, struct pool_workqueue *pwq) { struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int node; for_each_node(node) put_pwq_unlocked(ctx->pwq_tbl[node]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; int node; lockdep_assert_held(&wq_pool_mutex); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); tmp_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs || !tmp_attrs) goto out_free; /* * Calculate the attrs of the default pwq. * If the user configured cpumask doesn't overlap with the * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, wq_unbound_cpumask); if (unlikely(cpumask_empty(new_attrs->cpumask))) cpumask_copy(new_attrs->cpumask, wq_unbound_cpumask); /* * We may create multiple pwqs with differing cpumasks. Make a * copy of @new_attrs which will be modified and used to obtain * pools. */ copy_workqueue_attrs(tmp_attrs, new_attrs); /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_node(node) { if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) { ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); if (!ctx->pwq_tbl[node]) goto out_free; } else { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[node] = ctx->dfl_pwq; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); ctx->attrs = new_attrs; ctx->wq = wq; free_workqueue_attrs(tmp_attrs); return ctx; out_free: free_workqueue_attrs(tmp_attrs); free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return NULL; } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int node; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwq and install the new one */ for_each_node(node) ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node, ctx->pwq_tbl[node]); /* @dfl_pwq might not have been used, ensure it's linked */ link_pwq(ctx->dfl_pwq); swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); mutex_unlock(&ctx->wq->mutex); } static void apply_wqattrs_lock(void) { /* CPUs should stay stable across pwq creations and installations */ get_online_cpus(); mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); put_online_cpus(); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; /* creating multiple pwqs breaks ordering guarantee */ if (!list_empty(&wq->pwqs)) { if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->flags &= ~__WQ_ORDERED; } ctx = apply_wqattrs_prepare(wq, attrs); if (!ctx) return -ENOMEM; /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA * machines, this function maps a separate pwq to each NUMA node with * possibles CPUs in @attrs->cpumask so that work items are affine to the * NUMA node it was issued on. Older pwqs are released as in-flight work * items finish. Note that a work item which repeatedly requeues itself * back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Assumes caller has CPU hotplug read exclusion, i.e. get_online_cpus(). * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; lockdep_assert_cpus_held(); mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU coming up or going down * @online: whether @cpu is coming up or going down * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of * @wq accordingly. * * If NUMA affinity can't be adjusted due to memory allocation failure, it * falls back to @wq->dfl_pwq which may not be optimal but is always * correct. * * Note that when the last allowed CPU of a NUMA node goes offline for a * workqueue with a cpumask spanning multiple nodes, the workers which were * already executing the work items for the workqueue will lose their CPU * affinity and may execute on any CPU. This is similar to how per-cpu * workqueues behave on CPU_DOWN. If a workqueue user wants strict * affinity, it's the user's responsibility to flush the work item from * CPU_DOWN_PREPARE. */ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, bool online) { int node = cpu_to_node(cpu); int cpu_off = online ? -1 : cpu; struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; cpumask_t *cpumask; lockdep_assert_held(&wq_pool_mutex); if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->no_numa) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = wq_update_unbound_numa_attrs_buf; cpumask = target_attrs->cpumask; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); pwq = unbound_pwq_by_node(wq, node); /* * Let's determine what needs to be done. If the target cpumask is * different from the default pwq's, we need to compare it to @pwq's * and create a new one if they don't match. If the target cpumask * equals the default pwq's, the default pwq should be used. */ if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) { if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) return; } else { goto use_dfl_pwq; } /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = numa_pwq_tbl_install(wq, node, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); get_pwq(wq->dfl_pwq); raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; if (!(wq->flags & WQ_UNBOUND)) { wq->cpu_pwqs = alloc_percpu(struct pool_workqueue); if (!wq->cpu_pwqs) return -ENOMEM; for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); struct worker_pool *cpu_pools = per_cpu(cpu_worker_pools, cpu); init_pwq(pwq, wq, &cpu_pools[highpri]); mutex_lock(&wq->mutex); link_pwq(pwq); mutex_unlock(&wq->mutex); } return 0; } get_online_cpus(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } put_online_cpus(); return ret; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; if (max_active < 1 || max_active > lim) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, lim); return clamp_val(max_active, 1, lim); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; int ret; if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) return -ENOMEM; rescuer->rescue_wq = wq; rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); kfree(rescuer); return ret; } wq->rescuer = rescuer; kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { size_t tbl_size = 0; va_list args; struct workqueue_struct *wq; struct pool_workqueue *pwq; /* * Unbound && max_active == 1 used to imply ordered, which is no * longer the case on NUMA machines due to per-node pools. While * alloc_ordered_workqueue() is the right way to create an ordered * workqueue, keep the previous behavior to avoid subtle breakages * on NUMA. */ if ((flags & WQ_UNBOUND) && max_active == 1) flags |= __WQ_ORDERED; /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]); wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs(); if (!wq->unbound_attrs) goto err_free_wq; } va_start(args, max_active); vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); /* init wq */ wq->flags = flags; wq->saved_max_active = max_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); if (alloc_and_link_pwqs(wq) < 0) goto err_unreg_lockdep; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; /* * wq_pool_mutex protects global freeze state and workqueues list. * Grab it, adjust max_active and add the new @wq to workqueues * list. */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); mutex_unlock(&wq_pool_mutex); return wq; err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_destroy: destroy_workqueue(wq); return NULL; } EXPORT_SYMBOL_GPL(alloc_workqueue); static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; if (pwq->nr_active || !list_empty(&pwq->inactive_works)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int node; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_workqueue_state(); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND)) { wq_unregister_lockdep(wq); /* * The base ref is never dropped on per-cpu pwqs. Directly * schedule RCU free. */ call_rcu(&wq->rcu, rcu_free_wq); } else { /* * We're the sole accessor of @wq at this point. Directly * access numa_pwq_tbl[] and dfl_pwq to put the base refs. * @wq will be freed when the last pwq is released. */ for_each_node(node) { pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL); put_pwq_unlocked(pwq); } /* * Put dfl_pwq. @wq may be freed any time after dfl_pwq is * put. Don't access it afterwards. */ pwq = wq->dfl_pwq; wq->dfl_pwq = NULL; put_pwq_unlocked(pwq); } } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { struct pool_workqueue *pwq; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * Note that both per-cpu and unbound workqueues may be associated with * multiple pool_workqueues which have separate congested states. A * workqueue being congested on one CPU doesn't mean the workqueue is also * contested on other CPUs / NUMA nodes. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; rcu_read_lock(); preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); if (!(wq->flags & WQ_UNBOUND)) pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); else pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); } static void pr_cont_work(bool comma, struct work_struct *work) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { pr_cont("%s %ps", comma ? "," : "", work->func); } } static void show_pwq(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d/%d refcnt=%d%s\n", pwq->nr_active, pwq->max_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont("%s %d%s:%ps", comma ? "," : "", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : "", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont("\n"); } } /** * show_workqueue_state - dump workqueue state * * Called from a sysrq handler or try_to_freeze_tasks() and prints out * all busy workqueues and pools. */ void show_workqueue_state(void) { struct workqueue_struct *wq; struct worker_pool *pool; unsigned long flags; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { struct pool_workqueue *pwq; bool idle = true; for_each_pwq(pwq, wq) { if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { idle = false; break; } } if (idle) continue; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); if (pwq->nr_active || !list_empty(&pwq->inactive_works)) show_pwq(pwq); raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_workqueue_state(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } for_each_pool(pool, pi) { struct worker *worker; bool first = true; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s%d", first ? "idle: " : "", task_pid_nr(worker->task)); first = false; } pr_cont("\n"); next_pool: raw_spin_unlock_irqrestore(&pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_workqueue_state(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { int off; /* always show the actual comm */ off = strscpy(buf, task->comm, size); if (off < 0) return; /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * except for the ones which are still executing works from * before the last CPU down must be on the cpu. After * this, they may become diasporas. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); /* * Call schedule() so that we cross rq->lock and thus can * guarantee sched callbacks see the %WORKER_UNBOUND flag. * This is necessary as scheduler callbacks may be invoked * from other cpus. */ schedule(); /* * Sched callbacks are disabled now. Zap nr_running. * After this, nr_running stays zero and need_more_worker() * and keep_working() are always true as long as the * worklist is not empty. This pool now behaves as an * unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ atomic_set(&pool->nr_running, 0); /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ raw_spin_lock_irq(&pool->lock); wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * A bound idle worker should actually be on the runqueue * of the associated CPU for local wake-ups targeting it to * work. Kick all idle workers so that they migrate to the * associated CPU. Doing this in the same loop as * replacing UNBOUND with REBOUND is safe as no worker will * be bound before @pool->lock is released. */ if (worker_flags & WORKER_IDLE) wake_up_process(worker->task); /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update NUMA affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) wq_update_unbound_numa(wq, cpu, true); mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update NUMA affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) wq_update_unbound_numa(wq, cpu, false); mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); /** * work_on_cpu_safe - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { long ret = -ENODEV; get_online_cpus(); if (cpu_online(cpu)) ret = work_on_cpu(cpu, fn, arg); put_online_cpus(); return ret; } EXPORT_SYMBOL_GPL(work_on_cpu_safe); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(void) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND)) continue; /* creating multiple pwqs breaks ordering guarantee */ if (!list_empty(&wq->pwqs)) { if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED; } ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs); if (!ctx) { ret = -ENOMEM; break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } return ret; } /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Retun: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; cpumask_var_t saved_cpumask; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { apply_wqattrs_lock(); if (cpumask_equal(cpumask, wq_unbound_cpumask)) { ret = 0; goto out_unlock; } if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) { ret = -ENOMEM; goto out_unlock; } /* save the old wq_unbound_cpumask. */ cpumask_copy(saved_cpumask, wq_unbound_cpumask); /* update wq_unbound_cpumask at first and apply it to wqs. */ cpumask_copy(wq_unbound_cpumask, cpumask); ret = workqueue_apply_unbound_cpumask(); /* restore the wq_unbound_cpumask when failed. */ if (ret < 0) cpumask_copy(wq_unbound_cpumask, saved_cpumask); free_cpumask_var(saved_cpumask); out_unlock: apply_wqattrs_unlock(); } return ret; } #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * pool_ids RO int : the associated pool IDs for each node * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * numa RW bool : whether enable NUMA affinity */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_pool_ids_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); const char *delim = ""; int node, written = 0; get_online_cpus(); rcu_read_lock(); for_each_node(node) { written += scnprintf(buf + written, PAGE_SIZE - written, "%s%d:%d", delim, node, unbound_pwq_by_node(wq, node)->pool->id); delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); rcu_read_unlock(); put_online_cpus(); return written; } static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", !wq->unbound_attrs->no_numa); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = -EINVAL; if (sscanf(buf, "%d", &v) == 1) { attrs->no_numa = !v; ret = apply_workqueue_attrs_locked(wq, attrs); } out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(numa, 0644, wq_numa_show, wq_numa_store), __ATTR_NULL, }; static struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; static ssize_t wq_unbound_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq_unbound_cpumask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t wq_unbound_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static struct device_attribute wq_sysfs_cpumask_attr = __ATTR(cpumask, 0644, wq_unbound_cpumask_show, wq_unbound_cpumask_store); static int __init wq_sysfs_init(void) { int err; err = subsys_virtual_register(&wq_subsys, NULL); if (err) return err; return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active or creating new pwqs by applying * attributes breaks ordering guarantee. Disallow exposing ordered * workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ pool_ts = READ_ONCE(pool->watchdog_ts); touched = READ_ONCE(wq_watchdog_touched); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; if (pool->cpu >= 0) { unsigned long cpu_touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); if (time_after(cpu_touched, ts)) ts = cpu_touched; } /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_workqueue_state(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; else wq_watchdog_touched = jiffies; } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void __init wq_numa_init(void) { cpumask_var_t *tbl; int node, cpu; if (num_possible_nodes() <= 1) return; if (wq_disable_numa) { pr_info("workqueue: NUMA affinity support disabled\n"); return; } for_each_possible_cpu(cpu) { if (WARN_ON(cpu_to_node(cpu) == NUMA_NO_NODE)) { pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); return; } } wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!wq_update_unbound_numa_attrs_buf); /* * We want masks of possible CPUs of each node which isn't readily * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); cpumask_set_cpu(cpu, tbl[node]); } wq_numa_possible_cpumask = tbl; wq_numa_enabled = true; } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first half of two-staged workqueue subsystem initialization * and invoked as soon as the bare basics - memory allocation, cpumasks and * idr are up. It sets up all the data structures and system workqueues * and allows early boot code to create workqueues and queue/cancel work * items. Actual work item execution starts only after kthreads can be * created and scheduled right before early initcalls. */ void __init workqueue_init_early(void) { int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_cpu_worker_pool(pool, cpu) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. * Turn off NUMA so that dfl_pwq is used for all nodes. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->no_numa = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq); } /** * workqueue_init - bring workqueue subsystem fully online * * This is the latter half of two-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. * Workqueues have been created and work items queued on them, but there * are no kworkers executing the work items yet. Populate the worker pools * with the initial workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some * archs such as power and arm64. As per-cpu pools created * previously could be missing node hint and unbound pools NUMA * affinity, fix them up. * * Also, while iterating workqueues, create rescuers if requested. */ wq_numa_init(); mutex_lock(&wq_pool_mutex); for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->node = cpu_to_node(cpu); } } list_for_each_entry(wq, &workqueues, list) { wq_update_unbound_numa(wq, smp_processor_id(), true); WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* create the initial workers */ for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rcuwait writer; wait_queue_head_t waiters; atomic_t block; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }, #else #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) #endif #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \ .block = ATOMIC_INIT(0), \ __PERCPU_RWSEM_DEP_MAP_INIT(name) \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool); static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); preempt_disable(); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); } static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked * writer. */ smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); } extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_held(sem) lockdep_is_held(sem) #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_release(&sem->dep_map, ip); } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip); } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H #include <asm/processor.h> #if defined(__KERNEL__) && !defined(__ASSEMBLY__) #include <asm/asm.h> #include <linux/bitops.h> #include <asm/alternative.h> enum cpuid_leafs { CPUID_1_EDX = 0, CPUID_8000_0001_EDX, CPUID_8086_0001_EDX, CPUID_LNX_1, CPUID_1_ECX, CPUID_C000_0001_EDX, CPUID_8000_0001_ECX, CPUID_LNX_2, CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, CPUID_LNX_4, CPUID_7_1_EAX, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, CPUID_LNX_5, CPUID_8000_0021_ECX, NR_CPUID_WORDS, }; #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] #else #define X86_CAP_FMT "%d:%d" #define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31) #endif /* * In order to save room, we index into this array by doing * X86_BUG_<name> - NCAPINTS*32. */ extern const char * const x86_bug_flags[NBUGINTS*32]; #define test_cpu_cap(c, bit) \ arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) /* * There are 32 bits/features in each mask word. The high bits * (selected with (bit>>5) give us the word number and the low 5 * bits give us the bit/feature number inside the word. * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can * see if it is set in the mask word. */ #define CHECK_BIT_IN_MASK_WORD(maskname, word, bit) \ (((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word )) /* * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all * header macros which use NCAPINTS need to be changed. The duplicated macro * use causes the compiler to issue errors for all headers so that all usage * sites can be corrected. */ #define REQUIRED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 1, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 2, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 3, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 4, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 5, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 6, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 7, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 8, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 9, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ BUILD_BUG_ON_ZERO(NCAPINTS != 23)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 1, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 2, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 3, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 4, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 5, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 6, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 7, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 8, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 9, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ BUILD_BUG_ON_ZERO(NCAPINTS != 23)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, \ (unsigned long __percpu *)&cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel * infrastructure to be used. It may *not* directly test the CPU * itself. Use the cpu_has() family if you want true runtime * testing of CPU features, like in hypervisor code where you are * supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) extern void setup_clear_cpu_cap(unsigned int bit); extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_cap(bit) do { \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) #if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) /* * Workaround for the sake of BPF compilation which utilizes kernel * headers, but clang does not support ASM GOTO and fails the build. */ #ifndef __BPF_TRACING__ #warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments" #endif #define static_cpu_has(bit) boot_cpu_has(bit) #else /* * Static testing of CPU features. Used the same as boot_cpu_has(). It * statically patches the target code for additional performance. Use * static_cpu_has() only in fast paths, where every cycle counts. Which * means that the boot_cpu_has() variant is already fast enough for the * majority of cases and you should stick to using it as it is generally * only two instructions: a RIP-relative MOV and a TEST. */ static __always_inline bool _static_cpu_has(u16 bit) { asm_volatile_goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".section .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum],%[cap_byte]\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".previous\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; t_no: return false; } #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) #endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) #define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) #define cpu_have_feature boot_cpu_has #define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ #endif /* _ASM_X86_CPUFEATURE_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * NSA Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <sds@tycho.nsa.gov> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { struct super_block *sb; /* back pointer to sb object */ u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct *selinux_inode( const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct *selinux_msg_msg( const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct *selinux_ipc( const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } #endif /* _SELINUX_OBJSEC_H_ */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases. * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value * * Return: microseconds value */ unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /** * mktime64 - Converts date to seconds. * @year0: year to convert * @mon0: month to convert * @day: day to convert * @hour: hour to convert * @min: minute to convert * @sec: second to convert * * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. * * Return: seconds since the epoch time for the given input date */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC. * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Return: the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(const s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * the _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h * * Return: jiffies value */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); /** * __usecs_to_jiffies: - convert microseconds to jiffies * @u: time in milliseconds * * Return: jiffies value */ unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /** * timespec64_to_jiffies - convert a timespec64 value to jiffies * @value: pointer to &struct timespec64 * * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. * * Return: jiffies value */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); /** * jiffies_to_timespec64 - convert jiffies value to &struct timespec64 * @jiffies: jiffies value * @value: pointer to &struct timespec64 */ void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ /** * jiffies_to_clock_t - Convert jiffies to clock_t * @x: jiffies value * * Return: jiffies converted to clock_t (CLOCKS_PER_SEC) */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); /** * clock_t_to_jiffies - Convert clock_t to jiffies * @x: clock_t value * * Return: clock_t value converted to jiffies */ unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); /** * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t * @x: jiffies_64 value * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ notrace u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); /** * nsec_to_clock_t - Convert nsec value to clock_t * @x: nsec value * * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } /** * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds * @j: jiffies64 value * * Return: nanoseconds value */ u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); /** * jiffies64_to_msecs - Convert jiffies64 to milliseconds * @j: jiffies64 value * * Return: milliseconds value */ u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies64 value */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies value */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /** * timespec64_add_safe - Add two timespec64 values and do a safety check * for overflow. * @lhs: first (left) timespec64 to add * @rhs: second (right) timespec64 to add * * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. * * Return: sum of @lhs + @rhs */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } /** * get_timespec64 - get user's time value into kernel space * @ts: destination &struct timespec64 * @uts: user's time value as &struct __kernel_timespec * * Handles compat or 32-bit modes. * * Return: %0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); /** * put_timespec64 - convert timespec64 value to __kernel_timespec format and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * * Return: %0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } /** * get_old_timespec32 - get user's old-format time value into kernel space * @ts: destination &struct timespec64 * @uts: user's old-format time value (&struct old_timespec32) * * Handles X86_X32_ABI compatibility conversion. * * Return: %0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); /** * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct old_timespec32 * * Handles X86_X32_ABI compatibility conversion. * * Return: %0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); /** * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: %0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); /** * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format * and copy the latter to userspace * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: %0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); /** * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: %0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); /** * put_old_itimerspec32 - convert &struct itimerspec64 to &struct * old_itimerspec32 and copy the latter to userspace * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: %0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Returns 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * Returns 0 if successful, -ve on error. */ int cap_inode_killpriv(struct dentry *dentry) { int error; error = __vfs_removexattr(dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(kuid_t kroot) { struct user_namespace *ns; if (!uid_valid(kroot)) return false; for (ns = current_user_ns(); ; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; kuid_t kroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = sizeof(struct vfs_ns_cap_data); ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0 || !tmpbuf) { size = ret; goto out_free; } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { root = 0; } else if (is_v3header((size_t) ret, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(kroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return make_kuid(task_ns, rootid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /* * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If all is ok, we return the new size, on error return < 0. */ int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; rootid = rootid_from_xattr(*ivalue, size, task_ns); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); kvfree(*ivalue); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.cap[i] = (new->cap_bset.cap[i] & permitted) | (new->cap_inheritable.cap[i] & inheritable); if (permitted & ~new->cap_permitted.cap[i]) /* insufficient to execute correctly */ ret = -EPERM; } /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /* * Extract the on-exec-apply capability sets for an executable file. */ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!rootid_owns_currentns(rootkuid)) return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->rootid = rootkuid; return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. Returns 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied, returning 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilties to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Detemine if scheduler policy change is permitted * @p: The task to affect * * Detemine if the requested scheduler policy change is permitted for the * specified task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_ioprio - Detemine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Detemine if the requested I/O priority change is permitted for the specified * task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_ioprio - Detemine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Detemine if the requested task priority change is permitted for the * specified task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2, @arg3, @arg4, @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Returns 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted, returning 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /* * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. Returns 0 if this mapping should be allowed * -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kernfs.h - pseudo filesystem decoupled from vfs locking */ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H #include <linux/kernel.h> #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/wait.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; struct super_block; struct file_system_type; struct poll_table_struct; struct fs_context; struct kernfs_fs_context; struct kernfs_open_node; struct kernfs_iattrs; enum kernfs_node_type { KERNFS_DIR = 0x0001, KERNFS_FILE = 0x0002, KERNFS_LINK = 0x0004, }; #define KERNFS_TYPE_MASK 0x000f #define KERNFS_FLAG_MASK ~KERNFS_TYPE_MASK #define KERNFS_MAX_USER_XATTRS 128 #define KERNFS_USER_XATTR_SIZE_LIMIT (128 << 10) enum kernfs_node_flag { KERNFS_ACTIVATED = 0x0010, KERNFS_NS = 0x0020, KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, KERNFS_HAS_RELEASE = 0x2000, }; /* @flags for kernfs_create_root() */ enum kernfs_root_flag { /* * kernfs_nodes are created in the deactivated state and invisible. * They require explicit kernfs_activate() to become visible. This * can be used to make related nodes become visible atomically * after all nodes are created successfully. */ KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, /* * For regular files, if the opener has CAP_DAC_OVERRIDE, open(2) * succeeds regardless of the RW permissions. sysfs had an extra * layer of enforcement where open(2) fails with -EACCES regardless * of CAP_DAC_OVERRIDE if the permission doesn't have the * respective read or write access at all (none of S_IRUGO or * S_IWUGO) or the respective operation isn't implemented. The * following flag enables that behavior. */ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, /* * The filesystem supports exportfs operation, so userspace can use * fhandle to access nodes of the fs. */ KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, /* * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, }; /* type-specific structures for kernfs_node union members */ struct kernfs_elem_dir { unsigned long subdirs; /* children rbtree starts here and goes through kn->rb */ struct rb_root children; /* * The kernfs hierarchy this directory belongs to. This fits * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; }; struct kernfs_elem_symlink { struct kernfs_node *target_kn; }; struct kernfs_elem_attr { const struct kernfs_ops *ops; struct kernfs_open_node *open; loff_t size; struct kernfs_node *notify_next; /* for kernfs_notify() */ }; /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are * private to kernfs and shouldn't be accessed directly by kernfs users. * * As long as s_count reference is held, the kernfs_node itself is * accessible. Dereferencing elem or any other outer entity requires * active reference. */ struct kernfs_node { atomic_t count; atomic_t active; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* * Use kernfs_get_parent() and kernfs_name/path() instead of * accessing the following two fields directly. If the node is * never moved to a different parent, it is safe to access the * parent directly. */ struct kernfs_node *parent; const char *name; struct rb_node rb; const void *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ union { struct kernfs_elem_dir dir; struct kernfs_elem_symlink symlink; struct kernfs_elem_attr attr; }; void *priv; /* * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, * the low 32bits are ino and upper generation. */ u64 id; unsigned short flags; umode_t mode; struct kernfs_iattrs *iattr; }; /* * kernfs_syscall_ops may be specified on kernfs_create_root() to support * syscalls. These optional callbacks are invoked on the matching syscalls * and can perform any kernfs operations which don't necessarily have to be * the exact operation requested. An active reference is held for each * kernfs_node parameter. */ struct kernfs_syscall_ops { int (*show_options)(struct seq_file *sf, struct kernfs_root *root); int (*mkdir)(struct kernfs_node *parent, const char *name, umode_t mode); int (*rmdir)(struct kernfs_node *kn); int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name); int (*show_path)(struct seq_file *sf, struct kernfs_node *kn, struct kernfs_root *root); }; struct kernfs_root { /* published fields */ struct kernfs_node *kn; unsigned int flags; /* KERNFS_ROOT_* flags */ /* private fields, do not use outside kernfs proper */ struct idr ino_idr; u32 last_id_lowbits; u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_mutex */ struct list_head supers; wait_queue_head_t deactivate_waitq; }; struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ struct mutex mutex; struct mutex prealloc_mutex; int event; struct list_head list; char *prealloc_buf; size_t atomic_write_len; bool mmapped:1; bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* * Optional open/release methods. Both are called with * @of->seq_file populated. */ int (*open)(struct kernfs_open_file *of); void (*release)(struct kernfs_open_file *of); /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq * operations are optional and if not implemented, the behavior is * equivalent to single_open(). @sf->private points to the * associated kernfs_open_file. * * read() is bounced through kernel buffer and a read larger than * PAGE_SIZE results in partial operation of PAGE_SIZE. */ int (*seq_show)(struct seq_file *sf, void *v); void *(*seq_start)(struct seq_file *sf, loff_t *ppos); void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); void (*seq_stop)(struct seq_file *sf, void *v); ssize_t (*read)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); /* * write() is bounced through kernel buffer. If atomic_write_len * is not set, a write larger than PAGE_SIZE results in partial * operations of PAGE_SIZE chunks. If atomic_write_len is set, * writes upto the specified size are executed atomically but * larger ones are rejected with -E2BIG. */ size_t atomic_write_len; /* * "prealloc" causes a buffer to be allocated at open for * all read/write requests. As ->seq_show uses seq_read() * which does its own allocation, it is incompatible with * ->prealloc. Provide ->read and ->write with ->prealloc. */ bool prealloc; ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif }; /* * The kernfs superblock creation/mount parameter context. */ struct kernfs_fs_context { struct kernfs_root *root; /* Root of the hierarchy being mounted */ void *ns_tag; /* Namespace tag of the mount (or NULL) */ unsigned long magic; /* File system specific magic number */ /* The following are set/used by kernfs_mount() */ bool new_sb_created; /* Set to T if we allocated a new sb */ }; #ifdef CONFIG_KERNFS static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return kn->flags & KERNFS_TYPE_MASK; } static inline ino_t kernfs_id_ino(u64 id) { /* id is ino if ino_t is 64bit; otherwise, low 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return id; else return (u32)id; } static inline u32 kernfs_id_gen(u64 id) { /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return 1; else return id >> 32; } static inline ino_t kernfs_ino(struct kernfs_node *kn) { return kernfs_id_ino(kn->id); } static inline ino_t kernfs_gen(struct kernfs_node *kn) { return kernfs_id_gen(kn->id); } /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty * * This is to be called right after @kn is created to enable namespace * under it. All children of @kn must have non-NULL namespace tags and * only the ones which match the super_block's tag will be visible. */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); WARN_ON_ONCE(!RB_EMPTY_ROOT(&kn->dir.children)); kn->flags |= KERNFS_NS; } /** * kernfs_ns_enabled - test whether namespace is enabled * @kn: the node to test * * Test whether namespace filtering is enabled for the children of @ns. */ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return kn->flags & KERNFS_NS; } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns); struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns); void kernfs_get(struct kernfs_node *kn); void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key); struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target); void kernfs_activate(struct kernfs_node *kn); void kernfs_remove(struct kernfs_node *kn); void kernfs_break_active_protection(struct kernfs_node *kn); void kernfs_unbreak_active_protection(struct kernfs_node *kn); bool kernfs_remove_self(struct kernfs_node *kn); int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns); int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size); int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags); const void *kernfs_super_ns(struct super_block *sb); int kernfs_get_tree(struct fs_context *fc); void kernfs_free_fs_context(struct fs_context *fc); void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return 0; } /* whatever */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { } static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return false; } static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { } static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { return NULL; } static inline struct kernfs_node * kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { return NULL; } static inline struct kernfs_node * kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { return NULL; } static inline void kernfs_get(struct kernfs_node *kn) { } static inline void kernfs_put(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { return NULL; } static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } static inline struct inode * kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { return NULL; } static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { return ERR_PTR(-ENOSYS); } static inline void kernfs_activate(struct kernfs_node *kn) { } static inline void kernfs_remove(struct kernfs_node *kn) { } static inline bool kernfs_remove_self(struct kernfs_node *kn) { return false; } static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn, const char *name, const void *ns) { return -ENOSYS; } static inline int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { return -ENOSYS; } static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } static inline void kernfs_notify(struct kernfs_node *kn) { } static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size) { return -ENOSYS; } static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags) { return -ENOSYS; } static inline const void *kernfs_super_ns(struct super_block *sb) { return NULL; } static inline int kernfs_get_tree(struct fs_context *fc) { return -ENOSYS; } static inline void kernfs_free_fs_context(struct fs_context *fc) { } static inline void kernfs_kill_sb(struct super_block *sb) { } static inline void kernfs_init(void) { } #endif /* CONFIG_KERNFS */ /** * kernfs_path - build full path of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * If @kn is NULL result will be "(null)". * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return kernfs_path_from_node(kn, NULL, buf, buflen); } static inline struct kernfs_node * kernfs_find_and_get(struct kernfs_node *kn, const char *name) { return kernfs_find_and_get_ns(kn, name, NULL); } static inline struct kernfs_node * kernfs_walk_and_get(struct kernfs_node *kn, const char *path) { return kernfs_walk_and_get_ns(kn, path, NULL); } static inline struct kernfs_node * kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, void *priv) { return kernfs_create_dir_ns(parent, name, mode, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, priv, NULL); } static inline struct kernfs_node * kernfs_create_file_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns) { struct lock_class_key *key = NULL; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = (struct lock_class_key *)&ops->lockdep_key; #endif return __kernfs_create_file(parent, name, mode, uid, gid, size, ops, priv, ns, key); } static inline struct kernfs_node * kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, const struct kernfs_ops *ops, void *priv) { return kernfs_create_file_ns(parent, name, mode, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, size, ops, priv, NULL); } static inline int kernfs_remove_by_name(struct kernfs_node *parent, const char *name) { return kernfs_remove_by_name_ns(parent, name, NULL); } static inline int kernfs_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name) { return kernfs_rename_ns(kn, new_parent, new_name, NULL); } #endif /* __LINUX_KERNFS_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const void *kobject_namespace(struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } /* * populate_dir - populate directory with attributes. * @kobj: object we're working on. * * Most subsystems have a set of default attributes that are associated * with an object that registers with them. This is a helper called during * object registration that loops through the default attributes of the * subsystem and creates attributes files for them in sysfs. */ static int populate_dir(struct kobject *kobj) { struct kobj_type *t = get_ktype(kobj); struct attribute *attr; int error = 0; int i; if (t && t->default_attrs) { for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) { error = sysfs_create_file(kobj, attr); if (error) break; } } return error; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; error = populate_dir(kobj); if (error) { sysfs_remove_dir(kobj); return error; } if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(ops->type <= KOBJ_NS_TYPE_NONE); BUG_ON(ops->type >= KOBJ_NS_TYPES); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(struct kobject *kobj) { int length = 1; struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(struct kobject *kobj, char *path, int length) { struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("kobject: '%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("kobject: '%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; strreplace(t, '/', '!'); s = t; } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack(); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack(); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("kobject: can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack(); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("kobject: '%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("kobject: '%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("kobject: '%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("kobject: '%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("kobject: '%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("kobject: '%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * (get_random_int() & 0x3); pr_info("kobject: '%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("kobject: (%p): %s\n", kobj, __func__); kfree(kobj); } static struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) return err; kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc(sizeof(*kset), GFP_KERNEL); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (type >= KOBJ_NS_TYPES) goto out; error = -EINVAL; if (type <= KOBJ_NS_TYPE_NONE) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } void *kobj_ns_grab_current(enum kobj_ns_type type) { void *ns = NULL; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); spin_unlock(&kobj_ns_type_lock); return ns; } const void *kobj_ns_initial(enum kobj_ns_type type) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->initial_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/blkdev.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/blk-cgroup.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wakeup_delayed(struct bdi_writeback *wb); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; extern struct workqueue_struct *bdi_async_bio_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void __add_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); /* * Flags in backing_dev_info::capability * * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages * should contribute to accounting * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ #define BDI_CAP_WRITEBACK (1 << 0) #define BDI_CAP_WRITEBACK_ACCT (1 << 1) #define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_bdi; #endif return sb->s_bdi; } static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { return wb->congested & cong_bits; } long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } static inline int bdi_sched_wait(void *word) { schedule(); return 0; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct blkcg *blkcg); int inode_congested(struct inode *inode, int cong_bits); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * Cgroup writeback requires support from the filesystem. Also, both memcg and * iocg have to be on the default hierarchy. Test whether all conditions are * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb_is_valid - test whether an inode has a wb associated * @inode: inode of interest * * Returns %true if @inode has a wb associated. May be called without any * locking. */ static inline bool inode_to_wb_is_valid(struct inode *inode) { return inode->i_wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (inode->i_sb->s_iflags & SB_I_CGROUPWB) && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline bool inode_to_wb_is_valid(struct inode *inode) { return true; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct blkcg *blkcg) { } static inline int inode_congested(struct inode *inode, int cong_bits) { return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } #endif /* CONFIG_CGROUP_WRITEBACK */ static inline int inode_read_congested(struct inode *inode) { return inode_congested(inode, 1 << WB_sync_congested); } static inline int inode_write_congested(struct inode *inode) { return inode_congested(inode, 1 << WB_async_congested); } static inline int inode_rw_congested(struct inode *inode) { return inode_congested(inode, (1 << WB_sync_congested) | (1 << WB_async_congested)); } static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) { return wb_congested(&bdi->wb, cong_bits); } static inline int bdi_read_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, 1 << WB_sync_congested); } static inline int bdi_write_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, 1 << WB_async_congested); } static inline int bdi_rw_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, (1 << WB_sync_congested) | (1 << WB_async_congested)); } const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * * File: integrity_iint.c * - implements the integrity hooks: integrity_inode_alloc, * integrity_inode_free * - cache integrity information associated with an inode * using a rbtree tree. */ #include <linux/slab.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/file.h> #include <linux/uaccess.h> #include <linux/security.h> #include <linux/lsm_hooks.h> #include "integrity.h" static struct rb_root integrity_iint_tree = RB_ROOT; static DEFINE_RWLOCK(integrity_iint_lock); static struct kmem_cache *iint_cache __read_mostly; struct dentry *integrity_dir; /* * __integrity_iint_find - return the iint associated with an inode */ static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode) { struct integrity_iint_cache *iint; struct rb_node *n = integrity_iint_tree.rb_node; while (n) { iint = rb_entry(n, struct integrity_iint_cache, rb_node); if (inode < iint->inode) n = n->rb_left; else if (inode > iint->inode) n = n->rb_right; else return iint; } return NULL; } /* * integrity_iint_find - return the iint associated with an inode */ struct integrity_iint_cache *integrity_iint_find(struct inode *inode) { struct integrity_iint_cache *iint; if (!IS_IMA(inode)) return NULL; read_lock(&integrity_iint_lock); iint = __integrity_iint_find(inode); read_unlock(&integrity_iint_lock); return iint; } #define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH+1) /* * It is not clear that IMA should be nested at all, but as long is it measures * files both on overlayfs and on underlying fs, we need to annotate the iint * mutex to avoid lockdep false positives related to IMA + overlayfs. * See ovl_lockdep_annotate_inode_mutex_key() for more details. */ static inline void iint_lockdep_annotate(struct integrity_iint_cache *iint, struct inode *inode) { #ifdef CONFIG_LOCKDEP static struct lock_class_key iint_mutex_key[IMA_MAX_NESTING]; int depth = inode->i_sb->s_stack_depth; if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING)) depth = 0; lockdep_set_class(&iint->mutex, &iint_mutex_key[depth]); #endif } static void iint_init_always(struct integrity_iint_cache *iint, struct inode *inode) { iint->ima_hash = NULL; iint->version = 0; iint->flags = 0UL; iint->atomic_flags = 0UL; iint->ima_file_status = INTEGRITY_UNKNOWN; iint->ima_mmap_status = INTEGRITY_UNKNOWN; iint->ima_bprm_status = INTEGRITY_UNKNOWN; iint->ima_read_status = INTEGRITY_UNKNOWN; iint->ima_creds_status = INTEGRITY_UNKNOWN; iint->evm_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; mutex_init(&iint->mutex); iint_lockdep_annotate(iint, inode); } static void iint_free(struct integrity_iint_cache *iint) { kfree(iint->ima_hash); mutex_destroy(&iint->mutex); kmem_cache_free(iint_cache, iint); } /** * integrity_inode_get - find or allocate an iint associated with an inode * @inode: pointer to the inode * @return: allocated iint * * Caller must lock i_mutex */ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) { struct rb_node **p; struct rb_node *node, *parent = NULL; struct integrity_iint_cache *iint, *test_iint; /* * The integrity's "iint_cache" is initialized at security_init(), * unless it is not included in the ordered list of LSMs enabled * on the boot command line. */ if (!iint_cache) panic("%s: lsm=integrity required.\n", __func__); iint = integrity_iint_find(inode); if (iint) return iint; iint = kmem_cache_alloc(iint_cache, GFP_NOFS); if (!iint) return NULL; iint_init_always(iint, inode); write_lock(&integrity_iint_lock); p = &integrity_iint_tree.rb_node; while (*p) { parent = *p; test_iint = rb_entry(parent, struct integrity_iint_cache, rb_node); if (inode < test_iint->inode) { p = &(*p)->rb_left; } else if (inode > test_iint->inode) { p = &(*p)->rb_right; } else { write_unlock(&integrity_iint_lock); kmem_cache_free(iint_cache, iint); return test_iint; } } iint->inode = inode; node = &iint->rb_node; inode->i_flags |= S_IMA; rb_link_node(node, parent, p); rb_insert_color(node, &integrity_iint_tree); write_unlock(&integrity_iint_lock); return iint; } /** * integrity_inode_free - called on security_inode_free * @inode: pointer to the inode * * Free the integrity information(iint) associated with an inode. */ void integrity_inode_free(struct inode *inode) { struct integrity_iint_cache *iint; if (!IS_IMA(inode)) return; write_lock(&integrity_iint_lock); iint = __integrity_iint_find(inode); rb_erase(&iint->rb_node, &integrity_iint_tree); write_unlock(&integrity_iint_lock); iint_free(iint); } static void iint_init_once(void *foo) { struct integrity_iint_cache *iint = foo; memset(iint, 0, sizeof(*iint)); } static int __init integrity_iintcache_init(void) { iint_cache = kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache), 0, SLAB_PANIC, iint_init_once); return 0; } DEFINE_LSM(integrity) = { .name = "integrity", .init = integrity_iintcache_init, }; /* * integrity_kernel_read - read data from the file * * This is a function for reading file content instead of kernel_read(). * It does not perform locking checks to ensure it cannot be blocked. * It does not perform security checks because it is irrelevant for IMA. * */ int integrity_kernel_read(struct file *file, loff_t offset, void *addr, unsigned long count) { return __kernel_read(file, addr, count, &offset); } /* * integrity_load_keys - load integrity keys hook * * Hooks is called from init/main.c:kernel_init_freeable() * when rootfs is ready */ void __init integrity_load_keys(void) { ima_load_x509(); evm_load_x509(); } static int __init integrity_fs_init(void) { integrity_dir = securityfs_create_dir("integrity", NULL); if (IS_ERR(integrity_dir)) { int ret = PTR_ERR(integrity_dir); if (ret != -ENODEV) pr_err("Unable to create integrity sysfs dir: %d\n", ret); integrity_dir = NULL; return ret; } return 0; } late_initcall(integrity_fs_init) |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/group.c - Operations for adding/removing multiple files at once. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2013 Greg Kroah-Hartman * Copyright (c) 2013 The Linux Foundation */ #include <linux/kobject.h> #include <linux/module.h> #include <linux/dcache.h> #include <linux/namei.h> #include <linux/err.h> #include <linux/fs.h> #include "sysfs.h" static void remove_files(struct kernfs_node *parent, const struct attribute_group *grp) { struct attribute *const *attr; struct bin_attribute *const *bin_attr; if (grp->attrs) for (attr = grp->attrs; *attr; attr++) kernfs_remove_by_name(parent, (*attr)->name); if (grp->bin_attrs) for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); } static int create_files(struct kernfs_node *parent, struct kobject *kobj, kuid_t uid, kgid_t gid, const struct attribute_group *grp, int update) { struct attribute *const *attr; struct bin_attribute *const *bin_attr; int error = 0, i; if (grp->attrs) { for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { umode_t mode = (*attr)->mode; /* * In update mode, we're changing the permissions or * visibility. Do this by first removing then * re-adding (if required) the file. */ if (update) kernfs_remove_by_name(parent, (*attr)->name); if (grp->is_visible) { mode = grp->is_visible(kobj, *attr, i); if (!mode) continue; } WARN(mode & ~(SYSFS_PREALLOC | 0664), "Attribute %s: Invalid permissions 0%o\n", (*attr)->name, mode); mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, *attr, false, mode, uid, gid, NULL); if (unlikely(error)) break; } if (error) { remove_files(parent, grp); goto exit; } } if (grp->bin_attrs) { for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { umode_t mode = (*bin_attr)->attr.mode; if (update) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); if (grp->is_bin_visible) { mode = grp->is_bin_visible(kobj, *bin_attr, i); if (!mode) continue; } WARN(mode & ~(SYSFS_PREALLOC | 0664), "Attribute %s: Invalid permissions 0%o\n", (*bin_attr)->attr.name, mode); mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, &(*bin_attr)->attr, true, mode, uid, gid, NULL); if (error) break; } if (error) remove_files(parent, grp); } exit: return error; } static int internal_create_group(struct kobject *kobj, int update, const struct attribute_group *grp) { struct kernfs_node *kn; kuid_t uid; kgid_t gid; int error; if (WARN_ON(!kobj || (!update && !kobj->sd))) return -EINVAL; /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; if (!grp->attrs && !grp->bin_attrs) { WARN(1, "sysfs: (bin_)attrs not set by subsystem for group: %s/%s\n", kobj->name, grp->name ?: ""); return -EINVAL; } kobject_get_ownership(kobj, &uid, &gid); if (grp->name) { if (update) { kn = kernfs_find_and_get(kobj->sd, grp->name); if (!kn) { pr_warn("Can't update unknown attr grp name: %s/%s\n", kobj->name, grp->name); return -EINVAL; } } else { kn = kernfs_create_dir_ns(kobj->sd, grp->name, S_IRWXU | S_IRUGO | S_IXUGO, uid, gid, kobj, NULL); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(kobj->sd, grp->name); return PTR_ERR(kn); } } } else kn = kobj->sd; kernfs_get(kn); error = create_files(kn, kobj, uid, gid, grp, update); if (error) { if (grp->name) kernfs_remove(kn); } kernfs_put(kn); if (grp->name && update) kernfs_put(kn); return error; } /** * sysfs_create_group - given a directory kobject, create an attribute group * @kobj: The kobject to create the group on * @grp: The attribute group to create * * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * * Returns 0 on success or error code on failure. */ int sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 0, grp); } EXPORT_SYMBOL_GPL(sysfs_create_group); static int internal_create_groups(struct kobject *kobj, int update, const struct attribute_group **groups) { int error = 0; int i; if (!groups) return 0; for (i = 0; groups[i]; i++) { error = internal_create_group(kobj, update, groups[i]); if (error) { while (--i >= 0) sysfs_remove_group(kobj, groups[i]); break; } } return error; } /** * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to create the group on * @groups: The attribute groups to create, NULL terminated * * This function creates a bunch of attribute groups. If an error occurs when * creating a group, all previously created groups will be removed, unwinding * everything back to the original state when this function was called. * It will explicitly warn and error if any of the attribute files being * created already exist. * * Returns 0 on success or error code from sysfs_create_group on failure. */ int sysfs_create_groups(struct kobject *kobj, const struct attribute_group **groups) { return internal_create_groups(kobj, 0, groups); } EXPORT_SYMBOL_GPL(sysfs_create_groups); /** * sysfs_update_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to update the group on * @groups: The attribute groups to update, NULL terminated * * This function update a bunch of attribute groups. If an error occurs when * updating a group, all previously updated groups will be removed together * with already existing (not updated) attributes. * * Returns 0 on success or error code from sysfs_update_group on failure. */ int sysfs_update_groups(struct kobject *kobj, const struct attribute_group **groups) { return internal_create_groups(kobj, 1, groups); } EXPORT_SYMBOL_GPL(sysfs_update_groups); /** * sysfs_update_group - given a directory kobject, update an attribute group * @kobj: The kobject to update the group on * @grp: The attribute group to update * * This function updates an attribute group. Unlike * sysfs_create_group(), it will explicitly not warn or error if any * of the attribute files being created already exist. Furthermore, * if the visibility of the files has changed through the is_visible() * callback, it will update the permissions and add or remove the * relevant files. Changing a group's name (subdirectory name under * kobj's directory in sysfs) is not allowed. * * The primary use for this function is to call it after making a change * that affects group visibility. * * Returns 0 on success or error code on failure. */ int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 1, grp); } EXPORT_SYMBOL_GPL(sysfs_update_group); /** * sysfs_remove_group: remove a group from a kobject * @kobj: kobject to remove the group from * @grp: group to remove * * This function removes a group of attributes from a kobject. The attributes * previously have to have been created for this group, otherwise it will fail. */ void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent = kobj->sd; struct kernfs_node *kn; if (grp->name) { kn = kernfs_find_and_get(parent, grp->name); if (!kn) { WARN(!kn, KERN_WARNING "sysfs group '%s' not found for kobject '%s'\n", grp->name, kobject_name(kobj)); return; } } else { kn = parent; kernfs_get(kn); } remove_files(kn, grp); if (grp->name) kernfs_remove(kn); kernfs_put(kn); } EXPORT_SYMBOL_GPL(sysfs_remove_group); /** * sysfs_remove_groups - remove a list of groups * * @kobj: The kobject for the groups to be removed from * @groups: NULL terminated list of groups to be removed * * If groups is not NULL, remove the specified groups from the kobject. */ void sysfs_remove_groups(struct kobject *kobj, const struct attribute_group **groups) { int i; if (!groups) return; for (i = 0; groups[i]; i++) sysfs_remove_group(kobj, groups[i]); } EXPORT_SYMBOL_GPL(sysfs_remove_groups); /** * sysfs_merge_group - merge files into a pre-existing attribute group. * @kobj: The kobject containing the group. * @grp: The files to create and the attribute group they belong to. * * This function returns an error if the group doesn't exist or any of the * files already exist in that group, in which case none of the new files * are created. */ int sysfs_merge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; kuid_t uid; kgid_t gid; int error = 0; struct attribute *const *attr; int i; parent = kernfs_find_and_get(kobj->sd, grp->name); if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr)) error = sysfs_add_file_mode_ns(parent, *attr, false, (*attr)->mode, uid, gid, NULL); if (error) { while (--i >= 0) kernfs_remove_by_name(parent, (*--attr)->name); } kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_merge_group); /** * sysfs_unmerge_group - remove files from a pre-existing attribute group. * @kobj: The kobject containing the group. * @grp: The files to remove and the attribute group they belong to. */ void sysfs_unmerge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; struct attribute *const *attr; parent = kernfs_find_and_get(kobj->sd, grp->name); if (parent) { for (attr = grp->attrs; *attr; ++attr) kernfs_remove_by_name(parent, (*attr)->name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_unmerge_group); /** * sysfs_add_link_to_group - add a symlink to an attribute group. * @kobj: The kobject containing the group. * @group_name: The name of the group. * @target: The target kobject of the symlink to create. * @link_name: The name of the symlink to create. */ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name, struct kobject *target, const char *link_name) { struct kernfs_node *parent; int error = 0; parent = kernfs_find_and_get(kobj->sd, group_name); if (!parent) return -ENOENT; error = sysfs_create_link_sd(parent, target, link_name); kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_add_link_to_group); /** * sysfs_remove_link_from_group - remove a symlink from an attribute group. * @kobj: The kobject containing the group. * @group_name: The name of the group. * @link_name: The name of the symlink to remove. */ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, const char *link_name) { struct kernfs_node *parent; parent = kernfs_find_and_get(kobj->sd, group_name); if (parent) { kernfs_remove_by_name(parent, link_name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); /** * compat_only_sysfs_link_entry_to_kobj - add a symlink to a kobject pointing * to a group or an attribute * @kobj: The kobject containing the group. * @target_kobj: The target kobject. * @target_name: The name of the target group or attribute. * @symlink_name: The name of the symlink file (target_name will be * considered if symlink_name is NULL). */ int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, struct kobject *target_kobj, const char *target_name, const char *symlink_name) { struct kernfs_node *target; struct kernfs_node *entry; struct kernfs_node *link; /* * We don't own @target_kobj and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See sysfs_remove_dir() * for details. */ spin_lock(&sysfs_symlink_target_lock); target = target_kobj->sd; if (target) kernfs_get(target); spin_unlock(&sysfs_symlink_target_lock); if (!target) return -ENOENT; entry = kernfs_find_and_get(target_kobj->sd, target_name); if (!entry) { kernfs_put(target); return -ENOENT; } if (!symlink_name) symlink_name = target_name; link = kernfs_create_link(kobj->sd, symlink_name, entry); if (PTR_ERR(link) == -EEXIST) sysfs_warn_dup(kobj->sd, symlink_name); kernfs_put(entry); kernfs_put(target); return PTR_ERR_OR_ZERO(link); } EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj); static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, const struct attribute_group *grp, struct iattr *newattrs) { struct kernfs_node *kn; int error; if (grp->attrs) { struct attribute *const *attr; for (attr = grp->attrs; *attr; attr++) { kn = kernfs_find_and_get(grp_kn, (*attr)->name); if (!kn) return -ENOENT; error = kernfs_setattr(kn, newattrs); kernfs_put(kn); if (error) return error; } } if (grp->bin_attrs) { struct bin_attribute *const *bin_attr; for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); if (!kn) return -ENOENT; error = kernfs_setattr(kn, newattrs); kernfs_put(kn); if (error) return error; } } return 0; } /** * sysfs_group_change_owner - change owner of an attribute group. * @kobj: The kobject containing the group. * @grp: The attribute group. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Returns 0 on success or error code on failure. */ int sysfs_group_change_owner(struct kobject *kobj, const struct attribute_group *grp, kuid_t kuid, kgid_t kgid) { struct kernfs_node *grp_kn; int error; struct iattr newattrs = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = kuid, .ia_gid = kgid, }; if (!kobj->state_in_sysfs) return -EINVAL; if (grp->name) { grp_kn = kernfs_find_and_get(kobj->sd, grp->name); } else { kernfs_get(kobj->sd); grp_kn = kobj->sd; } if (!grp_kn) return -ENOENT; error = kernfs_setattr(grp_kn, &newattrs); if (!error) error = sysfs_group_attrs_change_owner(grp_kn, grp, &newattrs); kernfs_put(grp_kn); return error; } EXPORT_SYMBOL_GPL(sysfs_group_change_owner); /** * sysfs_groups_change_owner - change owner of a set of attribute groups. * @kobj: The kobject containing the groups. * @groups: The attribute groups. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Returns 0 on success or error code on failure. */ int sysfs_groups_change_owner(struct kobject *kobj, const struct attribute_group **groups, kuid_t kuid, kgid_t kgid) { int error = 0, i; if (!kobj->state_in_sysfs) return -EINVAL; if (!groups) return 0; for (i = 0; groups[i]; i++) { error = sysfs_group_change_owner(kobj, groups[i], kuid, kgid); if (error) break; } return error; } EXPORT_SYMBOL_GPL(sysfs_groups_change_owner); |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_INTERNAL_H #define _ASM_X86_FPU_INTERNAL_H #include <linux/compat.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <asm/user.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #include <asm/cpufeature.h> #include <asm/trace/fpu.h> /* * High level FPU state handling functions: */ extern void fpu__prepare_read(struct fpu *fpu); extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); extern void fpu__drop(struct fpu *fpu); extern int fpu__copy(struct task_struct *dst, struct task_struct *src); extern void fpu__clear_user_states(struct fpu *fpu); extern void fpu__clear_all(struct fpu *fpu); extern int fpu__exception_code(struct fpu *fpu, int trap_nr); /* * Boot time FPU initialization functions: */ extern void fpu__init_cpu(void); extern void fpu__init_system_xstate(void); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: */ #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ (void)(x); 0; }) #endif /* * FPU related CPU feature flag helper routines: */ static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { return static_cpu_has(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return static_cpu_has(X86_FEATURE_FXSR); } /* * fpstate handling functions: */ extern union fpregs_state init_fpstate; extern void fpstate_init(union fpregs_state *state); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif static inline void fpstate_init_xstate(struct xregs_state *xsave) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; } static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; fx->mxcsr = MXCSR_DEFAULT; } extern void fpstate_sanitize_xstate(struct fpu *fpu); /* Returns 0 or the negated trap number, which results in -EFAULT for #PF */ #define user_insn(insn, output, input...) \ ({ \ int err; \ \ might_fault(); \ \ asm volatile(ASM_STAC "\n" \ "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: negl %%eax\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn_err(insn, output, input...) \ ({ \ int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: movl $-1,%[err]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE(1b, 3b) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); } static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_kernel_to_fregs(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fregs_err(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_fxregs_to_kernel(struct fpu *fpu) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); } static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); } /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" /* * After this @err contains 0 on success or the negated trap number when * the operation raises an exception. For faults this results in -EFAULT. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n\t" \ ".pushsection .fixup,\"ax\"\n\t" \ "3: negl %%eax\n\t" \ "jmp 2b\n\t" \ ".popsection\n\t" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact * format and supervisor states in addition to modified optimization in * XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * We use XSAVE as a fallback. * * The 661 label is defined in the ALTERNATIVE* macros as the address of the * original instruction which gets replaced. We need to use it here as the * address of the instruction where we might get an exception at. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile(ALTERNATIVE_2(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ ".pushsection .fixup,\"ax\"\n" \ "4: movl $-2, %[err]\n" \ "jmp 3b\n" \ ".popsection\n" \ _ASM_EXTABLE(661b, 4b) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) { u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON(system_state != SYSTEM_BOOTING); if (boot_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * Save processor xstate to xsave area. */ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) { u64 mask = xfeatures_mask_all; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. */ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(xstate, lmask, hmask); } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for * backward compatibility for old applications which don't understand * compacted format of xsave area. */ static inline int copy_xregs_to_user(struct xregs_state __user *buf) { u64 mask = xfeatures_mask_user(); u32 lmask = mask; u32 hmask = mask >> 32; int err; /* * Clear the xsave header first, so that reserved fields are * initialized to zero. */ err = __clear_user(&buf->header, sizeof(buf->header)); if (unlikely(err)) return -EFAULT; stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); return err; } /* * Restore xstate from user space xsave area. */ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; int err; if (static_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } extern int copy_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); else copy_kernel_to_fregs(&fpstate->fsave); } } static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) { /* * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is * pending. Clear the x87 state here by setting it to fixed values. * "m" is a random variable that should be in L1. */ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" "fildl %P[addr]" /* set F?P to defined value */ : : [addr] "m" (fpstate)); } __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); /* * FPU context switch related helper methods: */ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Either one of these invalidation functions is enough. Invalidate * a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* * These generally need preemption protection to work, * do try to avoid using these on their own: */ static inline void fpregs_deactivate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* * Internal helper, do not use directly. Use switch_fpu_return() instead. */ static inline void __fpregs_load_activate(void) { struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return; if (!fpregs_state_valid(fpu, cpu)) { copy_kernel_to_fpregs(&fpu->state); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } /* * FPU state switching for scheduling. * * This is a two-stage process: * * - switch_fpu_prepare() saves the old state. * This is done within the context of the old process. * * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state * will get loaded on return to userspace, or when the kernel needs it. * * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers * are saved in the current thread's FPU register state. * * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not * hold current()'s FPU registers. It is required to load the * registers before returning to userland or using the content * otherwise. * * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ static inline void switch_fpu_prepare(struct task_struct *prev, int cpu) { struct fpu *old_fpu = &prev->thread.fpu; if (static_cpu_has(X86_FEATURE_FPU) && !(prev->flags & PF_KTHREAD)) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ trace_x86_fpu_regs_deactivated(old_fpu); } } /* * Misc helper functions: */ /* * Load PKRU from the FPU context if available. Delay loading of the * complete FPU state until the return to userland. */ static inline void switch_fpu_finish(struct task_struct *next) { u32 pkru_val = init_pkru_value; struct pkru_state *pk; struct fpu *next_fpu = &next->thread.fpu; if (!static_cpu_has(X86_FEATURE_FPU)) return; set_thread_flag(TIF_NEED_FPU_LOAD); if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * PKRU state is switched eagerly because it needs to be valid before we * return to userland e.g. for a copy_to_user() operation. */ if (!(next->flags & PF_KTHREAD)) { /* * If the PKRU bit in xsave.header.xfeatures is not set, * then the PKRU component was in init state, which means * XRSTOR will set PKRU to 0. If the bit is not set then * get_xsave_addr() will return NULL because the PKRU value * in memory is not valid. This means pkru_val has to be * set to 0 and not to init_pkru_value. */ pk = get_xsave_addr(&next_fpu->state.xsave, XFEATURE_PKRU); pkru_val = pk ? pk->pkru : 0; } __write_pkru(pkru_val); } #endif /* _ASM_X86_FPU_INTERNAL_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM workqueue #if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WORKQUEUE_H #include <linux/tracepoint.h> #include <linux/workqueue.h> struct pool_workqueue; /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu * @pwq: pointer to struct pool_workqueue * @work: pointer to struct work_struct * * This event occurs when a work is queued immediately or once a * delayed work is actually queued on a workqueue (ie: once the delay * has been reached). */ TRACE_EVENT(workqueue_queue_work, TP_PROTO(unsigned int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __field( void *, workqueue) __field( unsigned int, req_cpu ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __entry->workqueue = pwq->wq; __entry->req_cpu = req_cpu; __entry->cpu = pwq->pool->cpu; ), TP_printk("work struct=%p function=%ps workqueue=%p req_cpu=%u cpu=%u", __entry->work, __entry->function, __entry->workqueue, __entry->req_cpu, __entry->cpu) ); /** * workqueue_activate_work - called when a work gets activated * @work: pointer to struct work_struct * * This event occurs when a queued work is put on the active queue, * which happens immediately after queueing unless @max_active limit * is reached. */ TRACE_EVENT(workqueue_activate_work, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) ), TP_fast_assign( __entry->work = work; ), TP_printk("work struct %p", __entry->work) ); /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * workqueue_execute_end - called immediately after the workqueue callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_end, TP_PROTO(struct work_struct *work, work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); #endif /* _TRACE_WORKQUEUE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <linux/kcov.h> #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/sysfs.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/mmu_context.h> /* * The default value should be high enough to not crash a system that randomly * crashes its kernel from time to time, but low enough to at least not permit * overflowing 32-bit refcounts or the ldsem writer count. */ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL static struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, .maxlen = sizeof(oops_limit), .mode = 0644, .proc_handler = proc_douintvec, }, { } }; static __init int kernel_exit_sysctls_init(void) { register_sysctl_init("kernel", kern_exit_table); return 0; } late_initcall(kernel_exit_sysctls_init); #endif static atomic_t oops_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); } static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); static __init int kernel_exit_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); return 0; } late_initcall(kernel_exit_sysfs_init); #endif static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_TGID); detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk); #endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void put_task_struct_rcu_user(struct task_struct *task) { if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct); } void release_task(struct task_struct *p) { struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); atomic_dec(&__task_cred(p)->user->processes); rcu_read_unlock(); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); seccomp_filter_release(p); proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat; } int rcuwait_wake_up(struct rcuwait *w) { int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } #ifdef CONFIG_MEMCG /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(c, &p->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search in the siblings */ list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (atomic_read(&mm->mm_users) <= 1) break; if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); /* * Delay read_unlock() till we have the task_lock() * to ensure that c does not slip away underneath us */ read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); put_task_struct(c); goto retry; } WRITE_ONCE(mm->owner, c); task_unlock(c); put_task_struct(c); } #endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(void) { struct mm_struct *mm = current->mm; struct core_state *core_state; exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); /* * Serialize with any possible pending coredump. * We must hold mmap_lock around checking core_state * and clearing tsk->mm. The core-inducing thread * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ mmap_read_lock(mm); core_state = mm->core_state; if (core_state) { struct core_thread self; mmap_read_unlock(mm); self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } __set_current_state(TASK_RUNNING); mmap_read_lock(mm); } mmgrab(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); current->user_dumpable = (get_dumpable(mm) == SUID_DUMP_USER); current->mm = NULL; mmap_read_unlock(mm); enter_lazy_tlb(mm, current); task_unlock(current); mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) { struct task_struct *t; for_each_thread(p, t) { if (!(t->flags & PF_EXITING)) return t; } return NULL; } static struct task_struct *find_child_reaper(struct task_struct *father, struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; struct task_struct *p, *n; if (likely(reaper != father)) return reaper; reaper = find_alive_thread(father); if (reaper) { pid_ns->child_reaper = reaper; return reaper; } write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); return father; } /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father, struct task_struct *child_reaper) { struct task_struct *thread, *reaper; thread = find_alive_thread(father); if (thread) return thread; if (father->signal->has_child_subreaper) { unsigned int ns_level = task_pid(father)->level; /* * Find the first ->is_child_subreaper ancestor in our pid_ns. * We can't check reaper != child_reaper to ensure we do not * cross the namespaces, the exiting parent could be injected * by setns() + fork(). * We check pid->level, this is slightly more efficient than * task_active_pid_ns(reaper) != task_active_pid_ns(father). */ for (reaper = father->real_parent; task_pid(reaper)->level == ns_level; reaper = reaper->real_parent) { if (reaper == &init_task) break; if (!reaper->signal->is_child_subreaper) continue; thread = find_alive_thread(reaper); if (thread) return thread; } } return child_reaper; } /* * Any that need to be release_task'd are put on the @dead list. */ static void reparent_leader(struct task_struct *father, struct task_struct *p, struct list_head *dead) { if (unlikely(p->exit_state == EXIT_DEAD)) return; /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_add(&p->ptrace_entry, dead); } } kill_orphaned_pgrp(p, father); } /* * This does two things: * * A. Make init inherit all the child processes * B. Check to see if any process groups have become orphaned * as a result of our exiting, and if they have any stopped * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void forget_original_parent(struct task_struct *father, struct list_head *dead) { struct task_struct *p, *t, *reaper; if (unlikely(!list_empty(&father->ptraced))) exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { RCU_INIT_POINTER(t->real_parent, reaper); BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) group_send_sig_info(t->pdeath_signal, SEND_SIG_NOINFO, t, PIDTYPE_TGID); } /* * If this is a threaded reparent there is no need to * notify anyone anything has happened. */ if (!same_thread_group(reaper, father)) reparent_leader(father, p, dead); } list_splice_tail_init(&father->children, &reaper->children); } /* * Send signals to all our closest relatives so that they know * to properly mourn us.. */ static void exit_notify(struct task_struct *tsk, int group_dead) { bool autoreap; struct task_struct *p, *n; LIST_HEAD(dead); write_lock_irq(&tasklist_lock); forget_original_parent(tsk, &dead); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && !ptrace_reparented(tsk) ? tsk->exit_signal : SIGCHLD; autoreap = do_notify_parent(tsk, sig); } else if (thread_group_leader(tsk)) { autoreap = thread_group_empty(tsk) && do_notify_parent(tsk, tsk->exit_signal); } else { autoreap = true; } if (autoreap) { tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exit_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } } #ifdef CONFIG_DEBUG_STACK_USAGE static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; unsigned long free; free = stack_not_used(current); if (free >= lowest_to_date) return; spin_lock(&low_water_lock); if (free < lowest_to_date) { pr_info("%s (%d) used greatest stack depth: %lu bytes left\n", current->comm, task_pid_nr(current), free); lowest_to_date = free; } spin_unlock(&low_water_lock); } #else static inline void check_stack_usage(void) {} #endif void __noreturn do_exit(long code) { struct task_struct *tsk = current; int group_dead; /* * We can get here from a kernel oops, sometimes with preemption off. * Start by checking for critical errors. * Then fix up important state like USER_DS and preemption. * Then do everything else. */ WARN_ON(blk_needs_flush_plug(tsk)); if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); /* * If do_exit is called because this processes oopsed, it's possible * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before * continuing. Amongst other possible reasons, this is to prevent * mm_release()->clear_child_tid() from writing to a user-controlled * kernel address. */ force_uaccess_begin(); if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), preempt_count()); preempt_count_set(PREEMPT_ENABLED); } profile_task_exit(tsk); kcov_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); /* * We're taking recursive faults here in do_exit. Safest is to just * leave this task alone and wait for reboot. */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); futex_exit_recursive(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm); acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { /* * If the last thread of global init has exited, panic * immediately to get a useable coredump. */ if (unlikely(is_global_init(tsk))) panic("Attempted to kill init! exitcode=0x%08x\n", tsk->signal->group_exit_code ?: (int)code); #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); } acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); /* * Since sampling can touch ->mm, make sure to stop everything before we * tear it down. * * Also flushes inherited counters to the parent - before the parent * gets woken up by child-exit notifications. */ perf_event_exit_task(tsk); exit_mm(); if (group_dead) acct_process(); trace_sched_process_exit(tsk); exit_sem(tsk); exit_shm(tsk); exit_files(tsk); exit_fs(tsk); if (group_dead) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); exit_thread(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); exit_tasks_rcu_start(); exit_notify(tsk, group_dead); proc_exit_connector(tsk); mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); #endif /* * Make sure we are holding no locks: */ debug_check_no_locks_held(); if (tsk->io_context) exit_io_context(tsk); if (tsk->splice_pipe) free_pipe_info(tsk->splice_pipe); if (tsk->task_frag.page) put_page(tsk->task_frag.page); validate_creds_for_do_exit(tsk); check_stack_usage(); preempt_disable(); if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); exit_tasks_rcu_finish(); lockdep_free_task(tsk); do_task_dead(); } EXPORT_SYMBOL_GPL(do_exit); void __noreturn make_task_dead(int signr) { /* * Take the task off the cpu after something catastrophic has * happened. */ unsigned int limit; /* * Every time the system oopses, if the oops happens while a reference * to an object was held, the reference leaks. * If the oops doesn't also leak memory, repeated oopsing can cause * reference counters to wrap around (if they're not using refcount_t). * This means that repeated oopsing can make unexploitable-looking bugs * exploitable through repeated oopsing. * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ limit = READ_ONCE(oops_limit); if (atomic_inc_return(&oops_count) >= limit && limit) panic("Oopsed too often (kernel.oops_limit is %d)", limit); do_exit(signr); } void complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); do_exit(code); } EXPORT_SYMBOL(complete_and_exit); SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); } /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ void do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; BUG_ON(exit_code & 0x80); /* core dumps don't get here */ if (signal_group_exit(sig)) exit_code = sig->group_exit_code; else if (!thread_group_empty(current)) { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); if (signal_group_exit(sig)) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); } do_exit(exit_code); /* NOTREACHED */ } /* * this kills every thread in the thread group. Note that any externally * wait4()-ing process will get the correct exit code - even if this * thread is not the thread group leader. */ SYSCALL_DEFINE1(exit_group, int, error_code) { do_group_exit((error_code & 0xff) << 8); /* NOTREACHED */ return 0; } struct waitid_info { pid_t pid; uid_t uid; int status; int cause; }; struct wait_opts { enum pid_type wo_type; int wo_flags; struct pid *wo_pid; struct waitid_info *wo_info; int wo_stat; struct rusage *wo_rusage; wait_queue_entry_t child_wait; int notask_error; }; static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { return wo->wo_type == PIDTYPE_MAX || task_pid_type(p, wo->wo_type) == wo->wo_pid; } static int eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; /* * Wait for all children (clone and not) if __WALL is set or * if it is traced by us. */ if (ptrace || (wo->wo_flags & __WALL)) return 1; /* * Otherwise, wait for clone children *only* if __WCLONE is set; * otherwise, wait for non-clone children *only*. * * Note: a "clone" child here is one that reports to its parent * using a signal other than SIGCHLD, or a non-leader thread which * we can only see if it is traced by us. */ if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; } /* * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { int state, status; pid_t pid = task_pid_vnr(p); uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); struct waitid_info *infop; if (!likely(wo->wo_flags & WEXITED)) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { status = p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); goto out_info; } /* * Move the task's state to DEAD/TRACE, only one thread can do this. */ state = (ptrace_reparented(p) && thread_group_leader(p)) ? EXIT_TRACE : EXIT_DEAD; if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; /* * We own this thread, nobody else can reap it. */ read_unlock(&tasklist_lock); sched_annotate_sleep(); /* * Check thread_group_leader() to exclude the traced sub-threads. */ if (state == EXIT_DEAD && thread_group_leader(p)) { struct signal_struct *sig = p->signal; struct signal_struct *psig = current->signal; unsigned long maxrss; u64 tgutime, tgstime; /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group * are in its signal_struct, as are those for the child * processes it has previously reaped. All these * accumulate in the parent's signal_struct c* fields. * * We don't bother to take a lock here to protect these * p->signal fields because the whole thread group is dead * and nobody can change them. * * psig->stats_lock also protects us from our sub-theads * which can reap other children at the same time. Until * we change k_getrusage()-like users to rely on this lock * we have to take ->siglock as well. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); spin_lock_irq(¤t->sighand->siglock); write_seqlock(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += p->maj_flt + sig->maj_flt + sig->cmaj_flt; psig->cnvcsw += p->nvcsw + sig->nvcsw + sig->cnvcsw; psig->cnivcsw += p->nivcsw + sig->nivcsw + sig->cnivcsw; psig->cinblock += task_io_get_inblock(p) + sig->inblock + sig->cinblock; psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; maxrss = max(sig->maxrss, sig->cmaxrss); if (psig->cmaxrss < maxrss) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); write_sequnlock(&psig->stats_lock); spin_unlock_irq(¤t->sighand->siglock); } if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; wo->wo_stat = status; if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); /* If parent wants a zombie, don't release it now */ state = EXIT_ZOMBIE; if (do_notify_parent(p, p->exit_signal)) state = EXIT_DEAD; p->exit_state = state; write_unlock_irq(&tasklist_lock); } if (state == EXIT_DEAD) release_task(p); out_info: infop = wo->wo_info; if (infop) { if ((status & 0x7f) == 0) { infop->cause = CLD_EXITED; infop->status = status >> 8; } else { infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; infop->status = status & 0x7f; } infop->pid = pid; infop->uid = uid; } return pid; } static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) return &p->signal->group_exit_code; } return NULL; } /** * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED * @wo: wait options * @ptrace: is the wait for ptrace * @p: task to wait for * * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. * * CONTEXT: * read_lock(&tasklist_lock), which is released if return value is * non-zero. Also, grabs and releases @p->sighand->siglock. * * RETURNS: * 0 if wait condition didn't exist and search for other wait conditions * should continue. Non-zero return, -errno on failure and @p's pid on * success, implies that tasklist_lock is released and wait condition * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) { struct waitid_info *infop; int exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; if (!task_stopped_code(p, ptrace)) return 0; exit_code = 0; spin_lock_irq(&p->sighand->siglock); p_code = task_stopped_code(p, ptrace); if (unlikely(!p_code)) goto unlock_sig; exit_code = *p_code; if (!exit_code) goto unlock_sig; if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) return 0; /* * Now we are pretty sure this task is interesting. * Make sure it doesn't get reaped out from under us while we * give up the lock and then examine it below. We don't want to * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ get_task_struct(p); pid = task_pid_vnr(p); why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); if (likely(!(wo->wo_flags & WNOWAIT))) wo->wo_stat = (exit_code << 8) | 0x7f; infop = wo->wo_info; if (infop) { infop->cause = why; infop->status = exit_code; infop->pid = pid; infop->uid = uid; } return pid; } /* * Handle do_wait work for one task in a live, non-stopped state. * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { struct waitid_info *infop; pid_t pid; uid_t uid; if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; spin_lock_irq(&p->sighand->siglock); /* Re-check with the lock held. */ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { spin_unlock_irq(&p->sighand->siglock); return 0; } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); infop = wo->wo_info; if (!infop) { wo->wo_stat = 0xffff; } else { infop->cause = CLD_CONTINUED; infop->pid = pid; infop->uid = uid; infop->status = SIGCONT; } return pid; } /* * Consider @p for a wait by @parent. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; * then ->notask_error is 0 if @p is an eligible child, * or still -ECHILD. */ static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { /* * We can race with wait_task_zombie() from another thread. * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) return 0; ret = eligible_child(wo, ptrace, p); if (!ret) return ret; if (unlikely(exit_state == EXIT_TRACE)) { /* * ptrace == 0 means we are the natural parent. In this case * we should clear notask_error, debugger will notify us. */ if (likely(!ptrace)) wo->notask_error = 0; return 0; } if (likely(!ptrace) && unlikely(p->ptrace)) { /* * If it is traced by its real parent's group, just pretend * the caller is ptrace_do_wait() and reap this child if it * is zombie. * * This also hides group stop state from real parent; otherwise * a single stop can be reported twice as group and ptrace stop. * If a ptracer wants to distinguish these two events for its * own children it should create a separate process which takes * the role of real parent. */ if (!ptrace_reparented(p)) ptrace = 1; } /* slay zombie? */ if (exit_state == EXIT_ZOMBIE) { /* we don't reap group leaders with subthreads */ if (!delay_group_leader(p)) { /* * A zombie ptracee is only visible to its ptracer. * Notification and reaping will be cascaded to the * real parent when the ptracer detaches. */ if (unlikely(ptrace) || likely(!p->ptrace)) return wait_task_zombie(wo, p); } /* * Allow access to stopped/continued state via zombie by * falling through. Clearing of notask_error is complex. * * When !@ptrace: * * If WEXITED is set, notask_error should naturally be * cleared. If not, subset of WSTOPPED|WCONTINUED is set, * so, if there are live subthreads, there are events to * wait for. If all subthreads are dead, it's still safe * to clear - this function will be called again in finite * amount time once all the subthreads are released and * will then return without clearing. * * When @ptrace: * * Stopped state is per-task and thus can't change once the * target task dies. Only continued and exited can happen. * Clear notask_error if WCONTINUED | WEXITED. */ if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) wo->notask_error = 0; } else { /* * @p is alive and it's gonna stop, continue or exit, so * there always is something to wait for. */ wo->notask_error = 0; } /* * Wait for stopped. Depending on @ptrace, different stopped state * is used and the two don't interact with each other. */ ret = wait_task_stopped(wo, ptrace, p); if (ret) return ret; /* * Wait for continued. There's only one continued state and the * ptracer can consume it which can confuse the real parent. Don't * use WCONTINUED from ptracer. You don't need or want it. */ return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then * ->notask_error is 0 if there were any eligible children, * or still -ECHILD. */ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->children, sibling) { int ret = wait_consider_task(wo, 0, p); if (ret) return ret; } return 0; } static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { int ret = wait_consider_task(wo, 1, p); if (ret) return ret; } return 0; } static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct task_struct *p = key; if (!eligible_pid(wo, p)) return 0; if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent) return 0; return default_wake_function(wait, mode, sync, key); } void __wake_up_parent(struct task_struct *p, struct task_struct *parent) { __wake_up_sync_key(&parent->signal->wait_chldexit, TASK_INTERRUPTIBLE, p); } static long do_wait(struct wait_opts *wo) { struct task_struct *tsk; int retval; trace_sched_process_wait(wo->wo_pid); init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); wo->child_wait.private = current; add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); repeat: /* * If there is nothing that can match our criteria, just get out. * We will clear ->notask_error to zero if we see any child that * might later match our criteria, even if we are not able to reap * it yet. */ wo->notask_error = -ECHILD; if ((wo->wo_type < PIDTYPE_MAX) && (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type))) goto notask; set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); tsk = current; do { retval = do_wait_thread(wo, tsk); if (retval) goto end; retval = ptrace_do_wait(wo, tsk); if (retval) goto end; if (wo->wo_flags & __WNOTHREAD) break; } while_each_thread(current, tsk); read_unlock(&tasklist_lock); notask: retval = wo->notask_error; if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; if (!signal_pending(current)) { schedule(); goto repeat; } } end: __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; } static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; unsigned int f_flags = 0; if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; switch (which) { case P_ALL: type = PIDTYPE_MAX; break; case P_PID: type = PIDTYPE_PID; if (upid <= 0) return -EINVAL; pid = find_get_pid(upid); break; case P_PGID: type = PIDTYPE_PGID; if (upid < 0) return -EINVAL; if (upid) pid = find_get_pid(upid); else pid = get_task_pid(current, PIDTYPE_PGID); break; case P_PIDFD: type = PIDTYPE_PID; if (upid < 0) return -EINVAL; pid = pidfd_get_pid(upid, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); break; default: return -EINVAL; } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options; wo.wo_info = infop; wo.wo_rusage = ru; if (f_flags & O_NONBLOCK) wo.wo_flags |= WNOHANG; ret = do_wait(&wo); if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK)) ret = -EAGAIN; put_pid(pid); return ret; } SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { struct rusage r; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } long kernel_wait4(pid_t upid, int __user *stat_addr, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; /* -INT_MIN is not defined */ if (upid == INT_MIN) return -ESRCH; if (upid == -1) type = PIDTYPE_MAX; else if (upid < 0) { type = PIDTYPE_PGID; pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options | WEXITED; wo.wo_info = NULL; wo.wo_stat = 0; wo.wo_rusage = ru; ret = do_wait(&wo); put_pid(pid); if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr)) ret = -EFAULT; return ret; } int kernel_wait(pid_t pid, int *stat) { struct wait_opts wo = { .wo_type = PIDTYPE_PID, .wo_pid = find_get_pid(pid), .wo_flags = WEXITED, }; int ret; ret = do_wait(&wo); if (ret > 0 && wo.wo_stat) *stat = wo.wo_stat; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { struct rusage r; long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } return err; } #ifdef __ARCH_WANT_SYS_WAITPID /* * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) { return kernel_wait4(pid, stat_addr, options, NULL); } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(wait4, compat_pid_t, pid, compat_uint_t __user *, stat_addr, int, options, struct compat_rusage __user *, ru) { struct rusage r; long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && put_compat_rusage(&r, ru)) return -EFAULT; } return err; } COMPAT_SYSCALL_DEFINE5(waitid, int, which, compat_pid_t, pid, struct compat_siginfo __user *, infop, int, options, struct compat_rusage __user *, uru) { struct rusage ru; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (uru) { /* kernel_waitid() overwrites everything in ru */ if (COMPAT_USE_64BIT_TIME) err = copy_to_user(uru, &ru, sizeof(ru)); else err = put_compat_rusage(&ru, uru); if (err) return -EFAULT; } } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } #endif /** * thread_group_exited - check that a thread group has exited * @pid: tgid of thread group to be checked. * * Test if the thread group represented by tgid has exited (all * threads are zombies, dead or completely gone). * * Return: true if the thread group has exited. false otherwise. */ bool thread_group_exited(struct pid *pid) { struct task_struct *task; bool exited; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); exited = !task || (READ_ONCE(task->exit_state) && thread_group_empty(task)); rcu_read_unlock(); return exited; } EXPORT_SYMBOL(thread_group_exited); __weak void abort(void) { BUG(); /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } EXPORT_SYMBOL(abort); |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: fully on the stack (when can't do frame-checking) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { WARN_ONCE(1, "Bad or missing usercopy whitelist? Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); } void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } /* Checks for allocs that are marked in some way as spanning multiple pages. */ static inline void check_page_span(const void *ptr, unsigned long n, struct page *page, bool to_user) { #ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN const void *end = ptr + n - 1; struct page *endpage; bool is_reserved, is_cma; /* * Sometimes the kernel data regions are not marked Reserved (see * check below). And sometimes [_sdata,_edata) does not cover * rodata and/or bss, so check each range explicitly. */ /* Allow reads of kernel rodata region (if not marked as Reserved). */ if (ptr >= (const void *)__start_rodata && end <= (const void *)__end_rodata) { if (!to_user) usercopy_abort("rodata", NULL, to_user, 0, n); return; } /* Allow kernel data region (if not marked as Reserved). */ if (ptr >= (const void *)_sdata && end <= (const void *)_edata) return; /* Allow kernel bss region (if not marked as Reserved). */ if (ptr >= (const void *)__bss_start && end <= (const void *)__bss_stop) return; /* Is the object wholly within one base page? */ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == ((unsigned long)end & (unsigned long)PAGE_MASK))) return; /* Allow if fully inside the same compound (__GFP_COMP) page. */ endpage = virt_to_head_page(end); if (likely(endpage == page)) return; /* * Reject if range is entirely either Reserved (i.e. special or * device memory), or CMA. Otherwise, reject since the object spans * several independently allocated pages. */ is_reserved = PageReserved(page); is_cma = is_migrate_cma_page(page); if (!is_reserved && !is_cma) usercopy_abort("spans multiple pages", NULL, to_user, 0, n); for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { page = virt_to_head_page(ptr); if (is_reserved && !PageReserved(page)) usercopy_abort("spans Reserved and non-Reserved pages", NULL, to_user, 0, n); if (is_cma && !is_migrate_cma_page(page)) usercopy_abort("spans CMA and non-CMA pages", NULL, to_user, 0, n); } #endif } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { struct page *page; if (!virt_addr_valid(ptr)) return; /* * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the * highmem page or fallback to virt_to_page(). The following * is effectively a highmem-aware virt_to_head_page(). */ page = compound_head(kmap_to_page((void *)ptr)); if (PageSlab(page)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, page, to_user); } else { /* Verify object does not incorrectly span multiple pages. */ check_page_span(ptr, n, page, to_user); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, 0, n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { if (strtobool(str, &enable_checks)) pr_warn("Invalid option string for hardened_usercopy: '%s'\n", str); return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_H #define _LINUX_SCHED_TASK_H /* * Interface between the scheduler and various task lifetime (fork()/exit()) * functionality: */ #include <linux/sched.h> #include <linux/uaccess.h> struct task_struct; struct rusage; union thread_union; struct css_set; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL struct kernel_clone_args { u64 flags; int __user *pidfd; int __user *child_tid; int __user *parent_tid; int exit_signal; unsigned long stack; unsigned long stack_size; unsigned long tls; pid_t *set_tid; /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; int io_thread; struct cgroup *cgrp; struct css_set *cset; }; /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; extern union thread_union init_thread_union; extern struct task_struct init_task; #ifdef CONFIG_PROVE_RCU extern int lockdep_tasklist_lock_is_held(void); #endif /* #ifdef CONFIG_PROVE_RCU */ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); extern void release_task(struct task_struct * p); extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *, unsigned long); extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(struct task_struct *tsk); #else static inline void exit_thread(struct task_struct *tsk) { } #endif extern void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP extern void sched_exec(void); #else #define sched_exec() {} #endif static inline struct task_struct *get_task_struct(struct task_struct *t) { refcount_inc(&t->usage); return t; } extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); static inline void put_task_struct(struct task_struct *t) { if (!refcount_dec_and_test(&t->usage)) return; /* * under PREEMPT_RT, we can't call put_task_struct * in atomic context because it will indirectly * acquire sleeping locks. * * call_rcu() will schedule delayed_put_task_struct_rcu() * to be called in process context. * * __put_task_struct() is called when * refcount_dec_and_test(&t->usage) succeeds. * * This means that it can't "conflict" with * put_task_struct_rcu_user() which abuses ->rcu the same * way; rcu_users has a reference so task->usage can't be * zero after rcu_users 1 -> 0 transition. * * delayed_free_task() also uses ->rcu, but it is only called * when it fails to fork a process. Therefore, there is no * way it can conflict with put_task_struct(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) call_rcu(&t->rcu, __put_task_struct_rcu_cb); else __put_task_struct(t); } DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T)) static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) __put_task_struct(t); } void put_task_struct_rcu_user(struct task_struct *task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else # define arch_task_struct_size (sizeof(struct task_struct)) #endif #ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST /* * If an architecture has not declared a thread_struct whitelist we * must assume something there may need to be copied to userspace. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = 0; /* Handle dynamically sized thread_struct. */ *size = arch_task_struct_size - offsetof(struct task_struct, thread); } #endif #ifdef CONFIG_VMAP_STACK static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return t->stack_vm_area; } #else static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return NULL; } #endif /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), * neither inside nor outside. */ static inline void task_lock(struct task_struct *p) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) { spin_unlock(&p->alloc_lock); } #endif /* _LINUX_SCHED_TASK_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.h - generic kernel object infrastructure. * * Copyright (c) 2002-2003 Patrick Mochel * Copyright (c) 2002-2003 Open Source Development Labs * Copyright (c) 2006-2008 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2008 Novell Inc. * * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ #ifndef _KOBJECT_H_ #define _KOBJECT_H_ #include <linux/types.h> #include <linux/list.h> #include <linux/sysfs.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> #include <linux/uidgid.h> #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 64 /* number of env pointers */ #define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */ #ifdef CONFIG_UEVENT_HELPER /* path to the userspace helper executed on an event */ extern char uevent_helper[]; #endif /* counter to tag the uevent, read only except for the kobject core */ extern u64 uevent_seqnum; /* * The actions here must match the index to the string array * in lib/kobject_uevent.c * * Do not add new actions here without checking with the driver-core * maintainers. Action strings are not meant to express subsystem * or device specific properties. In most cases you want to send a * kobject_uevent_env(kobj, KOBJ_CHANGE, env) with additional event * specific variables added to the event environment. */ enum kobject_action { KOBJ_ADD, KOBJ_REMOVE, KOBJ_CHANGE, KOBJ_MOVE, KOBJ_ONLINE, KOBJ_OFFLINE, KOBJ_BIND, KOBJ_UNBIND, }; struct kobject { const char *name; struct list_head entry; struct kobject *parent; struct kset *kset; struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; #endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; unsigned int uevent_suppress:1; }; extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); extern __printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); extern struct kobject *kobject_get(struct kobject *kobj); extern struct kobject * __must_check kobject_get_unless_zero( struct kobject *kobj); extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); /** * kobject_has_children - Returns whether a kobject has children. * @kobj: the object to test * * This will return whether a kobject has other kobjects as children. * * It does NOT account for the presence of attribute files, only sub * directories. It also assumes there is no concurrent addition or * removal of such children, and thus relies on external locking. */ static inline bool kobject_has_children(struct kobject *kobj) { WARN_ON_ONCE(kref_read(&kobj->kref) == 0); return kobj->sd && kobj->sd->dir.subdirs; } struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid); }; struct kobj_uevent_env { char *argv[3]; char *envp[UEVENT_NUM_ENVP]; int envp_idx; char buf[UEVENT_BUFFER_SIZE]; int buflen; }; struct kset_uevent_ops { int (* const filter)(struct kset *kset, struct kobject *kobj); const char *(* const name)(struct kset *kset, struct kobject *kobj); int (* const uevent)(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, char *buf); ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count); }; extern const struct sysfs_ops kobj_sysfs_ops; struct sock; /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * * A kset defines a group of kobjects. They can be individually * different "types" but overall these kobjects all want to be grouped * together and operated on in the same manner. ksets are used to * define the attribute callbacks and other common events that happen to * a kobject. * * @list: the list of all kobjects for this kset * @list_lock: a lock for iterating over the kobjects * @kobj: the embedded kobject for this kset (recursion, isn't it fun...) * @uevent_ops: the set of uevent operations for this kset. These are * called whenever a kobject has something happen to it so that the kset * can add new environment variables, or filter out the uevents if so * desired. */ struct kset { struct list_head list; spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; } __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); extern void kset_unregister(struct kset *kset); extern struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { return kobj ? container_of(kobj, struct kset, kobj) : NULL; } static inline struct kset *kset_get(struct kset *k) { return k ? to_kset(kobject_get(&k->kobj)) : NULL; } static inline void kset_put(struct kset *k) { kobject_put(&k->kobj); } static inline struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } extern struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; /* The global /sys/kernel/mm/ kobject for people to chain off of */ extern struct kobject *mm_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kobject for people to chain off of */ extern struct kobject *power_kobj; /* The global /sys/firmware/ kobject for people to chain off of */ extern struct kobject *firmware_kobj; int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count); __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); #endif /* _KOBJECT_H_ */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <linux/string_helpers.h> #include "kstrtox.h" static unsigned long long simple_strntoull(const char *startp, size_t max_chars, char **endp, unsigned int base) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, unsigned int base) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, max_chars - 1, endp, base); return simple_strntoull(cp, max_chars, endp, base); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ' '); enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Needs to run from preemptible context */ static_branch_disable(¬_filled_random_ptr_key); } static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); static int fill_random_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { /* This may be in an interrupt handler. */ queue_work(system_unbound_wq, &enable_ptr_key_work); return 0; } static struct notifier_block random_ready = { .notifier_call = fill_random_ptr_key }; static int __init initialize_ptr_random(void) { int key_size = sizeof(ptr_key); int ret; /* Use hw RNG if available. */ if (get_random_bytes_arch(&ptr_key, key_size) == key_size) { static_branch_disable(¬_filled_random_ptr_key); return 0; } ret = register_random_ready_notifier(&random_ready); if (!ret) { return 0; } else if (ret == -EALREADY) { /* This is in preemptible context */ enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } return ret; } early_initcall(initialize_ptr_random); /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (static_branch_unlikely(¬_filled_random_ptr_key)) return -EAGAIN; #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return ptr_to_id(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_irq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev->bd_partno) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev->bd_partno, spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = number(p, pend, res->start, *specp); if (res->start != res->end) { *p++ = '-'; p = number(p, pend, res->end, *specp); } } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); /* current bit is 'cur', most recently seen range is [rbot, rtop] */ int cur, rbot, rtop; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; rbot = cur = find_first_bit(bitmap, nr_bits); while (cur < nr_bits) { rtop = cur; cur = find_next_bit(bitmap, nr_bits, cur + 1); if (cur < nr_bits && cur <= rtop + 1) continue; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rbot < rtop) { if (buf < end) *buf = '-'; buf++; buf = number(buf, end, rtop, default_dec_spec); } rbot = cur; } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; /* fall through */ default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; /* fall through */ case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false; int count = 2; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } raw = fmt[count] == 'r'; if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { /* Respect ISO 8601 */ if (buf < end) *buf = 'T'; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': flags = *(unsigned long *)flags_ptr; /* Remove zone id */ flags &= (1UL << NR_PAGEFLAGS) - 1; names = pageflag_names; break; case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users * - 'NF' For a netdev_features_t * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address. Equivalent to "%lx". * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); /* fall through */ case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_string(buf, end, ptr, spec, fmt); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) break; return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } } /* default is to _not_ leak addresses, hash before printing */ return ptr_to_id(buf, end, ptr, spec); } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; /* fall through */ case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ /* fall through */ default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; if (size != 0) return size - 1; return 0; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); /** * bprintf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of words(u32) written * into @bin_buf. */ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = vbin_printf(bin_buf, size, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL_GPL(bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matchs any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; /* fall through */ case 'd': is_sign = true; /* fall through */ case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') digit = *(str + 1); if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && (!isdigit(digit) || digit > '7')) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, field_width >= 0 ? field_width : INT_MAX, &next, base); else val.u = simple_strntoull(str, field_width >= 0 ? field_width : INT_MAX, &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { u32 val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { u32 val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-fallback.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H #include <linux/compiler.h> #ifndef arch_xchg_relaxed #define arch_xchg_relaxed arch_xchg #define arch_xchg_acquire arch_xchg #define arch_xchg_release arch_xchg #else /* arch_xchg_relaxed */ #ifndef arch_xchg_acquire #define arch_xchg_acquire(...) \ __atomic_op_acquire(arch_xchg, __VA_ARGS__) #endif #ifndef arch_xchg_release #define arch_xchg_release(...) \ __atomic_op_release(arch_xchg, __VA_ARGS__) #endif #ifndef arch_xchg #define arch_xchg(...) \ __atomic_op_fence(arch_xchg, __VA_ARGS__) #endif #endif /* arch_xchg_relaxed */ #ifndef arch_cmpxchg_relaxed #define arch_cmpxchg_relaxed arch_cmpxchg #define arch_cmpxchg_acquire arch_cmpxchg #define arch_cmpxchg_release arch_cmpxchg #else /* arch_cmpxchg_relaxed */ #ifndef arch_cmpxchg_acquire #define arch_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) #endif #ifndef arch_cmpxchg_release #define arch_cmpxchg_release(...) \ __atomic_op_release(arch_cmpxchg, __VA_ARGS__) #endif #ifndef arch_cmpxchg #define arch_cmpxchg(...) \ __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) #endif #endif /* arch_cmpxchg_relaxed */ #ifndef arch_cmpxchg64_relaxed #define arch_cmpxchg64_relaxed arch_cmpxchg64 #define arch_cmpxchg64_acquire arch_cmpxchg64 #define arch_cmpxchg64_release arch_cmpxchg64 #else /* arch_cmpxchg64_relaxed */ #ifndef arch_cmpxchg64_acquire #define arch_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) #endif #ifndef arch_cmpxchg64_release #define arch_cmpxchg64_release(...) \ __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) #endif #ifndef arch_cmpxchg64 #define arch_cmpxchg64(...) \ __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) #endif #endif /* arch_cmpxchg64_relaxed */ #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) { return smp_load_acquire(&(v)->counter); } #define arch_atomic_read_acquire arch_atomic_read_acquire #endif #ifndef arch_atomic_set_release static __always_inline void arch_atomic_set_release(atomic_t *v, int i) { smp_store_release(&(v)->counter, i); } #define arch_atomic_set_release arch_atomic_set_release #endif #ifndef arch_atomic_add_return_relaxed #define arch_atomic_add_return_acquire arch_atomic_add_return #define arch_atomic_add_return_release arch_atomic_add_return #define arch_atomic_add_return_relaxed arch_atomic_add_return #else /* arch_atomic_add_return_relaxed */ #ifndef arch_atomic_add_return_acquire static __always_inline int arch_atomic_add_return_acquire(int i, atomic_t *v) { int ret = arch_atomic_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_add_return_acquire arch_atomic_add_return_acquire #endif #ifndef arch_atomic_add_return_release static __always_inline int arch_atomic_add_return_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_add_return_relaxed(i, v); } #define arch_atomic_add_return_release arch_atomic_add_return_release #endif #ifndef arch_atomic_add_return static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_add_return arch_atomic_add_return #endif #endif /* arch_atomic_add_return_relaxed */ #ifndef arch_atomic_fetch_add_relaxed #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add #define arch_atomic_fetch_add_release arch_atomic_fetch_add #define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add #else /* arch_atomic_fetch_add_relaxed */ #ifndef arch_atomic_fetch_add_acquire static __always_inline int arch_atomic_fetch_add_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire #endif #ifndef arch_atomic_fetch_add_release static __always_inline int arch_atomic_fetch_add_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_add_relaxed(i, v); } #define arch_atomic_fetch_add_release arch_atomic_fetch_add_release #endif #ifndef arch_atomic_fetch_add static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_add arch_atomic_fetch_add #endif #endif /* arch_atomic_fetch_add_relaxed */ #ifndef arch_atomic_sub_return_relaxed #define arch_atomic_sub_return_acquire arch_atomic_sub_return #define arch_atomic_sub_return_release arch_atomic_sub_return #define arch_atomic_sub_return_relaxed arch_atomic_sub_return #else /* arch_atomic_sub_return_relaxed */ #ifndef arch_atomic_sub_return_acquire static __always_inline int arch_atomic_sub_return_acquire(int i, atomic_t *v) { int ret = arch_atomic_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire #endif #ifndef arch_atomic_sub_return_release static __always_inline int arch_atomic_sub_return_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_sub_return_relaxed(i, v); } #define arch_atomic_sub_return_release arch_atomic_sub_return_release #endif #ifndef arch_atomic_sub_return static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_sub_return arch_atomic_sub_return #endif #endif /* arch_atomic_sub_return_relaxed */ #ifndef arch_atomic_fetch_sub_relaxed #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub #define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub #else /* arch_atomic_fetch_sub_relaxed */ #ifndef arch_atomic_fetch_sub_acquire static __always_inline int arch_atomic_fetch_sub_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire #endif #ifndef arch_atomic_fetch_sub_release static __always_inline int arch_atomic_fetch_sub_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_sub_relaxed(i, v); } #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release #endif #ifndef arch_atomic_fetch_sub static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_sub arch_atomic_fetch_sub #endif #endif /* arch_atomic_fetch_sub_relaxed */ #ifndef arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { arch_atomic_add(1, v); } #define arch_atomic_inc arch_atomic_inc #endif #ifndef arch_atomic_inc_return_relaxed #ifdef arch_atomic_inc_return #define arch_atomic_inc_return_acquire arch_atomic_inc_return #define arch_atomic_inc_return_release arch_atomic_inc_return #define arch_atomic_inc_return_relaxed arch_atomic_inc_return #endif /* arch_atomic_inc_return */ #ifndef arch_atomic_inc_return static __always_inline int arch_atomic_inc_return(atomic_t *v) { return arch_atomic_add_return(1, v); } #define arch_atomic_inc_return arch_atomic_inc_return #endif #ifndef arch_atomic_inc_return_acquire static __always_inline int arch_atomic_inc_return_acquire(atomic_t *v) { return arch_atomic_add_return_acquire(1, v); } #define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire #endif #ifndef arch_atomic_inc_return_release static __always_inline int arch_atomic_inc_return_release(atomic_t *v) { return arch_atomic_add_return_release(1, v); } #define arch_atomic_inc_return_release arch_atomic_inc_return_release #endif #ifndef arch_atomic_inc_return_relaxed static __always_inline int arch_atomic_inc_return_relaxed(atomic_t *v) { return arch_atomic_add_return_relaxed(1, v); } #define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed #endif #else /* arch_atomic_inc_return_relaxed */ #ifndef arch_atomic_inc_return_acquire static __always_inline int arch_atomic_inc_return_acquire(atomic_t *v) { int ret = arch_atomic_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire #endif #ifndef arch_atomic_inc_return_release static __always_inline int arch_atomic_inc_return_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_inc_return_relaxed(v); } #define arch_atomic_inc_return_release arch_atomic_inc_return_release #endif #ifndef arch_atomic_inc_return static __always_inline int arch_atomic_inc_return(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_inc_return arch_atomic_inc_return #endif #endif /* arch_atomic_inc_return_relaxed */ #ifndef arch_atomic_fetch_inc_relaxed #ifdef arch_atomic_fetch_inc #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc #define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc #endif /* arch_atomic_fetch_inc */ #ifndef arch_atomic_fetch_inc static __always_inline int arch_atomic_fetch_inc(atomic_t *v) { return arch_atomic_fetch_add(1, v); } #define arch_atomic_fetch_inc arch_atomic_fetch_inc #endif #ifndef arch_atomic_fetch_inc_acquire static __always_inline int arch_atomic_fetch_inc_acquire(atomic_t *v) { return arch_atomic_fetch_add_acquire(1, v); } #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire #endif #ifndef arch_atomic_fetch_inc_release static __always_inline int arch_atomic_fetch_inc_release(atomic_t *v) { return arch_atomic_fetch_add_release(1, v); } #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release #endif #ifndef arch_atomic_fetch_inc_relaxed static __always_inline int arch_atomic_fetch_inc_relaxed(atomic_t *v) { return arch_atomic_fetch_add_relaxed(1, v); } #define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed #endif #else /* arch_atomic_fetch_inc_relaxed */ #ifndef arch_atomic_fetch_inc_acquire static __always_inline int arch_atomic_fetch_inc_acquire(atomic_t *v) { int ret = arch_atomic_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire #endif #ifndef arch_atomic_fetch_inc_release static __always_inline int arch_atomic_fetch_inc_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_inc_relaxed(v); } #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release #endif #ifndef arch_atomic_fetch_inc static __always_inline int arch_atomic_fetch_inc(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_inc arch_atomic_fetch_inc #endif #endif /* arch_atomic_fetch_inc_relaxed */ #ifndef arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { arch_atomic_sub(1, v); } #define arch_atomic_dec arch_atomic_dec #endif #ifndef arch_atomic_dec_return_relaxed #ifdef arch_atomic_dec_return #define arch_atomic_dec_return_acquire arch_atomic_dec_return #define arch_atomic_dec_return_release arch_atomic_dec_return #define arch_atomic_dec_return_relaxed arch_atomic_dec_return #endif /* arch_atomic_dec_return */ #ifndef arch_atomic_dec_return static __always_inline int arch_atomic_dec_return(atomic_t *v) { return arch_atomic_sub_return(1, v); } #define arch_atomic_dec_return arch_atomic_dec_return #endif #ifndef arch_atomic_dec_return_acquire static __always_inline int arch_atomic_dec_return_acquire(atomic_t *v) { return arch_atomic_sub_return_acquire(1, v); } #define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire #endif #ifndef arch_atomic_dec_return_release static __always_inline int arch_atomic_dec_return_release(atomic_t *v) { return arch_atomic_sub_return_release(1, v); } #define arch_atomic_dec_return_release arch_atomic_dec_return_release #endif #ifndef arch_atomic_dec_return_relaxed static __always_inline int arch_atomic_dec_return_relaxed(atomic_t *v) { return arch_atomic_sub_return_relaxed(1, v); } #define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed #endif #else /* arch_atomic_dec_return_relaxed */ #ifndef arch_atomic_dec_return_acquire static __always_inline int arch_atomic_dec_return_acquire(atomic_t *v) { int ret = arch_atomic_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire #endif #ifndef arch_atomic_dec_return_release static __always_inline int arch_atomic_dec_return_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_dec_return_relaxed(v); } #define arch_atomic_dec_return_release arch_atomic_dec_return_release #endif #ifndef arch_atomic_dec_return static __always_inline int arch_atomic_dec_return(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_dec_return arch_atomic_dec_return #endif #endif /* arch_atomic_dec_return_relaxed */ #ifndef arch_atomic_fetch_dec_relaxed #ifdef arch_atomic_fetch_dec #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec #define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec #endif /* arch_atomic_fetch_dec */ #ifndef arch_atomic_fetch_dec static __always_inline int arch_atomic_fetch_dec(atomic_t *v) { return arch_atomic_fetch_sub(1, v); } #define arch_atomic_fetch_dec arch_atomic_fetch_dec #endif #ifndef arch_atomic_fetch_dec_acquire static __always_inline int arch_atomic_fetch_dec_acquire(atomic_t *v) { return arch_atomic_fetch_sub_acquire(1, v); } #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire #endif #ifndef arch_atomic_fetch_dec_release static __always_inline int arch_atomic_fetch_dec_release(atomic_t *v) { return arch_atomic_fetch_sub_release(1, v); } #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release #endif #ifndef arch_atomic_fetch_dec_relaxed static __always_inline int arch_atomic_fetch_dec_relaxed(atomic_t *v) { return arch_atomic_fetch_sub_relaxed(1, v); } #define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed #endif #else /* arch_atomic_fetch_dec_relaxed */ #ifndef arch_atomic_fetch_dec_acquire static __always_inline int arch_atomic_fetch_dec_acquire(atomic_t *v) { int ret = arch_atomic_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire #endif #ifndef arch_atomic_fetch_dec_release static __always_inline int arch_atomic_fetch_dec_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_dec_relaxed(v); } #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release #endif #ifndef arch_atomic_fetch_dec static __always_inline int arch_atomic_fetch_dec(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_dec arch_atomic_fetch_dec #endif #endif /* arch_atomic_fetch_dec_relaxed */ #ifndef arch_atomic_fetch_and_relaxed #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and #define arch_atomic_fetch_and_release arch_atomic_fetch_and #define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and #else /* arch_atomic_fetch_and_relaxed */ #ifndef arch_atomic_fetch_and_acquire static __always_inline int arch_atomic_fetch_and_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire #endif #ifndef arch_atomic_fetch_and_release static __always_inline int arch_atomic_fetch_and_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_and_relaxed(i, v); } #define arch_atomic_fetch_and_release arch_atomic_fetch_and_release #endif #ifndef arch_atomic_fetch_and static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_and arch_atomic_fetch_and #endif #endif /* arch_atomic_fetch_and_relaxed */ #ifndef arch_atomic_andnot static __always_inline void arch_atomic_andnot(int i, atomic_t *v) { arch_atomic_and(~i, v); } #define arch_atomic_andnot arch_atomic_andnot #endif #ifndef arch_atomic_fetch_andnot_relaxed #ifdef arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot #endif /* arch_atomic_fetch_andnot */ #ifndef arch_atomic_fetch_andnot static __always_inline int arch_atomic_fetch_andnot(int i, atomic_t *v) { return arch_atomic_fetch_and(~i, v); } #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #endif #ifndef arch_atomic_fetch_andnot_acquire static __always_inline int arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) { return arch_atomic_fetch_and_acquire(~i, v); } #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #endif #ifndef arch_atomic_fetch_andnot_release static __always_inline int arch_atomic_fetch_andnot_release(int i, atomic_t *v) { return arch_atomic_fetch_and_release(~i, v); } #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #endif #ifndef arch_atomic_fetch_andnot_relaxed static __always_inline int arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) { return arch_atomic_fetch_and_relaxed(~i, v); } #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed #endif #else /* arch_atomic_fetch_andnot_relaxed */ #ifndef arch_atomic_fetch_andnot_acquire static __always_inline int arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #endif #ifndef arch_atomic_fetch_andnot_release static __always_inline int arch_atomic_fetch_andnot_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_andnot_relaxed(i, v); } #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #endif #ifndef arch_atomic_fetch_andnot static __always_inline int arch_atomic_fetch_andnot(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #endif #endif /* arch_atomic_fetch_andnot_relaxed */ #ifndef arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or #define arch_atomic_fetch_or_release arch_atomic_fetch_or #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or #else /* arch_atomic_fetch_or_relaxed */ #ifndef arch_atomic_fetch_or_acquire static __always_inline int arch_atomic_fetch_or_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire #endif #ifndef arch_atomic_fetch_or_release static __always_inline int arch_atomic_fetch_or_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_or_relaxed(i, v); } #define arch_atomic_fetch_or_release arch_atomic_fetch_or_release #endif #ifndef arch_atomic_fetch_or static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_or arch_atomic_fetch_or #endif #endif /* arch_atomic_fetch_or_relaxed */ #ifndef arch_atomic_fetch_xor_relaxed #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor #else /* arch_atomic_fetch_xor_relaxed */ #ifndef arch_atomic_fetch_xor_acquire static __always_inline int arch_atomic_fetch_xor_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire #endif #ifndef arch_atomic_fetch_xor_release static __always_inline int arch_atomic_fetch_xor_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_xor_relaxed(i, v); } #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release #endif #ifndef arch_atomic_fetch_xor static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #endif #endif /* arch_atomic_fetch_xor_relaxed */ #ifndef arch_atomic_xchg_relaxed #define arch_atomic_xchg_acquire arch_atomic_xchg #define arch_atomic_xchg_release arch_atomic_xchg #define arch_atomic_xchg_relaxed arch_atomic_xchg #else /* arch_atomic_xchg_relaxed */ #ifndef arch_atomic_xchg_acquire static __always_inline int arch_atomic_xchg_acquire(atomic_t *v, int i) { int ret = arch_atomic_xchg_relaxed(v, i); __atomic_acquire_fence(); return ret; } #define arch_atomic_xchg_acquire arch_atomic_xchg_acquire #endif #ifndef arch_atomic_xchg_release static __always_inline int arch_atomic_xchg_release(atomic_t *v, int i) { __atomic_release_fence(); return arch_atomic_xchg_relaxed(v, i); } #define arch_atomic_xchg_release arch_atomic_xchg_release #endif #ifndef arch_atomic_xchg static __always_inline int arch_atomic_xchg(atomic_t *v, int i) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_xchg_relaxed(v, i); __atomic_post_full_fence(); return ret; } #define arch_atomic_xchg arch_atomic_xchg #endif #endif /* arch_atomic_xchg_relaxed */ #ifndef arch_atomic_cmpxchg_relaxed #define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg #define arch_atomic_cmpxchg_release arch_atomic_cmpxchg #define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg #else /* arch_atomic_cmpxchg_relaxed */ #ifndef arch_atomic_cmpxchg_acquire static __always_inline int arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { int ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire #endif #ifndef arch_atomic_cmpxchg_release static __always_inline int arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) { __atomic_release_fence(); return arch_atomic_cmpxchg_relaxed(v, old, new); } #define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release #endif #ifndef arch_atomic_cmpxchg static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic_cmpxchg arch_atomic_cmpxchg #endif #endif /* arch_atomic_cmpxchg_relaxed */ #ifndef arch_atomic_try_cmpxchg_relaxed #ifdef arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg #endif /* arch_atomic_try_cmpxchg */ #ifndef arch_atomic_try_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg #endif #ifndef arch_atomic_try_cmpxchg_acquire static __always_inline bool arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire #endif #ifndef arch_atomic_try_cmpxchg_release static __always_inline bool arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release #endif #ifndef arch_atomic_try_cmpxchg_relaxed static __always_inline bool arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed #endif #else /* arch_atomic_try_cmpxchg_relaxed */ #ifndef arch_atomic_try_cmpxchg_acquire static __always_inline bool arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire #endif #ifndef arch_atomic_try_cmpxchg_release static __always_inline bool arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { __atomic_release_fence(); return arch_atomic_try_cmpxchg_relaxed(v, old, new); } #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release #endif #ifndef arch_atomic_try_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { bool ret; __atomic_pre_full_fence(); ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg #endif #endif /* arch_atomic_try_cmpxchg_relaxed */ #ifndef arch_atomic_sub_and_test /** * arch_atomic_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return arch_atomic_sub_return(i, v) == 0; } #define arch_atomic_sub_and_test arch_atomic_sub_and_test #endif #ifndef arch_atomic_dec_and_test /** * arch_atomic_dec_and_test - decrement and test * @v: pointer of type atomic_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return arch_atomic_dec_return(v) == 0; } #define arch_atomic_dec_and_test arch_atomic_dec_and_test #endif #ifndef arch_atomic_inc_and_test /** * arch_atomic_inc_and_test - increment and test * @v: pointer of type atomic_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return arch_atomic_inc_return(v) == 0; } #define arch_atomic_inc_and_test arch_atomic_inc_and_test #endif #ifndef arch_atomic_add_negative /** * arch_atomic_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return arch_atomic_add_return(i, v) < 0; } #define arch_atomic_add_negative arch_atomic_add_negative #endif #ifndef arch_atomic_fetch_add_unless /** * arch_atomic_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = arch_atomic_read(v); do { if (unlikely(c == u)) break; } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); return c; } #define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless #endif #ifndef arch_atomic_add_unless /** * arch_atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ static __always_inline bool arch_atomic_add_unless(atomic_t *v, int a, int u) { return arch_atomic_fetch_add_unless(v, a, u) != u; } #define arch_atomic_add_unless arch_atomic_add_unless #endif #ifndef arch_atomic_inc_not_zero /** * arch_atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ static __always_inline bool arch_atomic_inc_not_zero(atomic_t *v) { return arch_atomic_add_unless(v, 1, 0); } #define arch_atomic_inc_not_zero arch_atomic_inc_not_zero #endif #ifndef arch_atomic_inc_unless_negative static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v) { int c = arch_atomic_read(v); do { if (unlikely(c < 0)) return false; } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); return true; } #define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative #endif #ifndef arch_atomic_dec_unless_positive static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v) { int c = arch_atomic_read(v); do { if (unlikely(c > 0)) return false; } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); return true; } #define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive #endif #ifndef arch_atomic_dec_if_positive static __always_inline int arch_atomic_dec_if_positive(atomic_t *v) { int dec, c = arch_atomic_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!arch_atomic_try_cmpxchg(v, &c, dec)); return dec; } #define arch_atomic_dec_if_positive arch_atomic_dec_if_positive #endif #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> #endif #ifndef arch_atomic64_read_acquire static __always_inline s64 arch_atomic64_read_acquire(const atomic64_t *v) { return smp_load_acquire(&(v)->counter); } #define arch_atomic64_read_acquire arch_atomic64_read_acquire #endif #ifndef arch_atomic64_set_release static __always_inline void arch_atomic64_set_release(atomic64_t *v, s64 i) { smp_store_release(&(v)->counter, i); } #define arch_atomic64_set_release arch_atomic64_set_release #endif #ifndef arch_atomic64_add_return_relaxed #define arch_atomic64_add_return_acquire arch_atomic64_add_return #define arch_atomic64_add_return_release arch_atomic64_add_return #define arch_atomic64_add_return_relaxed arch_atomic64_add_return #else /* arch_atomic64_add_return_relaxed */ #ifndef arch_atomic64_add_return_acquire static __always_inline s64 arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire #endif #ifndef arch_atomic64_add_return_release static __always_inline s64 arch_atomic64_add_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_add_return_relaxed(i, v); } #define arch_atomic64_add_return_release arch_atomic64_add_return_release #endif #ifndef arch_atomic64_add_return static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_add_return arch_atomic64_add_return #endif #endif /* arch_atomic64_add_return_relaxed */ #ifndef arch_atomic64_fetch_add_relaxed #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add #define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add #else /* arch_atomic64_fetch_add_relaxed */ #ifndef arch_atomic64_fetch_add_acquire static __always_inline s64 arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire #endif #ifndef arch_atomic64_fetch_add_release static __always_inline s64 arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_add_relaxed(i, v); } #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release #endif #ifndef arch_atomic64_fetch_add static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_add arch_atomic64_fetch_add #endif #endif /* arch_atomic64_fetch_add_relaxed */ #ifndef arch_atomic64_sub_return_relaxed #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return #define arch_atomic64_sub_return_release arch_atomic64_sub_return #define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return #else /* arch_atomic64_sub_return_relaxed */ #ifndef arch_atomic64_sub_return_acquire static __always_inline s64 arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire #endif #ifndef arch_atomic64_sub_return_release static __always_inline s64 arch_atomic64_sub_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_sub_return_relaxed(i, v); } #define arch_atomic64_sub_return_release arch_atomic64_sub_return_release #endif #ifndef arch_atomic64_sub_return static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_sub_return arch_atomic64_sub_return #endif #endif /* arch_atomic64_sub_return_relaxed */ #ifndef arch_atomic64_fetch_sub_relaxed #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub #define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub #else /* arch_atomic64_fetch_sub_relaxed */ #ifndef arch_atomic64_fetch_sub_acquire static __always_inline s64 arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire #endif #ifndef arch_atomic64_fetch_sub_release static __always_inline s64 arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_sub_relaxed(i, v); } #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release #endif #ifndef arch_atomic64_fetch_sub static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub #endif #endif /* arch_atomic64_fetch_sub_relaxed */ #ifndef arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { arch_atomic64_add(1, v); } #define arch_atomic64_inc arch_atomic64_inc #endif #ifndef arch_atomic64_inc_return_relaxed #ifdef arch_atomic64_inc_return #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return #define arch_atomic64_inc_return_release arch_atomic64_inc_return #define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return #endif /* arch_atomic64_inc_return */ #ifndef arch_atomic64_inc_return static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { return arch_atomic64_add_return(1, v); } #define arch_atomic64_inc_return arch_atomic64_inc_return #endif #ifndef arch_atomic64_inc_return_acquire static __always_inline s64 arch_atomic64_inc_return_acquire(atomic64_t *v) { return arch_atomic64_add_return_acquire(1, v); } #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire #endif #ifndef arch_atomic64_inc_return_release static __always_inline s64 arch_atomic64_inc_return_release(atomic64_t *v) { return arch_atomic64_add_return_release(1, v); } #define arch_atomic64_inc_return_release arch_atomic64_inc_return_release #endif #ifndef arch_atomic64_inc_return_relaxed static __always_inline s64 arch_atomic64_inc_return_relaxed(atomic64_t *v) { return arch_atomic64_add_return_relaxed(1, v); } #define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed #endif #else /* arch_atomic64_inc_return_relaxed */ #ifndef arch_atomic64_inc_return_acquire static __always_inline s64 arch_atomic64_inc_return_acquire(atomic64_t *v) { s64 ret = arch_atomic64_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire #endif #ifndef arch_atomic64_inc_return_release static __always_inline s64 arch_atomic64_inc_return_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_inc_return_relaxed(v); } #define arch_atomic64_inc_return_release arch_atomic64_inc_return_release #endif #ifndef arch_atomic64_inc_return static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_inc_return arch_atomic64_inc_return #endif #endif /* arch_atomic64_inc_return_relaxed */ #ifndef arch_atomic64_fetch_inc_relaxed #ifdef arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc #endif /* arch_atomic64_fetch_inc */ #ifndef arch_atomic64_fetch_inc static __always_inline s64 arch_atomic64_fetch_inc(atomic64_t *v) { return arch_atomic64_fetch_add(1, v); } #define arch_atomic64_fetch_inc arch_atomic64_fetch_inc #endif #ifndef arch_atomic64_fetch_inc_acquire static __always_inline s64 arch_atomic64_fetch_inc_acquire(atomic64_t *v) { return arch_atomic64_fetch_add_acquire(1, v); } #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire #endif #ifndef arch_atomic64_fetch_inc_release static __always_inline s64 arch_atomic64_fetch_inc_release(atomic64_t *v) { return arch_atomic64_fetch_add_release(1, v); } #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release #endif #ifndef arch_atomic64_fetch_inc_relaxed static __always_inline s64 arch_atomic64_fetch_inc_relaxed(atomic64_t *v) { return arch_atomic64_fetch_add_relaxed(1, v); } #define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed #endif #else /* arch_atomic64_fetch_inc_relaxed */ #ifndef arch_atomic64_fetch_inc_acquire static __always_inline s64 arch_atomic64_fetch_inc_acquire(atomic64_t *v) { s64 ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire #endif #ifndef arch_atomic64_fetch_inc_release static __always_inline s64 arch_atomic64_fetch_inc_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_inc_relaxed(v); } #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release #endif #ifndef arch_atomic64_fetch_inc static __always_inline s64 arch_atomic64_fetch_inc(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_inc arch_atomic64_fetch_inc #endif #endif /* arch_atomic64_fetch_inc_relaxed */ #ifndef arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { arch_atomic64_sub(1, v); } #define arch_atomic64_dec arch_atomic64_dec #endif #ifndef arch_atomic64_dec_return_relaxed #ifdef arch_atomic64_dec_return #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return #define arch_atomic64_dec_return_release arch_atomic64_dec_return #define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return #endif /* arch_atomic64_dec_return */ #ifndef arch_atomic64_dec_return static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { return arch_atomic64_sub_return(1, v); } #define arch_atomic64_dec_return arch_atomic64_dec_return #endif #ifndef arch_atomic64_dec_return_acquire static __always_inline s64 arch_atomic64_dec_return_acquire(atomic64_t *v) { return arch_atomic64_sub_return_acquire(1, v); } #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire #endif #ifndef arch_atomic64_dec_return_release static __always_inline s64 arch_atomic64_dec_return_release(atomic64_t *v) { return arch_atomic64_sub_return_release(1, v); } #define arch_atomic64_dec_return_release arch_atomic64_dec_return_release #endif #ifndef arch_atomic64_dec_return_relaxed static __always_inline s64 arch_atomic64_dec_return_relaxed(atomic64_t *v) { return arch_atomic64_sub_return_relaxed(1, v); } #define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed #endif #else /* arch_atomic64_dec_return_relaxed */ #ifndef arch_atomic64_dec_return_acquire static __always_inline s64 arch_atomic64_dec_return_acquire(atomic64_t *v) { s64 ret = arch_atomic64_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire #endif #ifndef arch_atomic64_dec_return_release static __always_inline s64 arch_atomic64_dec_return_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_dec_return_relaxed(v); } #define arch_atomic64_dec_return_release arch_atomic64_dec_return_release #endif #ifndef arch_atomic64_dec_return static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_dec_return arch_atomic64_dec_return #endif #endif /* arch_atomic64_dec_return_relaxed */ #ifndef arch_atomic64_fetch_dec_relaxed #ifdef arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec #endif /* arch_atomic64_fetch_dec */ #ifndef arch_atomic64_fetch_dec static __always_inline s64 arch_atomic64_fetch_dec(atomic64_t *v) { return arch_atomic64_fetch_sub(1, v); } #define arch_atomic64_fetch_dec arch_atomic64_fetch_dec #endif #ifndef arch_atomic64_fetch_dec_acquire static __always_inline s64 arch_atomic64_fetch_dec_acquire(atomic64_t *v) { return arch_atomic64_fetch_sub_acquire(1, v); } #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire #endif #ifndef arch_atomic64_fetch_dec_release static __always_inline s64 arch_atomic64_fetch_dec_release(atomic64_t *v) { return arch_atomic64_fetch_sub_release(1, v); } #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release #endif #ifndef arch_atomic64_fetch_dec_relaxed static __always_inline s64 arch_atomic64_fetch_dec_relaxed(atomic64_t *v) { return arch_atomic64_fetch_sub_relaxed(1, v); } #define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed #endif #else /* arch_atomic64_fetch_dec_relaxed */ #ifndef arch_atomic64_fetch_dec_acquire static __always_inline s64 arch_atomic64_fetch_dec_acquire(atomic64_t *v) { s64 ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire #endif #ifndef arch_atomic64_fetch_dec_release static __always_inline s64 arch_atomic64_fetch_dec_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_dec_relaxed(v); } #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release #endif #ifndef arch_atomic64_fetch_dec static __always_inline s64 arch_atomic64_fetch_dec(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_dec arch_atomic64_fetch_dec #endif #endif /* arch_atomic64_fetch_dec_relaxed */ #ifndef arch_atomic64_fetch_and_relaxed #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and #define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and #else /* arch_atomic64_fetch_and_relaxed */ #ifndef arch_atomic64_fetch_and_acquire static __always_inline s64 arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire #endif #ifndef arch_atomic64_fetch_and_release static __always_inline s64 arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_and_relaxed(i, v); } #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release #endif #ifndef arch_atomic64_fetch_and static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_and arch_atomic64_fetch_and #endif #endif /* arch_atomic64_fetch_and_relaxed */ #ifndef arch_atomic64_andnot static __always_inline void arch_atomic64_andnot(s64 i, atomic64_t *v) { arch_atomic64_and(~i, v); } #define arch_atomic64_andnot arch_atomic64_andnot #endif #ifndef arch_atomic64_fetch_andnot_relaxed #ifdef arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot #endif /* arch_atomic64_fetch_andnot */ #ifndef arch_atomic64_fetch_andnot static __always_inline s64 arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and(~i, v); } #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #endif #ifndef arch_atomic64_fetch_andnot_acquire static __always_inline s64 arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_acquire(~i, v); } #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #endif #ifndef arch_atomic64_fetch_andnot_release static __always_inline s64 arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_release(~i, v); } #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #endif #ifndef arch_atomic64_fetch_andnot_relaxed static __always_inline s64 arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_relaxed(~i, v); } #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed #endif #else /* arch_atomic64_fetch_andnot_relaxed */ #ifndef arch_atomic64_fetch_andnot_acquire static __always_inline s64 arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #endif #ifndef arch_atomic64_fetch_andnot_release static __always_inline s64 arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_andnot_relaxed(i, v); } #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #endif #ifndef arch_atomic64_fetch_andnot static __always_inline s64 arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #endif #endif /* arch_atomic64_fetch_andnot_relaxed */ #ifndef arch_atomic64_fetch_or_relaxed #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or #define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or #else /* arch_atomic64_fetch_or_relaxed */ #ifndef arch_atomic64_fetch_or_acquire static __always_inline s64 arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire #endif #ifndef arch_atomic64_fetch_or_release static __always_inline s64 arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_or_relaxed(i, v); } #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release #endif #ifndef arch_atomic64_fetch_or static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_or arch_atomic64_fetch_or #endif #endif /* arch_atomic64_fetch_or_relaxed */ #ifndef arch_atomic64_fetch_xor_relaxed #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor #define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor #else /* arch_atomic64_fetch_xor_relaxed */ #ifndef arch_atomic64_fetch_xor_acquire static __always_inline s64 arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire #endif #ifndef arch_atomic64_fetch_xor_release static __always_inline s64 arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_xor_relaxed(i, v); } #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release #endif #ifndef arch_atomic64_fetch_xor static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor #endif #endif /* arch_atomic64_fetch_xor_relaxed */ #ifndef arch_atomic64_xchg_relaxed #define arch_atomic64_xchg_acquire arch_atomic64_xchg #define arch_atomic64_xchg_release arch_atomic64_xchg #define arch_atomic64_xchg_relaxed arch_atomic64_xchg #else /* arch_atomic64_xchg_relaxed */ #ifndef arch_atomic64_xchg_acquire static __always_inline s64 arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) { s64 ret = arch_atomic64_xchg_relaxed(v, i); __atomic_acquire_fence(); return ret; } #define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire #endif #ifndef arch_atomic64_xchg_release static __always_inline s64 arch_atomic64_xchg_release(atomic64_t *v, s64 i) { __atomic_release_fence(); return arch_atomic64_xchg_relaxed(v, i); } #define arch_atomic64_xchg_release arch_atomic64_xchg_release #endif #ifndef arch_atomic64_xchg static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 i) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_xchg_relaxed(v, i); __atomic_post_full_fence(); return ret; } #define arch_atomic64_xchg arch_atomic64_xchg #endif #endif /* arch_atomic64_xchg_relaxed */ #ifndef arch_atomic64_cmpxchg_relaxed #define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg #define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg #define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg #else /* arch_atomic64_cmpxchg_relaxed */ #ifndef arch_atomic64_cmpxchg_acquire static __always_inline s64 arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire #endif #ifndef arch_atomic64_cmpxchg_release static __always_inline s64 arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { __atomic_release_fence(); return arch_atomic64_cmpxchg_relaxed(v, old, new); } #define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release #endif #ifndef arch_atomic64_cmpxchg static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg #endif #endif /* arch_atomic64_cmpxchg_relaxed */ #ifndef arch_atomic64_try_cmpxchg_relaxed #ifdef arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg #endif /* arch_atomic64_try_cmpxchg */ #ifndef arch_atomic64_try_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg #endif #ifndef arch_atomic64_try_cmpxchg_acquire static __always_inline bool arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire #endif #ifndef arch_atomic64_try_cmpxchg_release static __always_inline bool arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release #endif #ifndef arch_atomic64_try_cmpxchg_relaxed static __always_inline bool arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed #endif #else /* arch_atomic64_try_cmpxchg_relaxed */ #ifndef arch_atomic64_try_cmpxchg_acquire static __always_inline bool arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire #endif #ifndef arch_atomic64_try_cmpxchg_release static __always_inline bool arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { __atomic_release_fence(); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); } #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release #endif #ifndef arch_atomic64_try_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg #endif #endif /* arch_atomic64_try_cmpxchg_relaxed */ #ifndef arch_atomic64_sub_and_test /** * arch_atomic64_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic64_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) { return arch_atomic64_sub_return(i, v) == 0; } #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test #endif #ifndef arch_atomic64_dec_and_test /** * arch_atomic64_dec_and_test - decrement and test * @v: pointer of type atomic64_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) { return arch_atomic64_dec_return(v) == 0; } #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test #endif #ifndef arch_atomic64_inc_and_test /** * arch_atomic64_inc_and_test - increment and test * @v: pointer of type atomic64_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) { return arch_atomic64_inc_return(v) == 0; } #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test #endif #ifndef arch_atomic64_add_negative /** * arch_atomic64_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic64_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) { return arch_atomic64_add_return(i, v) < 0; } #define arch_atomic64_add_negative arch_atomic64_add_negative #endif #ifndef arch_atomic64_fetch_add_unless /** * arch_atomic64_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 c = arch_atomic64_read(v); do { if (unlikely(c == u)) break; } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); return c; } #define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless #endif #ifndef arch_atomic64_add_unless /** * arch_atomic64_add_unless - add unless the number is already a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ static __always_inline bool arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { return arch_atomic64_fetch_add_unless(v, a, u) != u; } #define arch_atomic64_add_unless arch_atomic64_add_unless #endif #ifndef arch_atomic64_inc_not_zero /** * arch_atomic64_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic64_t * * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ static __always_inline bool arch_atomic64_inc_not_zero(atomic64_t *v) { return arch_atomic64_add_unless(v, 1, 0); } #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero #endif #ifndef arch_atomic64_inc_unless_negative static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v) { s64 c = arch_atomic64_read(v); do { if (unlikely(c < 0)) return false; } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); return true; } #define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative #endif #ifndef arch_atomic64_dec_unless_positive static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v) { s64 c = arch_atomic64_read(v); do { if (unlikely(c > 0)) return false; } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); return true; } #define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive #endif #ifndef arch_atomic64_dec_if_positive static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) { s64 dec, c = arch_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); return dec; } #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ // 90cd26cfd69d2250303d654955a0cc12620fb91b |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - decrement refcount for object. * @kref: object. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * Return non-zero if the increment succeeded. Otherwise return 0. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 | // SPDX-License-Identifier: GPL-2.0 /* * Block multiqueue core code * * Copyright (C) 2013-2014 Jens Axboe * Copyright (C) 2013-2014 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/kmemleak.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/smp.h> #include <linux/llist.h> #include <linux/list_sort.h> #include <linux/cpu.h> #include <linux/cache.h> #include <linux/sched/sysctl.h> #include <linux/sched/topology.h> #include <linux/sched/signal.h> #include <linux/suspend.h> #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> #include <linux/blk-crypto.h> #include <trace/events/block.h> #include <linux/blk-mq.h> #include <linux/t10-pi.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-tag.h" #include "blk-pm.h" #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" static DEFINE_PER_CPU(struct list_head, blk_cpu_done); static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); static int blk_mq_poll_stats_bkt(const struct request *rq) { int ddir, sectors, bucket; ddir = rq_data_dir(rq); sectors = blk_rq_stats_sectors(rq); bucket = ddir + 2 * ilog2(sectors); if (bucket < 0) return -1; else if (bucket >= BLK_MQ_POLL_STATS_BKTS) return ddir + BLK_MQ_POLL_STATS_BKTS - 2; return bucket; } /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { return !list_empty_careful(&hctx->dispatch) || sbitmap_any_bit_set(&hctx->ctx_map) || blk_mq_sched_has_work(hctx); } /* * Mark this ctx as having pending work in this hardware queue */ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; if (!sbitmap_test_bit(&hctx->ctx_map, bit)) sbitmap_set_bit(&hctx->ctx_map, bit); } static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; sbitmap_clear_bit(&hctx->ctx_map, bit); } struct mq_inflight { struct hd_struct *part; unsigned int inflight[2]; }; static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { struct mq_inflight *mi = priv; if ((!mi->part->partno || rq->part == mi->part) && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++; return true; } unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); return mi.inflight[0] + mi.inflight[1]; } void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); inflight[0] = mi.inflight[0]; inflight[1] = mi.inflight[1]; } void blk_freeze_queue_start(struct request_queue *q) { mutex_lock(&q->mq_freeze_lock); if (++q->mq_freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); mutex_unlock(&q->mq_freeze_lock); if (queue_is_mq(q)) blk_mq_run_hw_queues(q, false); } else { mutex_unlock(&q->mq_freeze_lock); } } EXPORT_SYMBOL_GPL(blk_freeze_queue_start); void blk_mq_freeze_queue_wait(struct request_queue *q) { wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout) { return wait_event_timeout(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter), timeout); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); /* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. */ void blk_freeze_queue(struct request_queue *q) { /* * In the !blk_mq case we are only calling this to kill the * q_usage_counter, otherwise this increases the freeze depth * and waits for it to return to zero. For this reason there is * no blk_unfreeze_queue(), and blk_freeze_queue() is not * exported to drivers as the only user for unfreeze is blk_mq. */ blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } void blk_mq_freeze_queue(struct request_queue *q) { /* * ...just an alias to keep freeze and unfreeze actions balanced * in the blk_mq_* namespace */ blk_freeze_queue(q); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); void blk_mq_unfreeze_queue(struct request_queue *q) { mutex_lock(&q->mq_freeze_lock); q->mq_freeze_depth--; WARN_ON_ONCE(q->mq_freeze_depth < 0); if (!q->mq_freeze_depth) { percpu_ref_resurrect(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } mutex_unlock(&q->mq_freeze_lock); } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); /* * FIXME: replace the scsi_internal_device_*block_nowait() calls in the * mpt3sas driver such that this function can be removed. */ void blk_mq_quiesce_queue_nowait(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); /** * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished * @q: request queue. * * Note: this function does not prevent that the struct request end_io() * callback function is invoked. Once this function is returned, we make * sure no dispatch can happen until the queue is unquiesced via * blk_mq_unquiesce_queue(). */ void blk_mq_quiesce_queue(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; bool rcu = false; blk_mq_quiesce_queue_nowait(q); queue_for_each_hw_ctx(q, hctx, i) { if (hctx->flags & BLK_MQ_F_BLOCKING) synchronize_srcu(hctx->srcu); else rcu = true; } if (rcu) synchronize_rcu(); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); /* * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() * @q: request queue. * * This function recovers queue into the state before quiescing * which is done by blk_mq_quiesce_queue. */ void blk_mq_unquiesce_queue(struct request_queue *q) { blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); /* dispatch requests which are inserted during quiescing */ blk_mq_run_hw_queues(q, true); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_wakeup_all(hctx->tags, true); } /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. */ static inline bool blk_mq_need_time_stamp(struct request *rq) { return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator; } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, unsigned int tag, u64 alloc_time_ns) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct request *rq = tags->static_rqs[tag]; if (data->q->elevator) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; } /* csd/requeue_work/fifo_time is initialized before use */ rq->q = data->q; rq->mq_ctx = data->ctx; rq->mq_hctx = data->hctx; rq->rq_flags = 0; rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PM) rq->rq_flags |= RQF_PM; if (blk_queue_io_stat(data->q)) rq->rq_flags |= RQF_IO_STAT; INIT_LIST_HEAD(&rq->queuelist); INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->rq_disk = NULL; rq->part = NULL; #ifdef CONFIG_BLK_RQ_ALLOC_TIME rq->alloc_time_ns = alloc_time_ns; #endif if (blk_mq_need_time_stamp(rq)) rq->start_time_ns = ktime_get_ns(); else rq->start_time_ns = 0; rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif blk_crypto_rq_set_defaults(rq); /* tag was already set */ WRITE_ONCE(rq->deadline, 0); rq->timeout = 0; rq->end_io = NULL; rq->end_io_data = NULL; data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++; refcount_set(&rq->ref, 1); if (!op_is_flush(data->cmd_flags)) { struct elevator_queue *e = data->q->elevator; rq->elv.icq = NULL; if (e && e->type->ops.prepare_request) { if (e->type->icq_cache) blk_mq_sched_assign_ioc(rq); e->type->ops.prepare_request(rq); rq->rq_flags |= RQF_ELVPRIV; } } data->hctx->queued++; return rq; } static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data) { struct request_queue *q = data->q; struct elevator_queue *e = q->elevator; u64 alloc_time_ns = 0; unsigned int tag; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = ktime_get_ns(); if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; if (e) { /* * Flush requests are special and go directly to the * dispatch list. Don't include reserved tags in the * limiting, as it isn't useful. */ if (!op_is_flush(data->cmd_flags) && e->type->ops.limit_depth && !(data->flags & BLK_MQ_REQ_RESERVED)) e->type->ops.limit_depth(data->cmd_flags, data); } retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); if (!e) blk_mq_tag_busy(data->hctx); /* * Waiting allocations only fail because of an inactive hctx. In that * case just retry the hctx assignment and tag allocation as CPU hotplug * should have migrated us to an online CPU by now. */ tag = blk_mq_get_tag(data); if (tag == BLK_MQ_NO_TAG) { if (data->flags & BLK_MQ_REQ_NOWAIT) return NULL; /* * Give up the CPU and sleep for a random short time to ensure * that thread using a realtime scheduling class are migrated * off the CPU, and thus off the hctx that is going away. */ msleep(3); goto retry; } return blk_mq_rq_ctx_init(data, tag, alloc_time_ns); } struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = op, }; struct request *rq; int ret; ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); rq = __blk_mq_alloc_request(&data); if (!rq) goto out_queue_exit; rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); } EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = op, }; u64 alloc_time_ns = 0; unsigned int cpu; unsigned int tag; int ret; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = ktime_get_ns(); /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) || WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) return ERR_PTR(-EIO); ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); /* * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ ret = -EXDEV; data.hctx = q->queue_hw_ctx[hctx_idx]; if (!blk_mq_hw_queue_mapped(data.hctx)) goto out_queue_exit; cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); if (!q->elevator) blk_mq_tag_busy(data.hctx); ret = -EWOULDBLOCK; tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) goto out_queue_exit; return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns); out_queue_exit: blk_queue_exit(q); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->tags, ctx, rq->tag); if (sched_tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (rq->rq_flags & RQF_ELVPRIV) { if (e && e->type->ops.finish_request) e->type->ops.finish_request(rq); if (rq->elv.icq) { put_io_context(rq->elv.icq->ioc); rq->elv.icq = NULL; } } ctx->rq_completed[rq_is_sync(rq)]++; if (rq->rq_flags & RQF_MQ_INFLIGHT) __blk_mq_dec_active_requests(hctx); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->backing_dev_info); rq_qos_done(q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (refcount_dec_and_test(&rq->ref)) __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { u64 now = 0; if (blk_mq_need_time_stamp(rq)) now = ktime_get_ns(); if (rq->rq_flags & RQF_STATS) { blk_mq_poll_stats_start(rq->q); blk_stat_add(rq, now); } blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); if (rq->end_io) { rq_qos_done(rq->q, rq); rq->end_io(rq, error); } else { blk_mq_free_request(rq); } } EXPORT_SYMBOL(__blk_mq_end_request); void blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); __blk_mq_end_request(rq, error); } EXPORT_SYMBOL(blk_mq_end_request); /* * Softirq action handler - move entries to local list and loop over them * while passing them to the queue registered handler. */ static __latent_entropy void blk_done_softirq(struct softirq_action *h) { struct list_head *cpu_list, local_list; local_irq_disable(); cpu_list = this_cpu_ptr(&blk_cpu_done); list_replace_init(cpu_list, &local_list); local_irq_enable(); while (!list_empty(&local_list)) { struct request *rq; rq = list_entry(local_list.next, struct request, ipi_list); list_del_init(&rq->ipi_list); rq->q->mq_ops->complete(rq); } } static void blk_mq_trigger_softirq(struct request *rq) { struct list_head *list; unsigned long flags; local_irq_save(flags); list = this_cpu_ptr(&blk_cpu_done); list_add_tail(&rq->ipi_list, list); /* * If the list only contains our just added request, signal a raise of * the softirq. If there are already entries there, someone already * raised the irq but it hasn't run yet. */ if (list->next == &rq->ipi_list) raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_restore(flags); } static int blk_softirq_cpu_dead(unsigned int cpu) { /* * If a CPU goes away, splice its entries to the current CPU * and trigger a run of the softirq */ local_irq_disable(); list_splice_init(&per_cpu(blk_cpu_done, cpu), this_cpu_ptr(&blk_cpu_done)); raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_enable(); return 0; } static void __blk_mq_complete_request_remote(void *data) { struct request *rq = data; /* * For most of single queue controllers, there is only one irq vector * for handling I/O completion, and the only irq's affinity is set * to all possible CPUs. On most of ARCHs, this affinity means the irq * is handled on one specific CPU. * * So complete I/O requests in softirq context in case of single queue * devices to avoid degrading I/O performance due to irqsoff latency. */ if (rq->q->nr_hw_queues == 1) blk_mq_trigger_softirq(rq); else rq->q->mq_ops->complete(rq); } static inline bool blk_mq_complete_need_ipi(struct request *rq) { int cpu = raw_smp_processor_id(); if (!IS_ENABLED(CONFIG_SMP) || !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) return false; /* same CPU or cache domain? Complete locally */ if (cpu == rq->mq_ctx->cpu || (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) && cpus_share_cache(cpu, rq->mq_ctx->cpu))) return false; /* don't try to IPI to an offline CPU */ return cpu_online(rq->mq_ctx->cpu); } bool blk_mq_complete_request_remote(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* * For a polled request, always complete locallly, it's pointless * to redirect the completion. */ if (rq->cmd_flags & REQ_HIPRI) return false; if (blk_mq_complete_need_ipi(rq)) { rq->csd.func = __blk_mq_complete_request_remote; rq->csd.info = rq; rq->csd.flags = 0; smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd); } else { if (rq->q->nr_hw_queues > 1) return false; blk_mq_trigger_softirq(rq); } return true; } EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote); /** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed * * Description: * Complete a request by scheduling the ->complete_rq operation. **/ void blk_mq_complete_request(struct request *rq) { if (!blk_mq_complete_request_remote(rq)) rq->q->mq_ops->complete(rq); } EXPORT_SYMBOL(blk_mq_complete_request); static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) __releases(hctx->srcu) { if (!(hctx->flags & BLK_MQ_F_BLOCKING)) rcu_read_unlock(); else srcu_read_unlock(hctx->srcu, srcu_idx); } static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx) __acquires(hctx->srcu) { if (!(hctx->flags & BLK_MQ_F_BLOCKING)) { /* shut up gcc false positive */ *srcu_idx = 0; rcu_read_lock(); } else *srcu_idx = srcu_read_lock(hctx->srcu); } /** * blk_mq_start_request - Start processing a request * @rq: Pointer to request to be started * * Function used by device drivers to notify the block layer that a request * is going to be processed now, so blk layer can do proper initializations * such as starting the timeout timer. */ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { rq->io_start_time_ns = ktime_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); blk_add_timer(rq); WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) q->integrity.profile->prepare_fn(rq); #endif } EXPORT_SYMBOL(blk_mq_start_request); static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_put_driver_tag(rq); trace_block_rq_requeue(rq); rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); rq->rq_flags &= ~RQF_TIMED_OUT; } } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); blk_mq_add_to_requeue_list(rq, true, kick_requeue_list); } EXPORT_SYMBOL(blk_mq_requeue_request); static void blk_mq_requeue_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); struct request *rq, *next; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); spin_unlock_irq(&q->requeue_lock); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP))) continue; rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); /* * If RQF_DONTPREP, rq has contained some driver specific * data, so insert it to hctx dispatch list to avoid any * merge. */ if (rq->rq_flags & RQF_DONTPREP) blk_mq_request_bypass_insert(rq, false, false); else blk_mq_sched_insert_request(rq, true, false, false); } while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_sched_insert_request(rq, false, false, false); } blk_mq_run_hw_queues(q, false); } void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list) { struct request_queue *q = rq->q; unsigned long flags; /* * We abuse this flag that is otherwise used by the I/O scheduler to * request head insertion from the workqueue. */ BUG_ON(rq->rq_flags & RQF_SOFTBARRIER); spin_lock_irqsave(&q->requeue_lock, flags); if (at_head) { rq->rq_flags |= RQF_SOFTBARRIER; list_add(&rq->queuelist, &q->requeue_list); } else { list_add_tail(&rq->queuelist, &q->requeue_list); } spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); } void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); } EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) { if (tag < tags->nr_tags) { prefetch(tags->rqs[tag]); return tags->rqs[tag]; } return NULL; } EXPORT_SYMBOL(blk_mq_tag_to_rq); static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { /* * If we find a request that isn't idle and the queue matches, * we know the queue is busy. Return false to stop the iteration. */ if (blk_mq_request_started(rq) && rq->q == hctx->queue) { bool *busy = priv; *busy = true; return false; } return true; } bool blk_mq_queue_inflight(struct request_queue *q) { bool busy = false; blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy); return busy; } EXPORT_SYMBOL_GPL(blk_mq_queue_inflight); static void blk_mq_rq_timed_out(struct request *req, bool reserved) { req->rq_flags |= RQF_TIMED_OUT; if (req->q->mq_ops->timeout) { enum blk_eh_timer_return ret; ret = req->q->mq_ops->timeout(req, reserved); if (ret == BLK_EH_DONE) return; WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } blk_add_timer(req); } static bool blk_mq_req_expired(struct request *rq, unsigned long *next) { unsigned long deadline; if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT) return false; if (rq->rq_flags & RQF_TIMED_OUT) return false; deadline = READ_ONCE(rq->deadline); if (time_after_eq(jiffies, deadline)) return true; if (*next == 0) *next = deadline; else if (time_after(*next, deadline)) *next = deadline; return false; } void blk_mq_put_rq_ref(struct request *rq) { if (is_flush_rq(rq)) rq->end_io(rq, 0); else if (refcount_dec_and_test(&rq->ref)) __blk_mq_free_request(rq); } static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { unsigned long *next = priv; /* * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot * be reallocated underneath the timeout handler's processing, then * the expire check is reliable. If the request is not expired, then * it was completed and reallocated as a new request after returning * from blk_mq_check_expired(). */ if (blk_mq_req_expired(rq, next)) blk_mq_rq_timed_out(rq, reserved); return true; } static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); unsigned long next = 0; struct blk_mq_hw_ctx *hctx; int i; /* A deadlock might occur if a request is stuck requiring a * timeout at the same time a queue freeze is waiting * completion, since the timeout code would not be able to * acquire the queue reference here. * * That's why we don't use blk_queue_enter here; instead, we use * percpu_ref_tryget directly, because we need to be able to * obtain a reference even in the short window between the queue * starting to freeze, by dropping the first reference in * blk_freeze_queue_start, and the moment the last request is * consumed, marked by the instant q_usage_counter reaches * zero. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next); if (next != 0) { mod_timer(&q->timeout, next); } else { /* * Request timeouts are handled as a forward rolling timer. If * we end up here it means that no requests are pending and * also that no request has been pending for a while. Mark * each hctx as idle. */ queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); } } blk_queue_exit(q); } struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; }; static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct flush_busy_ctx_data *flush_data = data; struct blk_mq_hw_ctx *hctx = flush_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); list_splice_tail_init(&ctx->rq_lists[type], flush_data->list); sbitmap_clear_bit(sb, bitnr); spin_unlock(&ctx->lock); return true; } /* * Process software queues that have been marked busy, splicing them * to the for-dispatch */ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) { struct flush_busy_ctx_data data = { .hctx = hctx, .list = list, }; sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data); } EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs); struct dispatch_rq_data { struct blk_mq_hw_ctx *hctx; struct request *rq; }; static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct dispatch_rq_data *dispatch_data = data; struct blk_mq_hw_ctx *hctx = dispatch_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next); list_del_init(&dispatch_data->rq->queuelist); if (list_empty(&ctx->rq_lists[type])) sbitmap_clear_bit(sb, bitnr); } spin_unlock(&ctx->lock); return !dispatch_data->rq; } struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start) { unsigned off = start ? start->index_hw[hctx->type] : 0; struct dispatch_rq_data data = { .hctx = hctx, .rq = NULL, }; __sbitmap_for_each_set(&hctx->ctx_map, off, dispatch_rq_from_ctx, &data); return data.rq; } static inline unsigned int queued_to_index(unsigned int queued) { if (!queued) return 0; return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1); } static bool __blk_mq_get_driver_tag(struct request *rq) { struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags; unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; int tag; blk_mq_tag_busy(rq->mq_hctx); if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { bt = rq->mq_hctx->tags->breserved_tags; tag_offset = 0; } else { if (!hctx_may_queue(rq->mq_hctx, bt)) return false; } tag = __sbitmap_queue_get(bt); if (tag == BLK_MQ_NO_TAG) return false; rq->tag = tag + tag_offset; return true; } static bool blk_mq_get_driver_tag(struct request *rq) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq)) return false; if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(rq->rq_flags & RQF_MQ_INFLIGHT)) { rq->rq_flags |= RQF_MQ_INFLIGHT; __blk_mq_inc_active_requests(hctx); } hctx->tags->rqs[rq->tag] = rq; return true; } static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx; hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { struct sbitmap_queue *sbq; list_del_init(&wait->entry); sbq = hctx->tags->bitmap_tags; atomic_dec(&sbq->ws_active); } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); return 1; } /* * Mark us waiting for a tag. For shared tags, this involves hooking us into * the tag wakeups. For non-shared tags, we can simply mark us needing a * restart. For both cases, take care to check the condition again after * marking us as waiting. */ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct sbitmap_queue *sbq = hctx->tags->bitmap_tags; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { blk_mq_sched_mark_restart_hctx(hctx); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. * * Don't clear RESTART here, someone else could have set it. * At most this will cost an extra queue run. */ return blk_mq_get_driver_tag(rq); } wait = &hctx->dispatch_wait; if (!list_empty_careful(&wait->entry)) return false; wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); /* * Add one explicit barrier since blk_mq_get_driver_tag() may * not imply barrier in case of failure. * * Order adding us to wait queue and allocating driver tag. * * The pair is the one implied in sbitmap_queue_wake_up() which * orders clearing sbitmap tag bits and waitqueue_active() in * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless * * Otherwise, re-order of adding wait queue and getting driver tag * may cause __sbitmap_queue_wake_up() to wake up nothing because * the waitqueue_active() may not observe us in wait queue. */ smp_mb(); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. */ ret = blk_mq_get_driver_tag(rq); if (!ret) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } /* * We got a tag, remove ourselves from the wait queue to ensure * someone else gets the wakeup. */ list_del_init(&wait->entry); atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return true; } #define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8 #define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4 /* * Update dispatch busy with the Exponential Weighted Moving Average(EWMA): * - EWMA is one simple way to compute running average value * - weight(7/8 and 1/8) is applied so that it can decrease exponentially * - take 4 as factor for avoiding to get too small(0) result, and this * factor doesn't matter because EWMA decreases exponentially */ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; ewma = hctx->dispatch_busy; if (!ewma && !busy) return; ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1; if (busy) ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR; ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT; hctx->dispatch_busy = ewma; } #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ static void blk_mq_handle_dev_resource(struct request *rq, struct list_head *list) { struct request *next = list_first_entry_or_null(list, struct request, queuelist); /* * If an I/O scheduler has been configured and we got a driver tag for * the next request already, free it. */ if (next) blk_mq_put_driver_tag(next); list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); } static void blk_mq_handle_zone_resource(struct request *rq, struct list_head *zone_list) { /* * If we end up here it is because we cannot dispatch a request to a * specific zone due to LLD level zone-write locking or other zone * related resource not being available. In this case, set the request * aside in zone_list for retrying it later. */ list_add(&rq->queuelist, zone_list); __blk_mq_requeue_request(rq); } enum prep_dispatch { PREP_DISPATCH_OK, PREP_DISPATCH_NO_TAG, PREP_DISPATCH_NO_BUDGET, }; static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, bool need_budget) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (need_budget && !blk_mq_get_dispatch_budget(rq->q)) { blk_mq_put_driver_tag(rq); return PREP_DISPATCH_NO_BUDGET; } if (!blk_mq_get_driver_tag(rq)) { /* * The initial allocation attempt failed, so we need to * rerun the hardware queue when a tag is freed. The * waitqueue takes care of that. If the queue is run * before we add this entry back on the dispatch list, * we'll re-run it below. */ if (!blk_mq_mark_tag_wait(hctx, rq)) { /* * All budgets not got from this function will be put * together during handling partial dispatch */ if (need_budget) blk_mq_put_dispatch_budget(rq->q); return PREP_DISPATCH_NO_TAG; } } return PREP_DISPATCH_OK; } /* release all allocated budgets before calling to blk_mq_dispatch_rq_list */ static void blk_mq_release_budgets(struct request_queue *q, unsigned int nr_budgets) { int i; for (i = 0; i < nr_budgets; i++) blk_mq_put_dispatch_budget(q); } /* * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, unsigned int nr_budgets) { enum prep_dispatch prep; struct request_queue *q = hctx->queue; struct request *rq, *nxt; int errors, queued; blk_status_t ret = BLK_STS_OK; LIST_HEAD(zone_list); bool needs_resource = false; if (list_empty(list)) return false; /* * Now process all the entries, sending them to the driver. */ errors = queued = 0; do { struct blk_mq_queue_data bd; rq = list_first_entry(list, struct request, queuelist); WARN_ON_ONCE(hctx != rq->mq_hctx); prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets); if (prep != PREP_DISPATCH_OK) break; list_del_init(&rq->queuelist); bd.rq = rq; /* * Flag last if we have no more requests, or if we have more * but can't assign a driver tag to it. */ if (list_empty(list)) bd.last = true; else { nxt = list_first_entry(list, struct request, queuelist); bd.last = !blk_mq_get_driver_tag(nxt); } /* * once the request is queued to lld, no need to cover the * budget any more */ if (nr_budgets) nr_budgets--; ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: needs_resource = true; fallthrough; case BLK_STS_DEV_RESOURCE: blk_mq_handle_dev_resource(rq, list); goto out; case BLK_STS_ZONE_RESOURCE: /* * Move the request to zone_list and keep going through * the dispatch list to find more requests the drive can * accept. */ blk_mq_handle_zone_resource(rq, &zone_list); needs_resource = true; break; default: errors++; blk_mq_end_request(rq, BLK_STS_IOERR); } } while (!list_empty(list)); out: if (!list_empty(&zone_list)) list_splice_tail_init(&zone_list, list); hctx->dispatched[queued_to_index(queued)]++; /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ if ((!list_empty(list) || errors || needs_resource || ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued) q->mq_ops->commit_rqs(hctx); /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. */ if (!list_empty(list)) { bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); blk_mq_release_budgets(q, nr_budgets); spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* * Order adding requests to hctx->dispatch and checking * SCHED_RESTART flag. The pair of this smp_mb() is the one * in blk_mq_sched_restart(). Avoid restart code path to * miss the new added requests to hctx->dispatch, meantime * SCHED_RESTART is observed here. */ smp_mb(); /* * If SCHED_RESTART was set by the caller of this function and * it is no longer set that means that it was cleared by another * thread and hence that a queue rerun is needed. * * If 'no_tag' is set, that means that we failed getting * a driver tag with an I/O scheduler attached. If our dispatch * waitqueue is no longer active, ensure that we run the queue * AFTER adding our entries back to the list. * * If no I/O scheduler has been configured it is possible that * the hardware queue got stopped and restarted before requests * were pushed back onto the dispatch list. Rerun the queue to * avoid starvation. Notes: * - blk_mq_run_hw_queue() checks whether or not a queue has * been stopped before rerunning a queue. * - Some but not all block drivers stop a queue before * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq * and dm-rq. * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do * similar if we couldn't get budget or couldn't lock a zone * and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (prep == PREP_DISPATCH_NO_BUDGET) needs_resource = true; if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); else if (needs_restart && needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); return false; } else blk_mq_update_dispatch_busy(hctx, false); return (queued + errors) != 0; } /** * __blk_mq_run_hw_queue - Run a hardware queue. * @hctx: Pointer to the hardware queue to run. * * Send pending requests to the hardware. */ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) { int srcu_idx; /* * We should be running this queue from one of the CPUs that * are mapped to it. * * There are at least two related races now between setting * hctx->next_cpu from blk_mq_hctx_next_cpu() and running * __blk_mq_run_hw_queue(): * * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(), * but later it becomes online, then this warning is harmless * at all * * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(), * but later it becomes offline, then the warning can't be * triggered, and we depend on blk-mq timeout handler to * handle dispatched requests to this hctx */ if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && cpu_online(hctx->next_cpu)) { printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n", raw_smp_processor_id(), cpumask_empty(hctx->cpumask) ? "inactive": "active"); dump_stack(); } /* * We can't run the queue inline with ints disabled. Ensure that * we catch bad users of this early. */ WARN_ON_ONCE(in_interrupt()); might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); hctx_lock(hctx, &srcu_idx); blk_mq_sched_dispatch_requests(hctx); hctx_unlock(hctx, srcu_idx); } static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx) { int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(hctx->cpumask); return cpu; } /* * It'd be great if the workqueue API had a way to pass * in a mask and had some smarts for more clever placement. * For now we just round-robin here, switching for every * BLK_MQ_CPU_WORK_BATCH queued items. */ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { bool tried = false; int next_cpu = hctx->next_cpu; if (hctx->queue->nr_hw_queues == 1) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { select_cpu: next_cpu = cpumask_next_and(next_cpu, hctx->cpumask, cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } /* * Do unbound schedule if we can't find a online CPU for this hctx, * and it should only happen in the path of handling CPU DEAD. */ if (!cpu_online(next_cpu)) { if (!tried) { tried = true; goto select_cpu; } /* * Make sure to re-select CPU next time once after CPUs * in hctx->cpumask become online again. */ hctx->next_cpu = next_cpu; hctx->next_cpu_batch = 1; return WORK_CPU_UNBOUND; } hctx->next_cpu = next_cpu; return next_cpu; } /** * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue. * @hctx: Pointer to the hardware queue to run. * @async: If we want to run the queue asynchronously. * @msecs: Microseconds of delay to wait before running the queue. * * If !@async, try to run the queue now. Else, run the queue asynchronously and * with a delay of @msecs. */ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, unsigned long msecs) { if (unlikely(blk_mq_hctx_stopped(hctx))) return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { int cpu = get_cpu(); if (cpumask_test_cpu(cpu, hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); put_cpu(); return; } put_cpu(); } kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, msecs_to_jiffies(msecs)); } /** * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously. * @hctx: Pointer to the hardware queue to run. * @msecs: Microseconds of delay to wait before running the queue. * * Run a hardware queue asynchronously with a delay of @msecs. */ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { __blk_mq_delay_run_hw_queue(hctx, true, msecs); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); /** * blk_mq_run_hw_queue - Start to run a hardware queue. * @hctx: Pointer to the hardware queue to run. * @async: If we want to run the queue asynchronously. * * Check if the request queue is not in a quiesced state and if there are * pending requests to be sent. If this is true, run the queue to send requests * to hardware. */ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { int srcu_idx; bool need_run; /* * When queue is quiesced, we may be switching io scheduler, or * updating nr_hw_queues, or other things, and we can't run queue * any more, even __blk_mq_hctx_has_pending() can't be called safely. * * And queue will be rerun in blk_mq_unquiesce_queue() if it is * quiesced. */ hctx_lock(hctx, &srcu_idx); need_run = !blk_queue_quiesced(hctx->queue) && blk_mq_hctx_has_pending(hctx); hctx_unlock(hctx, srcu_idx); if (need_run) __blk_mq_delay_run_hw_queue(hctx, async, 0); } EXPORT_SYMBOL(blk_mq_run_hw_queue); /** * blk_mq_run_hw_queues - Run all hardware queues in a request queue. * @q: Pointer to the request queue to run. * @async: If we want to run the queue asynchronously. */ void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; blk_mq_run_hw_queue(hctx, async); } } EXPORT_SYMBOL(blk_mq_run_hw_queues); /** * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously. * @q: Pointer to the request queue to run. * @msecs: Microseconds of delay to wait before running the queues. */ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; blk_mq_delay_run_hw_queue(hctx, msecs); } } EXPORT_SYMBOL(blk_mq_delay_run_hw_queues); /** * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped * @q: request queue. * * The caller is responsible for serializing this function against * blk_mq_{start,stop}_hw_queue(). */ bool blk_mq_queue_stopped(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hctx_stopped(hctx)) return true; return false; } EXPORT_SYMBOL(blk_mq_queue_stopped); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queue() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { cancel_delayed_work(&hctx->run_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); } EXPORT_SYMBOL(blk_mq_stop_hw_queue); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queues() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_stop_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_stop_hw_queues); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, false); } EXPORT_SYMBOL(blk_mq_start_hw_queue); void blk_mq_start_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_start_hw_queues); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { if (!blk_mq_hctx_stopped(hctx)) return; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); /* * Pairs with the smp_mb() in blk_mq_hctx_stopped() to order the * clearing of BLK_MQ_S_STOPPED above and the checking of dispatch * list in the subsequent routine. */ smp_mb__after_atomic(); blk_mq_run_hw_queue(hctx, async); } EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_stopped_hw_queue(hctx, async); } EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues); static void blk_mq_run_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx; hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work); /* * If we are stopped, don't run the queue. */ if (blk_mq_hctx_stopped(hctx)) return; __blk_mq_run_hw_queue(hctx); } static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; enum hctx_type type = hctx->type; lockdep_assert_held(&ctx->lock); trace_block_rq_insert(rq); if (at_head) list_add(&rq->queuelist, &ctx->rq_lists[type]); else list_add_tail(&rq->queuelist, &ctx->rq_lists[type]); } void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; lockdep_assert_held(&ctx->lock); __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } /** * blk_mq_request_bypass_insert - Insert a request at dispatch list. * @rq: Pointer to request to be inserted. * @at_head: true if the request should be inserted at the head of the list. * @run_queue: If we should run the hardware queue after inserting the request. * * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ void blk_mq_request_bypass_insert(struct request *rq, bool at_head, bool run_queue) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); if (at_head) list_add(&rq->queuelist, &hctx->dispatch); else list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); if (run_queue) blk_mq_run_hw_queue(hctx, false); } void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list) { struct request *rq; enum hctx_type type = hctx->type; /* * preemption doesn't flush plug list, so it's possible ctx->cpu is * offline now */ list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx); trace_block_rq_insert(rq); } spin_lock(&ctx->lock); list_splice_tail_init(list, &ctx->rq_lists[type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); } static int plug_rq_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); if (rqa->mq_ctx != rqb->mq_ctx) return rqa->mq_ctx > rqb->mq_ctx; if (rqa->mq_hctx != rqb->mq_hctx) return rqa->mq_hctx > rqb->mq_hctx; return blk_rq_pos(rqa) > blk_rq_pos(rqb); } void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(list); if (list_empty(&plug->mq_list)) return; list_splice_init(&plug->mq_list, &list); if (plug->rq_count > 2 && plug->multiple_queues) list_sort(NULL, &list, plug_rq_cmp); plug->rq_count = 0; do { struct list_head rq_list; struct request *rq, *head_rq = list_entry_rq(list.next); struct list_head *pos = &head_rq->queuelist; /* skip first */ struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx; struct blk_mq_ctx *this_ctx = head_rq->mq_ctx; unsigned int depth = 1; list_for_each_continue(pos, &list) { rq = list_entry_rq(pos); BUG_ON(!rq->q); if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) break; depth++; } list_cut_before(&rq_list, &list, pos); trace_block_unplug(head_rq->q, depth, !from_schedule); blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list, from_schedule); } while(!list_empty(&list)); } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { int err; if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; rq->__sector = bio->bi_iter.bi_sector; rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); WARN_ON_ONCE(err); blk_account_io_start(rq); } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie, bool last) { struct request_queue *q = rq->q; struct blk_mq_queue_data bd = { .rq = rq, .last = last, }; blk_qc_t new_cookie; blk_status_t ret; new_cookie = request_to_qc_t(hctx, rq); /* * For OK queue, we are done. For error, caller may kill it. * Any other error (busy), just add it to our list as we * previously would have done. */ ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: blk_mq_update_dispatch_busy(hctx, false); *cookie = new_cookie; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_update_dispatch_busy(hctx, true); __blk_mq_requeue_request(rq); break; default: blk_mq_update_dispatch_busy(hctx, false); *cookie = BLK_QC_T_NONE; break; } return ret; } static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie, bool bypass_insert, bool last) { struct request_queue *q = rq->q; bool run_queue = true; /* * RCU or SRCU read lock is needed before checking quiesced flag. * * When queue is stopped or quiesced, ignore 'bypass_insert' from * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller, * and avoid driver to try to dispatch again. */ if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) { run_queue = false; bypass_insert = false; goto insert; } if (q->elevator && !bypass_insert) goto insert; if (!blk_mq_get_dispatch_budget(q)) goto insert; if (!blk_mq_get_driver_tag(rq)) { blk_mq_put_dispatch_budget(q); goto insert; } return __blk_mq_issue_directly(hctx, rq, cookie, last); insert: if (bypass_insert) return BLK_STS_RESOURCE; blk_mq_sched_insert_request(rq, false, run_queue, false); return BLK_STS_OK; } /** * blk_mq_try_issue_directly - Try to send a request directly to device driver. * @hctx: Pointer of the associated hardware queue. * @rq: Pointer to request to be sent. * @cookie: Request queue cookie. * * If the device has enough resources to accept a new request now, send the * request directly to device driver. Else, insert at hctx->dispatch queue, so * we can try send it another time in the future. Requests inserted at this * queue have higher priority. */ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie) { blk_status_t ret; int srcu_idx; might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); hctx_lock(hctx, &srcu_idx); ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) blk_mq_request_bypass_insert(rq, false, true); else if (ret != BLK_STS_OK) blk_mq_end_request(rq, ret); hctx_unlock(hctx, srcu_idx); } blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) { blk_status_t ret; int srcu_idx; blk_qc_t unused_cookie; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; hctx_lock(hctx, &srcu_idx); ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last); hctx_unlock(hctx, srcu_idx); return ret; } void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; int errors = 0; while (!list_empty(list)) { blk_status_t ret; struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); if (ret != BLK_STS_OK) { errors++; if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { blk_mq_request_bypass_insert(rq, false, list_empty(list)); break; } blk_mq_end_request(rq, ret); } else queued++; } /* * If we didn't flush the entire list, we could have told * the driver there was more coming, but that turned out to * be a lie. */ if ((!list_empty(list) || errors) && hctx->queue->mq_ops->commit_rqs && queued) hctx->queue->mq_ops->commit_rqs(hctx); } static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) { list_add_tail(&rq->queuelist, &plug->mq_list); plug->rq_count++; if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) { struct request *tmp; tmp = list_first_entry(&plug->mq_list, struct request, queuelist); if (tmp->q != rq->q) plug->multiple_queues = true; } } /* * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple * queues. This is important for md arrays to benefit from merging * requests. */ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) { if (plug->multiple_queues) return BLK_MAX_REQUEST_COUNT * 2; return BLK_MAX_REQUEST_COUNT; } /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. * * Builds up a request structure from @q and @bio and send to the device. The * request may not be queued directly to hardware if: * * This request can be merged with another one * * We want to place request at plug queue for possible future merging * * There is an IO scheduler active at this queue * * It will not queue the request if there is an error with the bio, or at the * request creation. * * Returns: Request queue cookie. */ blk_qc_t blk_mq_submit_bio(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = op_is_flush(bio->bi_opf); struct blk_mq_alloc_data data = { .q = q, }; struct request *rq; struct blk_plug *plug; struct request *same_queue_rq = NULL; unsigned int nr_segs; blk_qc_t cookie; blk_status_t ret; blk_queue_bounce(q, &bio); __blk_queue_split(&bio, &nr_segs); if (!bio_integrity_prep(bio)) goto queue_exit; if (!is_flush_fua && !blk_queue_nomerges(q) && blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq)) goto queue_exit; if (blk_mq_sched_bio_merge(q, bio, nr_segs)) goto queue_exit; rq_qos_throttle(q, bio); data.cmd_flags = bio->bi_opf; rq = __blk_mq_alloc_request(&data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); goto queue_exit; } trace_block_getrq(q, bio, bio->bi_opf); rq_qos_track(q, rq, bio); cookie = request_to_qc_t(data.hctx, rq); blk_mq_bio_to_request(rq, bio, nr_segs); ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); blk_mq_free_request(rq); return BLK_QC_T_NONE; } plug = blk_mq_plug(q, bio); if (unlikely(is_flush_fua)) { /* Bypass scheduler for flush requests */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); } else if (plug && (q->nr_hw_queues == 1 || blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) || q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as * we know the driver uses bd->last in a smart fashion. * * Use normal plugging if this disk is slow HDD, as sequential * IO may benefit a lot from plug merging. */ unsigned int request_count = plug->rq_count; struct request *last = NULL; if (!request_count) trace_block_plug(q); else last = list_entry_rq(plug->mq_list.prev); if (request_count >= blk_plug_max_rq_count(plug) || (last && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_flush_plug_list(plug, false); trace_block_plug(q); } blk_add_rq_to_plug(plug, rq); } else if (q->elevator) { /* Insert the request at the IO scheduler queue */ blk_mq_sched_insert_request(rq, false, true, true); } else if (plug && !blk_queue_nomerges(q)) { /* * We do limited plugging. If the bio can be merged, do that. * Otherwise the existing request in the plug list will be * issued. So the plug list will have one request at most * The plug list might get flushed before this. If that happens, * the plug list is empty, and same_queue_rq is invalid. */ if (list_empty(&plug->mq_list)) same_queue_rq = NULL; if (same_queue_rq) { list_del_init(&same_queue_rq->queuelist); plug->rq_count--; } blk_add_rq_to_plug(plug, rq); trace_block_plug(q); if (same_queue_rq) { data.hctx = same_queue_rq->mq_hctx; trace_block_unplug(q, 1, true); blk_mq_try_issue_directly(data.hctx, same_queue_rq, &cookie); } } else if ((q->nr_hw_queues > 1 && is_sync) || !data.hctx->dispatch_busy) { /* * There is no scheduler and we can try to send directly * to the hardware. */ blk_mq_try_issue_directly(data.hctx, rq, &cookie); } else { /* Default case. */ blk_mq_sched_insert_request(rq, false, true, true); } return cookie; queue_exit: blk_queue_exit(q); return BLK_QC_T_NONE; } static size_t order_to_size(unsigned int order) { return (size_t)PAGE_SIZE << order; } /* called before freeing request pool in @tags */ static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct blk_mq_tags *drv_tags = set->tags[hctx_idx]; struct page *page; unsigned long flags; list_for_each_entry(page, &tags->page_list, lru) { unsigned long start = (unsigned long)page_address(page); unsigned long end = start + order_to_size(page->private); int i; for (i = 0; i < set->queue_depth; i++) { struct request *rq = drv_tags->rqs[i]; unsigned long rq_addr = (unsigned long)rq; if (rq_addr >= start && rq_addr < end) { WARN_ON_ONCE(refcount_read(&rq->ref) != 0); cmpxchg(&drv_tags->rqs[i], rq, NULL); } } } /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ spin_lock_irqsave(&drv_tags->lock, flags); spin_unlock_irqrestore(&drv_tags->lock, flags); } void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct page *page; if (tags->rqs && set->ops->exit_request) { int i; for (i = 0; i < tags->nr_tags; i++) { struct request *rq = tags->static_rqs[i]; if (!rq) continue; set->ops->exit_request(set, rq, hctx_idx); tags->static_rqs[i] = NULL; } } blk_mq_clear_rq_mapping(set, tags, hctx_idx); while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); /* * Remove kmemleak object previously allocated in * blk_mq_alloc_rqs(). */ kmemleak_free(page_address(page)); __free_pages(page, page->private); } } void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; blk_mq_free_tags(tags, flags); } struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags, unsigned int flags) { struct blk_mq_tags *tags; int node; node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx); if (node == NUMA_NO_NODE) node = set->numa_node; tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags); if (!tags) return NULL; tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) { blk_mq_free_tags(tags, flags); return NULL; } tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->static_rqs) { kfree(tags->rqs); blk_mq_free_tags(tags, flags); return NULL; } return tags; } static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { int ret; if (set->ops->init_request) { ret = set->ops->init_request(set, rq, hctx_idx, node); if (ret) return ret; } WRITE_ONCE(rq->state, MQ_RQ_IDLE); return 0; } int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth) { unsigned int i, j, entries_per_page, max_order = 4; size_t rq_size, left; int node; node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx); if (node == NUMA_NO_NODE) node = set->numa_node; INIT_LIST_HEAD(&tags->page_list); /* * rq_size is the size of the request plus driver payload, rounded * to the cacheline size */ rq_size = round_up(sizeof(struct request) + set->cmd_size, cache_line_size()); left = rq_size * depth; for (i = 0; i < depth; ) { int this_order = max_order; struct page *page; int to_do; void *p; while (this_order && left < order_to_size(this_order - 1)) this_order--; do { page = alloc_pages_node(node, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; if (!this_order--) break; if (order_to_size(this_order) < rq_size) break; } while (1); if (!page) goto fail; page->private = this_order; list_add_tail(&page->lru, &tags->page_list); p = page_address(page); /* * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, depth - i); left -= to_do * rq_size; for (j = 0; j < to_do; j++) { struct request *rq = p; tags->static_rqs[i] = rq; if (blk_mq_init_request(set, rq, hctx_idx, node)) { tags->static_rqs[i] = NULL; goto fail; } p += rq_size; i++; } } return 0; fail: blk_mq_free_rqs(set, tags, hctx_idx); return -ENOMEM; } struct rq_iter_data { struct blk_mq_hw_ctx *hctx; bool has_rq; }; static bool blk_mq_has_request(struct request *rq, void *data, bool reserved) { struct rq_iter_data *iter_data = data; if (rq->mq_hctx != iter_data->hctx) return true; iter_data->has_rq = true; return false; } static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->sched_tags ? hctx->sched_tags : hctx->tags; struct rq_iter_data data = { .hctx = hctx, }; blk_mq_all_tag_iter(tags, blk_mq_has_request, &data); return data.has_rq; } static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu, struct blk_mq_hw_ctx *hctx) { if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu) return false; if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids) return false; return true; } static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); int ret = 0; if (!cpumask_test_cpu(cpu, hctx->cpumask) || !blk_mq_last_cpu_in_hctx(cpu, hctx)) return 0; /* * Prevent new request from being allocated on the current hctx. * * The smp_mb__after_atomic() Pairs with the implied barrier in * test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is * seen once we return from the tag allocator. */ set_bit(BLK_MQ_S_INACTIVE, &hctx->state); smp_mb__after_atomic(); /* * Try to grab a reference to the queue and wait for any outstanding * requests. If we could not grab a reference the queue has been * frozen and there are no requests. */ if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) { while (blk_mq_hctx_has_requests(hctx)) { /* * The wakeup capable IRQ handler of block device is * not called during suspend. Skip the loop by checking * pm_wakeup_pending to prevent the deadlock and improve * suspend latency. */ if (pm_wakeup_pending()) { clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); ret = -EBUSY; break; } msleep(5); } percpu_ref_put(&hctx->queue->q_usage_counter); } return ret; } static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); if (cpumask_test_cpu(cpu, hctx->cpumask)) clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); return 0; } /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it * gets run. */ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); if (!cpumask_test_cpu(cpu, hctx->cpumask)) return 0; ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { list_splice_init(&ctx->rq_lists[type], &tmp); blk_mq_hctx_clear_pending(hctx, ctx); } spin_unlock(&ctx->lock); if (list_empty(&tmp)) return 0; spin_lock(&hctx->lock); list_splice_tail_init(&tmp, &hctx->dispatch); spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); return 0; } static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { if (!(hctx->flags & BLK_MQ_F_STACKING)) cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } /* * Before freeing hw queue, clearing the flush request reference in * tags->rqs[] for avoiding potential UAF. */ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, unsigned int queue_depth, struct request *flush_rq) { int i; unsigned long flags; /* The hw queue may not be mapped yet */ if (!tags) return; WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0); for (i = 0; i < queue_depth; i++) cmpxchg(&tags->rqs[i], flush_rq, NULL); /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ spin_lock_irqsave(&tags->lock, flags); spin_unlock_irqrestore(&tags->lock, flags); } /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { struct request *flush_rq = hctx->fq->flush_rq; if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], set->queue_depth, flush_rq); if (set->ops->exit_request) set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); blk_mq_remove_cpuhp(hctx); spin_lock(&q->unused_hctx_lock); list_add(&hctx->hctx_list, &q->unused_hctx_list); spin_unlock(&q->unused_hctx_lock); } static void blk_mq_exit_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set, int nr_queue) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; blk_mq_debugfs_unregister_hctx(hctx); blk_mq_exit_hctx(q, set, hctx, i); } } static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set) { int hw_ctx_size = sizeof(struct blk_mq_hw_ctx); BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu), __alignof__(struct blk_mq_hw_ctx)) != sizeof(struct blk_mq_hw_ctx)); if (tag_set->flags & BLK_MQ_F_BLOCKING) hw_ctx_size += sizeof(struct srcu_struct); return hw_ctx_size; } static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) { hctx->queue_num = hctx_idx; if (!(hctx->flags & BLK_MQ_F_STACKING)) cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto unregister_cpu_notifier; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, hctx->numa_node)) goto exit_hctx; return 0; exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); unregister_cpu_notifier: blk_mq_remove_cpuhp(hctx); return -1; } static struct blk_mq_hw_ctx * blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, int node) { struct blk_mq_hw_ctx *hctx; gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node); if (!hctx) goto fail_alloc_hctx; if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node)) goto free_hctx; atomic_set(&hctx->nr_active, 0); atomic_set(&hctx->elevator_queued, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); /* * Allocate space for all possible cpus to avoid allocation at * runtime */ hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *), gfp, node); if (!hctx->ctxs) goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), gfp, node)) goto free_ctxs; hctx->nr_ctx = 0; spin_lock_init(&hctx->dispatch_wait_lock); init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake); INIT_LIST_HEAD(&hctx->dispatch_wait.entry); hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp); if (!hctx->fq) goto free_bitmap; if (hctx->flags & BLK_MQ_F_BLOCKING) init_srcu_struct(hctx->srcu); blk_mq_hctx_kobj_init(hctx); return hctx; free_bitmap: sbitmap_free(&hctx->ctx_map); free_ctxs: kfree(hctx->ctxs); free_cpumask: free_cpumask_var(hctx->cpumask); free_hctx: kfree(hctx); fail_alloc_hctx: return NULL; } static void blk_mq_init_cpu_queues(struct request_queue *q, unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; unsigned int i, j; for_each_possible_cpu(i) { struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; int k; __ctx->cpu = i; spin_lock_init(&__ctx->lock); for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++) INIT_LIST_HEAD(&__ctx->rq_lists[k]); __ctx->queue = q; /* * Set local node, IFF we have more than one hw queue. If * not, we remain on the home node of the device */ for (j = 0; j < set->nr_maps; j++) { hctx = blk_mq_map_queue_type(q, j, i); if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) hctx->numa_node = cpu_to_node(i); } } } static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set, int hctx_idx) { unsigned int flags = set->flags; int ret = 0; set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx, set->queue_depth, set->reserved_tags, flags); if (!set->tags[hctx_idx]) return false; ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx, set->queue_depth); if (!ret) return true; blk_mq_free_rq_map(set->tags[hctx_idx], flags); set->tags[hctx_idx] = NULL; return false; } static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set, unsigned int hctx_idx) { unsigned int flags = set->flags; if (set->tags && set->tags[hctx_idx]) { blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx); blk_mq_free_rq_map(set->tags[hctx_idx], flags); set->tags[hctx_idx] = NULL; } } static void blk_mq_map_swqueue(struct request_queue *q) { unsigned int i, j, hctx_idx; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; hctx->dispatch_from = NULL; } /* * Map software to hardware queues. * * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { ctx = per_cpu_ptr(q->queue_ctx, i); for (j = 0; j < set->nr_maps; j++) { if (!set->map[j].nr_queues) { ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); continue; } hctx_idx = set->map[j].mq_map[i]; /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[hctx_idx] && !__blk_mq_alloc_map_and_request(set, hctx_idx)) { /* * If tags initialization fail for some hctx, * that hctx won't be brought online. In this * case, remap the current ctx to hctx[0] which * is guaranteed to always have tags allocated */ set->map[j].mq_map[i] = 0; } hctx = blk_mq_map_queue_type(q, j, i); ctx->hctxs[j] = hctx; /* * If the CPU is already set in the mask, then we've * mapped this one already. This can happen if * devices share queues across queue maps. */ if (cpumask_test_cpu(i, hctx->cpumask)) continue; cpumask_set_cpu(i, hctx->cpumask); hctx->type = j; ctx->index_hw[hctx->type] = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; /* * If the nr_ctx type overflows, we have exceeded the * amount of sw queues we can support. */ BUG_ON(!hctx->nr_ctx); } for (; j < HCTX_MAX_TYPES; j++) ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); } queue_for_each_hw_ctx(q, hctx, i) { /* * If no software queues are mapped to this hardware queue, * disable it and free the request entries. */ if (!hctx->nr_ctx) { /* Never unmap queue 0. We need it as a * fallback in case of a new remap fails * allocation */ if (i && set->tags[i]) blk_mq_free_map_and_requests(set, i); hctx->tags = NULL; continue; } hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping * over all possibly mapped software queues. */ sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx); /* * Initialize batch roundrobin counts */ hctx->next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } } /* * Caller needs to ensure that we're either frozen/quiesced, or that * the queue isn't live yet. */ static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (shared) hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; else hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; } } static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q); } } static void blk_mq_del_queue_tag_set(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); list_del(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); INIT_LIST_HEAD(&q->tag_set_list); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { mutex_lock(&set->tag_list_lock); /* * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, true); } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } /* All allocations will be freed in release handler of q->mq_kobj */ static int blk_mq_alloc_ctxs(struct request_queue *q) { struct blk_mq_ctxs *ctxs; int cpu; ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL); if (!ctxs) return -ENOMEM; ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!ctxs->queue_ctx) goto fail; for_each_possible_cpu(cpu) { struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu); ctx->ctxs = ctxs; } q->mq_kobj = &ctxs->kobj; q->queue_ctx = ctxs->queue_ctx; return 0; fail: kfree(ctxs); return -ENOMEM; } /* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free * and headache because q->mq_kobj shouldn't have been introduced, * but we can't group ctx/kctx kobj without it. */ void blk_mq_release(struct request_queue *q) { struct blk_mq_hw_ctx *hctx, *next; int i; queue_for_each_hw_ctx(q, hctx, i) WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list)); /* all hctx are in .unused_hctx_list now */ list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) { list_del_init(&hctx->hctx_list); kobject_put(&hctx->kobj); } kfree(q->queue_hw_ctx); /* * release .mq_kobj and sw queue's kobject now because * both share lifetime with request queue. */ blk_mq_sysfs_deinit(q); } struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata) { struct request_queue *uninit_q, *q; uninit_q = blk_alloc_queue(set->numa_node); if (!uninit_q) return ERR_PTR(-ENOMEM); uninit_q->queuedata = queuedata; /* * Initialize the queue without an elevator. device_add_disk() will do * the initialization. */ q = blk_mq_init_allocated_queue(set, uninit_q, false); if (IS_ERR(q)) blk_cleanup_queue(uninit_q); return q; } EXPORT_SYMBOL_GPL(blk_mq_init_queue_data); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) { return blk_mq_init_queue_data(set, NULL); } EXPORT_SYMBOL(blk_mq_init_queue); /* * Helper for setting up a queue with mq ops, given queue depth, and * the passed in mq ops flags. */ struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags) { struct request_queue *q; int ret; memset(set, 0, sizeof(*set)); set->ops = ops; set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = queue_depth; set->numa_node = NUMA_NO_NODE; set->flags = set_flags; ret = blk_mq_alloc_tag_set(set); if (ret) return ERR_PTR(ret); q = blk_mq_init_queue(set); if (IS_ERR(q)) { blk_mq_free_tag_set(set); return q; } return q; } EXPORT_SYMBOL(blk_mq_init_sq_queue); static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) { struct blk_mq_hw_ctx *hctx = NULL, *tmp; /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { if (tmp->numa_node == node) { hctx = tmp; break; } } if (hctx) list_del_init(&hctx->hctx_list); spin_unlock(&q->unused_hctx_lock); if (!hctx) hctx = blk_mq_alloc_hctx(q, set, node); if (!hctx) goto fail; if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) goto free_hctx; return hctx; free_hctx: kobject_put(&hctx->kobj); fail: return NULL; } static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { int i, j, end; struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx; if (q->nr_hw_queues < set->nr_hw_queues) { struct blk_mq_hw_ctx **new_hctxs; new_hctxs = kcalloc_node(set->nr_hw_queues, sizeof(*new_hctxs), GFP_KERNEL, set->numa_node); if (!new_hctxs) return; if (hctxs) memcpy(new_hctxs, hctxs, q->nr_hw_queues * sizeof(*hctxs)); q->queue_hw_ctx = new_hctxs; kfree(hctxs); hctxs = new_hctxs; } /* protect against switching io scheduler */ mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int node; struct blk_mq_hw_ctx *hctx; node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], i); /* * If the hw queue has been mapped to another numa node, * we need to realloc the hctx. If allocation fails, fallback * to use the previous one. */ if (hctxs[i] && (hctxs[i]->numa_node == node)) continue; hctx = blk_mq_alloc_and_init_hctx(set, q, i, node); if (hctx) { if (hctxs[i]) blk_mq_exit_hctx(q, set, hctxs[i], i); hctxs[i] = hctx; } else { if (hctxs[i]) pr_warn("Allocate new hctx on node %d fails,\ fallback to previous one on node %d\n", node, hctxs[i]->numa_node); else break; } } /* * Increasing nr_hw_queues fails. Free the newly allocated * hctxs and keep the previous q->nr_hw_queues. */ if (i != set->nr_hw_queues) { j = q->nr_hw_queues; end = i; } else { j = i; end = q->nr_hw_queues; q->nr_hw_queues = set->nr_hw_queues; } for (; j < end; j++) { struct blk_mq_hw_ctx *hctx = hctxs[j]; if (hctx) { if (hctx->tags) blk_mq_free_map_and_requests(set, j); blk_mq_exit_hctx(q, set, hctx, j); hctxs[j] = NULL; } } mutex_unlock(&q->sysfs_lock); } struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q, bool elevator_init) { /* mark the queue as mq asap */ q->mq_ops = set->ops; q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn, blk_mq_poll_stats_bkt, BLK_MQ_POLL_STATS_BKTS, q); if (!q->poll_cb) goto err_exit; if (blk_mq_alloc_ctxs(q)) goto err_poll; /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->tag_set = set; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; if (set->nr_maps > HCTX_TYPE_POLL && set->map[HCTX_TYPE_POLL].nr_queues) blk_queue_flag_set(QUEUE_FLAG_POLL, q); q->sg_reserved_size = INT_MAX; INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); q->nr_requests = set->queue_depth; /* * Default to classic polling */ q->poll_nsec = BLK_MQ_POLL_CLASSIC; blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); if (elevator_init) elevator_init_mq(q); return q; err_hctxs: kfree(q->queue_hw_ctx); q->nr_hw_queues = 0; blk_mq_sysfs_deinit(q); err_poll: blk_stat_free_callback(q->poll_cb); q->poll_cb = NULL; err_exit: q->mq_ops = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; for (i = 0; i < set->nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_request(set, i)) goto out_unwind; cond_resched(); } return 0; out_unwind: while (--i >= 0) blk_mq_free_map_and_requests(set, i); return -ENOMEM; } /* * Allocate the request maps associated with this tag_set. Note that this * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */ static int blk_mq_alloc_map_and_requests(struct blk_mq_tag_set *set) { unsigned int depth; int err; depth = set->queue_depth; do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); if (!set->queue_depth || err) { pr_err("blk-mq: failed to allocate request map\n"); return -ENOMEM; } if (depth != set->queue_depth) pr_info("blk-mq: reduced tag depth (%u -> %u)\n", depth, set->queue_depth); return 0; } static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the * number of hardware queues. */ if (set->nr_maps == 1) set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues; if (set->ops->map_queues && !is_kdump_kernel()) { int i; /* * transport .map_queues is usually done in the following * way: * * for (queue = 0; queue < set->nr_hw_queues; queue++) { * mask = get_cpu_mask(queue) * for_each_cpu(cpu, mask) * set->map[x].mq_map[cpu] = queue; * } * * When we need to remap, the table has to be cleared for * killing stale mapping since one CPU may not be mapped * to any hw queue. */ for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); return set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set, int cur_nr_hw_queues, int new_nr_hw_queues) { struct blk_mq_tags **new_tags; if (cur_nr_hw_queues >= new_nr_hw_queues) return 0; new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!new_tags) return -ENOMEM; if (set->tags) memcpy(new_tags, set->tags, cur_nr_hw_queues * sizeof(*set->tags)); kfree(set->tags); set->tags = new_tags; set->nr_hw_queues = new_nr_hw_queues; return 0; } /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the * requested depth down, if it's too large. In that case, the set * value will be stored in set->queue_depth. */ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) { int i, ret; BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS); if (!set->nr_hw_queues) return -EINVAL; if (!set->queue_depth) return -EINVAL; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) return -EINVAL; if (!set->ops->queue_rq) return -EINVAL; if (!set->ops->get_budget ^ !set->ops->put_budget) return -EINVAL; if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); set->queue_depth = BLK_MQ_MAX_DEPTH; } if (!set->nr_maps) set->nr_maps = 1; else if (set->nr_maps > HCTX_MAX_TYPES) return -EINVAL; /* * If a crashdump is active, then we are potentially in a very * memory constrained environment. Limit us to 1 queue and * 64 tags to prevent using too much memory. */ if (is_kdump_kernel()) { set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = min(64U, set->queue_depth); } /* * There is no use for more h/w queues than cpus if we just have * a single map */ if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0) return -ENOMEM; ret = -ENOMEM; for (i = 0; i < set->nr_maps; i++) { set->map[i].mq_map = kcalloc_node(nr_cpu_ids, sizeof(set->map[i].mq_map[0]), GFP_KERNEL, set->numa_node); if (!set->map[i].mq_map) goto out_free_mq_map; set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues; } ret = blk_mq_update_queue_map(set); if (ret) goto out_free_mq_map; ret = blk_mq_alloc_map_and_requests(set); if (ret) goto out_free_mq_map; if (blk_mq_is_sbitmap_shared(set->flags)) { atomic_set(&set->active_queues_shared_sbitmap, 0); if (blk_mq_init_shared_sbitmap(set, set->flags)) { ret = -ENOMEM; goto out_free_mq_rq_maps; } } mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; out_free_mq_rq_maps: for (i = 0; i < set->nr_hw_queues; i++) blk_mq_free_map_and_requests(set, i); out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); set->map[i].mq_map = NULL; } kfree(set->tags); set->tags = NULL; return ret; } EXPORT_SYMBOL(blk_mq_alloc_tag_set); void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; for (i = 0; i < set->nr_hw_queues; i++) blk_mq_free_map_and_requests(set, i); if (blk_mq_is_sbitmap_shared(set->flags)) blk_mq_exit_shared_sbitmap(set); for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; } kfree(set->tags); set->tags = NULL; } EXPORT_SYMBOL(blk_mq_free_tag_set); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) { struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_hw_ctx *hctx; int i, ret; if (!set) return -EINVAL; if (q->nr_requests == nr) return 0; blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); ret = 0; queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->tags) continue; /* * If we're using an MQ scheduler, just update the scheduler * queue depth. This is similar to what the old code would do. */ if (!hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); if (!ret && blk_mq_is_sbitmap_shared(set->flags)) blk_mq_tag_resize_shared_sbitmap(set, nr); } else { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); } if (ret) break; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(hctx); } if (!ret) q->nr_requests = nr; blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); return ret; } /* * request_queue and elevator_type pair. * It is just used by __blk_mq_update_nr_hw_queues to cache * the elevator_type associated with a request_queue. */ struct blk_mq_qe_pair { struct list_head node; struct request_queue *q; struct elevator_type *type; }; /* * Cache the elevator_type in qe pair list and switch the * io scheduler to 'none' */ static bool blk_mq_elv_switch_none(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; if (!q->elevator) return true; qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!qe) return false; INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; list_add(&qe->node, head); mutex_lock(&q->sysfs_lock); /* * After elevator_switch_mq, the previous elevator_queue will be * released by elevator_release. The reference of the io scheduler * module get by elevator_get will also be put. So we need to get * a reference of the io scheduler module here to prevent it to be * removed. */ __module_get(qe->type->elevator_owner); elevator_switch_mq(q, NULL); mutex_unlock(&q->sysfs_lock); return true; } static void blk_mq_elv_switch_back(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; struct elevator_type *t = NULL; list_for_each_entry(qe, head, node) if (qe->q == q) { t = qe->type; break; } if (!t) return; list_del(&qe->node); kfree(qe); mutex_lock(&q->sysfs_lock); elevator_switch_mq(q, t); mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; LIST_HEAD(head); int prev_nr_hw_queues; lockdep_assert_held(&set->tag_list_lock); if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; if (nr_hw_queues < 1) return; if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. */ list_for_each_entry(q, &set->tag_list, tag_set_list) if (!blk_mq_elv_switch_none(&head, q)) goto switch_back; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); blk_mq_sysfs_unregister(q); } prev_nr_hw_queues = set->nr_hw_queues; if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) < 0) goto reregister; set->nr_hw_queues = nr_hw_queues; fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n", nr_hw_queues, prev_nr_hw_queues); set->nr_hw_queues = prev_nr_hw_queues; blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); goto fallback; } blk_mq_map_swqueue(q); } reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register(q); blk_mq_debugfs_register_hctxs(q); } switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); } void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { mutex_lock(&set->tag_list_lock); __blk_mq_update_nr_hw_queues(set, nr_hw_queues); mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); /* Enable polling stats and return whether they were already enabled. */ static bool blk_poll_stats_enable(struct request_queue *q) { if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) || blk_queue_flag_test_and_set(QUEUE_FLAG_POLL_STATS, q)) return true; blk_stat_add_callback(q, q->poll_cb); return false; } static void blk_mq_poll_stats_start(struct request_queue *q) { /* * We don't arm the callback if polling stats are not enabled or the * callback is already active. */ if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) || blk_stat_is_active(q->poll_cb)) return; blk_stat_activate_msecs(q->poll_cb, 100); } static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb) { struct request_queue *q = cb->data; int bucket; for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) { if (cb->stat[bucket].nr_samples) q->poll_stat[bucket] = cb->stat[bucket]; } } static unsigned long blk_mq_poll_nsecs(struct request_queue *q, struct request *rq) { unsigned long ret = 0; int bucket; /* * If stats collection isn't on, don't sleep but turn it on for * future users */ if (!blk_poll_stats_enable(q)) return 0; /* * As an optimistic guess, use half of the mean service time * for this type of request. We can (and should) make this smarter. * For instance, if the completion latencies are tight, we can * get closer than just half the mean. This is especially * important on devices where the completion latencies are longer * than ~10 usec. We do use the stats for the relevant IO size * if available which does lead to better estimates. */ bucket = blk_mq_poll_stats_bkt(rq); if (bucket < 0) return ret; if (q->poll_stat[bucket].nr_samples) ret = (q->poll_stat[bucket].mean + 1) / 2; return ret; } static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, struct request *rq) { struct hrtimer_sleeper hs; enum hrtimer_mode mode; unsigned int nsecs; ktime_t kt; if (rq->rq_flags & RQF_MQ_POLL_SLEPT) return false; /* * If we get here, hybrid polling is enabled. Hence poll_nsec can be: * * 0: use half of prev avg * >0: use this specific value */ if (q->poll_nsec > 0) nsecs = q->poll_nsec; else nsecs = blk_mq_poll_nsecs(q, rq); if (!nsecs) return false; rq->rq_flags |= RQF_MQ_POLL_SLEPT; /* * This will be replaced with the stats tracking code, using * 'avg_completion_time / 2' as the pre-sleep target. */ kt = nsecs; mode = HRTIMER_MODE_REL; hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode); hrtimer_set_expires(&hs.timer, kt); do { if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE) break; set_current_state(TASK_UNINTERRUPTIBLE); hrtimer_sleeper_start_expires(&hs, mode); if (hs.task) io_schedule(); hrtimer_cancel(&hs.timer); mode = HRTIMER_MODE_ABS; } while (hs.task && !signal_pending(current)); __set_current_state(TASK_RUNNING); destroy_hrtimer_on_stack(&hs.timer); return true; } static bool blk_mq_poll_hybrid(struct request_queue *q, struct blk_mq_hw_ctx *hctx, blk_qc_t cookie) { struct request *rq; if (q->poll_nsec == BLK_MQ_POLL_CLASSIC) return false; if (!blk_qc_t_is_internal(cookie)) rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie)); else { rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie)); /* * With scheduling, if the request has completed, we'll * get a NULL return here, as we clear the sched tag when * that happens. The request still remains valid, like always, * so we should be safe with just the NULL check. */ if (!rq) return false; } return blk_mq_poll_hybrid_sleep(q, rq); } /** * blk_poll - poll for IO completions * @q: the queue * @cookie: cookie passed back at IO submission time * @spin: whether to spin for completions * * Description: * Poll for completions on the passed in queue. Returns number of * completed entries found. If @spin is true, then blk_poll will continue * looping until at least one completion is found, unless the task is * otherwise marked running (or we need to reschedule). */ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) { struct blk_mq_hw_ctx *hctx; long state; if (!blk_qc_t_valid(cookie) || !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return 0; if (current->plug) blk_flush_plug_list(current->plug, false); hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; /* * If we sleep, have the caller restart the poll loop to reset * the state. Like for the other success return cases, the * caller is responsible for checking if the IO completed. If * the IO isn't complete, we'll get called again and will go * straight to the busy poll loop. */ if (blk_mq_poll_hybrid(q, hctx, cookie)) return 1; hctx->poll_considered++; state = current->state; do { int ret; hctx->poll_invoked++; ret = q->mq_ops->poll(hctx); if (ret > 0) { hctx->poll_success++; __set_current_state(TASK_RUNNING); return ret; } if (signal_pending_state(state, current)) __set_current_state(TASK_RUNNING); if (current->state == TASK_RUNNING) return 1; if (ret < 0 || !spin) break; cpu_relax(); } while (!need_resched()); __set_current_state(TASK_RUNNING); return 0; } EXPORT_SYMBOL_GPL(blk_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { return rq->mq_ctx->cpu; } EXPORT_SYMBOL(blk_mq_rq_cpu); static int __init blk_mq_init(void) { int i; for_each_possible_cpu(i) INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, "block/softirq:dead", NULL, blk_softirq_cpu_dead); cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", blk_mq_hctx_notify_online, blk_mq_hctx_notify_offline); return 0; } subsys_initcall(blk_mq_init); |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the AF_INET socket handler. * * Version: @(#)sock.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche <flla@stud.uni-sb.de> * * Fixes: * Alan Cox : Volatiles in skbuff pointers. See * skbuff comments. May be overdone, * better to prove they can be removed * than the reverse. * Alan Cox : Added a zapped field for tcp to note * a socket is reset and must stay shut up * Alan Cox : New fields for options * Pauline Middelink : identd support * Alan Cox : Eliminate low level recv/recvfrom * David S. Miller : New socket lookup architecture. * Steve Whitehouse: Default routines for sock_ops * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made * protinfo be just a void pointer, as the * protocol specific parts were moved to * respective headers and ipv4/v6, etc now * use private slabcaches for its socks * Pedro Hortas : New flags field for socket options */ #ifndef _SOCK_H #define _SOCK_H #include <linux/hardirq.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/timer.h> #include <linux/cache.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* struct sk_buff */ #include <linux/mm.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/static_key.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> #include <linux/rbtree.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of * the other protocols. */ /* Define this to get the SOCK_DBG debugging facility. */ #define SOCK_DEBUGGING #ifdef SOCK_DEBUGGING #define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ printk(KERN_DEBUG msg); } while (0) #else /* Validate arguments and do nothing */ static inline __printf(2, 3) void SOCK_DEBUG(const struct sock *sk, const char *msg, ...) { } #endif /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. */ typedef struct { spinlock_t slock; int owned; wait_queue_head_t wq; /* * We express the mutex-alike socket_lock semantics * to the lock validator by explicitly managing * the slock as a lock variant (in addition to * the slock itself): */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } socket_lock_t; struct sock; struct proto; struct net; typedef __u32 __bitwise __portpair; typedef __u64 __bitwise __addrpair; /** * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @skc_v6_daddr: IPV6 destination address * @skc_v6_rcv_saddr: IPV6 source address * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_listener: connection request listener socket (aka rsk_listener) * [union with @skc_flags] * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) * [union with @skc_incoming_cpu] * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { union { __addrpair skc_addrpair; struct { __be32 skc_daddr; __be32 skc_rcv_saddr; }; }; union { unsigned int skc_hash; __u16 skc_u16hashes[2]; }; /* skc_dport && skc_num must be grouped as well */ union { __portpair skc_portpair; struct { __be16 skc_dport; __u16 skc_num; }; }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse:4; unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; struct hlist_node skc_portaddr_node; }; struct proto *skc_prot; possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; struct in6_addr skc_v6_rcv_saddr; #endif atomic64_t skc_cookie; /* following fields are padding to force * offset(struct sock, sk_refcnt) == 128 on 64bit arches * assuming IPV6 is enabled. We use this padding differently * for different kind of 'sockets' */ union { unsigned long skc_flags; struct sock *skc_listener; /* request_sock */ struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() */ /* private: */ int skc_dontcopy_begin[0]; /* public: */ union { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; #ifdef CONFIG_XPS unsigned short skc_rx_queue_mapping; #endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; refcount_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; union { u32 skc_rxhash; u32 skc_window_clamp; u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; struct bpf_local_storage; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags * @sk_write_queue: Packet sending queue * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes * @__sk_flags_offset: empty field used to determine location of bitfield * @sk_padding: unused element for alignment * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) * @sk_route_forced_caps: static, forced route capabilities * (set in tcp_init_sock()) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, * IPV6_ADDRFORM for instance) * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' * @sk_drops: raw/udp drops counter * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING socket options * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @sk_owner: reference to the real owner of the socket that calls * sock_lock_init_class_and_name(). */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; #define sk_node __sk_common.skc_node #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping #ifdef CONFIG_XPS #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_portpair __sk_common.skc_portpair #define sk_num __sk_common.skc_num #define sk_dport __sk_common.skc_dport #define sk_addrpair __sk_common.skc_addrpair #define sk_daddr __sk_common.skc_daddr #define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; struct sk_buff *sk_rx_skb_cache; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. * Note : rmem_alloc is in this structure to fill a hole * on 64bit arches, not because its logically part of * backlog. */ struct { atomic_t rmem_alloc; int len; struct sk_buff *head; struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; /* ===== mostly read cache line ===== */ unsigned int sk_napi_id; #endif int sk_rcvbuf; int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; /* private: */ struct socket_wq *sk_wq_raw; /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry __rcu *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; /* ===== cache line for TX ===== */ int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; union { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; struct sk_buff *sk_tx_skb_cache; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; __u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ long sk_sndtimeo; struct timer_list sk_timer; __u32 sk_priority; __u32 sk_mark; unsigned long sk_pacing_rate; /* bytes per second */ unsigned long sk_max_pacing_rate; struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; __u32 sk_txhash; /* * Because of non atomicity rules, all * changes are protected by socket lock. */ u8 sk_padding : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, sk_userlocks : 4; u8 sk_pacing_shift; u16 sk_type; u16 sk_protocol; u16 sk_gso_max_segs; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; spinlock_t sk_peer_lock; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); #endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) struct module *sk_owner; #endif }; enum sk_pacing { SK_PACING_NONE = 0, SK_PACING_NEEDED = 1, SK_PACING_FQ = 2, }; /* flag bits in sk_user_data * * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might * not be suitable for copying when cloning the socket. For instance, * it can point to a reference counted object. sk_user_data bottom * bit is set if pointer must not be copied. * * - SK_USER_DATA_BPF: Mark whether sk_user_data field is * managed/owned by a BPF reuseport array. This bit should be set * when sk_user_data's sk is added to the bpf's reuseport_array. * * - SK_USER_DATA_PSOCK: Mark whether pointer stored in * sk_user_data points to psock type. This bit should be set * when sk_user_data is assigned to a psock object. */ #define SK_USER_DATA_NOCOPY 1UL #define SK_USER_DATA_BPF 2UL #define SK_USER_DATA_PSOCK 4UL #define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\ SK_USER_DATA_PSOCK) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied * @sk: socket */ static inline bool sk_user_data_is_nocopy(const struct sock *sk) { return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); } #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) /** * __rcu_dereference_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits */ static inline void * __rcu_dereference_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } #define rcu_dereference_sk_user_data(sk) \ __rcu_dereference_sk_user_data_with_flags(sk, 0) #define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ ({ \ uintptr_t __tmp1 = (uintptr_t)(ptr), \ __tmp2 = (uintptr_t)(flags); \ WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \ WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), \ __tmp1 | __tmp2); \ }) #define rcu_assign_sk_user_data(sk, ptr) \ __rcu_assign_sk_user_data_with_flags(sk, ptr, 0) /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE * on a socket means that the socket will reuse everybody else's port * without looking at the other's sk_reuse value. */ #define SK_NO_REUSE 0 #define SK_CAN_REUSE 1 #define SK_FORCE_REUSE 2 int sk_set_peek_off(struct sock *sk, int val); static inline int sk_peek_offset(struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); } return 0; } static inline void sk_peek_offset_bwd(struct sock *sk, int val) { s32 off = READ_ONCE(sk->sk_peek_off); if (unlikely(off >= 0)) { off = max_t(s32, off - val, 0); WRITE_ONCE(sk->sk_peek_off, off); } } static inline void sk_peek_offset_fwd(struct sock *sk, int val) { sk_peek_offset_bwd(sk, -val); } /* * Hashed lists helper routines */ static inline struct sock *sk_entry(const struct hlist_node *node) { return hlist_entry(node, struct sock, sk_node); } static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); } static inline struct sock *sk_head(const struct hlist_head *head) { return hlist_empty(head) ? NULL : __sk_head(head); } static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); } static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); } static inline struct sock *sk_next(const struct sock *sk) { return hlist_entry_safe(sk->sk_node.next, struct sock, sk_node); } static inline struct sock *sk_nulls_next(const struct sock *sk) { return (!is_a_nulls(sk->sk_nulls_node.next)) ? hlist_nulls_entry(sk->sk_nulls_node.next, struct sock, sk_nulls_node) : NULL; } static inline bool sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } static inline bool sk_hashed(const struct sock *sk) { return !sk_unhashed(sk); } static inline void sk_node_init(struct hlist_node *node) { node->pprev = NULL; } static inline void sk_nulls_node_init(struct hlist_nulls_node *node) { node->pprev = NULL; } static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); } /* NB: equivalent to hlist_del_init_rcu */ static inline bool __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { __sk_del_node(sk); sk_node_init(&sk->sk_node); return true; } return false; } /* Grab socket reference count. This operation is valid only when sk is ALREADY grabbed f.e. it is found in hash table or a list and the lookup is made under lock preventing hash table modifications. */ static __always_inline void sock_hold(struct sock *sk) { refcount_inc(&sk->sk_refcnt); } /* Ungrab socket in the context, which assumes that socket refcnt cannot hit zero, f.e. it is true in context of any socketcall. */ static __always_inline void __sock_put(struct sock *sk) { refcount_dec(&sk->sk_refcnt); } static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk) { if (sk_hashed(sk)) { hlist_nulls_del_init_rcu(&sk->sk_nulls_node); return true; } return false; } static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } static inline bool sk_nulls_replace_node_init_rcu(struct sock *old, struct sock *new) { if (sk_hashed(old)) { hlist_nulls_replace_init_rcu(&old->sk_nulls_node, &new->sk_nulls_node); __sock_put(old); return true; } return false; } static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); } static inline void sk_add_node(struct sock *sk, struct hlist_head *list) { sock_hold(sk); __sk_add_node(sk, list); } static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&sk->sk_node, list); else hlist_add_head_rcu(&sk->sk_node, list); } static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); hlist_add_tail_rcu(&sk->sk_node, list); } static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); __sk_nulls_add_node_rcu(sk, list); } static inline void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); } static inline void sk_add_bind_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_bind_node, list); } #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) #define sk_for_each_from(__sk) \ hlist_for_each_entry_from(__sk, sk_node) #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) #define sk_for_each_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) #define sk_for_each_bound_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @offset: offset of hlist_node within the struct. * */ #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) static inline struct user_namespace *sk_user_ns(struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from * userspace. */ return sk->sk_socket->file->f_cred->user_ns; } /* Sock flags */ enum sock_flags { SOCK_DEAD, SOCK_DONE, SOCK_URGINLINE, SOCK_KEEPOPEN, SOCK_LINGER, SOCK_DESTROY, SOCK_BROADCAST, SOCK_TIMESTAMP, SOCK_ZAPPED, SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG, /* %SO_DEBUG setting */ SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ SOCK_RXQ_OVFL, SOCK_ZEROCOPY, /* buffers from userspace */ SOCK_WIFI_STATUS, /* push wifi status to userspace */ SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS. * Will use last 4 bytes of packet sent from * user-space instead. */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) { nsk->sk_flags = osk->sk_flags; } static inline void sock_set_flag(struct sock *sk, enum sock_flags flag) { __set_bit(flag, &sk->sk_flags); } static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) { __clear_bit(flag, &sk->sk_flags); } static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, int valbool) { if (valbool) sock_set_flag(sk, bit); else sock_reset_flag(sk, bit); } static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); } #ifdef CONFIG_NET DECLARE_STATIC_KEY_FALSE(memalloc_socks_key); static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) { return 0; } static inline void __receive_sock(struct file *file) { } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) { return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1); } static inline void sk_acceptq_added(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); } /* * Compute minimal free write space needed to queue new packets. */ static inline int sk_stream_min_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); } static inline void sk_wmem_queued_add(struct sock *sk, int val) { WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ skb_dst_force(skb); if (!sk->sk_backlog.tail) WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } /* * Take into account size of receive queue and backlog queue * Do not take into account this skb truesize, * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); return qsize > limit; } /* The per-socket spinlock must be held here. */ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, unsigned int limit) { if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) return -ENOMEM; __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; } int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); return sk->sk_backlog_rcv(sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) { int cpu = raw_smp_processor_id(); if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu)) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } static inline void sock_rps_record_flow_hash(__u32 hash) { #ifdef CONFIG_RPS struct rps_sock_flow_table *sock_flow_table; rcu_read_lock(); sock_flow_table = rcu_dereference(rps_sock_flow_table); rps_record_sock_flow(sock_flow_table, hash); rcu_read_unlock(); #endif } static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS if (static_branch_unlikely(&rfs_needed)) { /* Reading sk->sk_rxhash might incur an expensive cache line * miss. * * TCP_ESTABLISHED does cover almost all states where RFS * might be useful, and is cheaper [1] than testing : * IPv4: inet_sk(sk)->inet_daddr * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ if (sk->sk_state == TCP_ESTABLISHED) { /* This READ_ONCE() is paired with the WRITE_ONCE() * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). */ sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); } } #endif } static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in sock_rps_record_flow(). */ if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS /* Paired with READ_ONCE() in sock_rps_record_flow() */ WRITE_ONCE(sk->sk_rxhash, 0); #endif } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ *(__timeo) = wait_woken(__wait, \ TASK_INTERRUPTIBLE, \ *(__timeo)); \ } \ sched_annotate_sleep(); \ lock_sock(__sk); \ __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) int sk_stream_wait_connect(struct sock *sk, long *timeo_p); int sk_stream_wait_memory(struct sock *sk, long *timeo_p); void sk_stream_wait_close(struct sock *sk, long timeo_p); int sk_stream_error(struct sock *sk, int flags, int err); void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); void __sk_flush_backlog(struct sock *sk); static inline bool sk_flush_backlog(struct sock *sk) { if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { __sk_flush_backlog(sk); return true; } return false; } int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; struct inet_hashinfo; struct raw_hashinfo; struct smc_hashinfo; struct module; /* * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes * un-modified. Special care is taken when initializing object to zero. */ static inline void sk_prot_clear_nulls(struct sock *sk, int size) { if (offsetof(struct sock, sk_node.next) != 0) memset(sk, 0, offsetof(struct sock, sk_node.next)); memset(&sk->sk_node.pprev, 0, size - offsetof(struct sock, sk_node.pprev)); } /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); struct sock * (*accept)(struct sock *sk, int flags, int *err, bool kern); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); bool (*bpf_bypass_getsockopt)(int level, int optname); void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; u32 sysctl_wmem_offset; u32 sysctl_rmem_offset; int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; struct udp_table *udp_table; struct raw_hashinfo *raw_hash; struct smc_hashinfo *smc_hash; } h; struct module *owner; char name[32]; struct list_head node; #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); } __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); int sock_load_diag_module(int family, int protocol); #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) { atomic_inc(&sk->sk_prot->socks); } static inline void sk_refcnt_debug_dec(struct sock *sk) { atomic_dec(&sk->sk_prot->socks); printk(KERN_DEBUG "%s socket %p released, %d are still alive\n", sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks)); } static inline void sk_refcnt_debug_release(const struct sock *sk) { if (refcount_read(&sk->sk_refcnt) != 1) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", sk->sk_prot->name, sk, refcount_read(&sk->sk_refcnt)); } #else /* SOCK_REFCNT_DEBUG */ #define sk_refcnt_debug_inc(sk) do { } while (0) #define sk_refcnt_debug_dec(sk) do { } while (0) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? sk->sk_prot->stream_memory_free(sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) { return __sk_stream_memory_free(sk, 0); } static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && __sk_stream_memory_free(sk, wake); } static inline bool sk_stream_is_writeable(const struct sock *sk) { return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, struct cgroup *ancestor) { #ifdef CONFIG_SOCK_CGROUP_DATA return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), ancestor); #else return -ENOTSUPP; #endif } static inline bool sk_has_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure != NULL; } static inline bool sk_under_global_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure && !!READ_ONCE(*sk->sk_prot->memory_pressure); } static inline bool sk_under_memory_pressure(const struct sock *sk) { if (!sk->sk_prot->memory_pressure) return false; if (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return !!READ_ONCE(*sk->sk_prot->memory_pressure); } static inline long sk_memory_allocated(const struct sock *sk) { return atomic_long_read(sk->sk_prot->memory_allocated); } static inline long sk_memory_allocated_add(struct sock *sk, int amt) { return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { atomic_long_sub(amt, sk->sk_prot->memory_allocated); } static inline void sk_sockets_allocated_dec(struct sock *sk) { percpu_counter_dec(sk->sk_prot->sockets_allocated); } static inline void sk_sockets_allocated_inc(struct sock *sk) { percpu_counter_inc(sk->sk_prot->sockets_allocated); } static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int proto_sockets_allocated_sum_positive(struct proto *prot) { return percpu_counter_sum_positive(prot->sockets_allocated); } static inline long proto_memory_allocated(struct proto *prot) { return atomic_long_read(prot->memory_allocated); } static inline bool proto_memory_pressure(struct proto *prot) { if (!prot->memory_pressure) return false; return !!READ_ONCE(*prot->memory_pressure); } #ifdef CONFIG_PROC_FS /* Called with local bh disabled */ void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc) { } #endif /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); return sk->sk_prot->hash(sk); } /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) /* Sockets 0-1023 can't be bound to unless you are superuser */ #define PROT_SOCK 1024 #define SHUTDOWN_MASK 3 #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 #define SOCK_SNDBUF_LOCK 1 #define SOCK_RCVBUF_LOCK 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 struct socket_alloc { struct socket socket; struct inode vfs_inode; }; static inline struct socket *SOCKET_I(struct inode *inode) { return &container_of(inode, struct socket_alloc, vfs_inode)->socket; } static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } /* * Functions for memory accounting */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); /* We used to have PAGE_SIZE here, but systems with 64KB pages * do not necessarily have 16x time more memory than 4KB ones. */ #define SK_MEM_QUANTUM 4096 #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 /* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]); #if PAGE_SIZE > SK_MEM_QUANTUM val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; #elif PAGE_SIZE < SK_MEM_QUANTUM val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; #endif return val; } static inline int sk_mem_pages(int amt) { return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; } static inline bool sk_has_account(struct sock *sk) { /* return true if protocol supports memory accounting */ return !!sk->sk_prot->memory_allocated; } static inline bool sk_wmem_schedule(struct sock *sk, int size) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool __sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || pfmemalloc; } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline void sk_mem_reclaim(struct sock *sk) { if (!sk_has_account(sk)) return; if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) __sk_mem_reclaim(sk, sk->sk_forward_alloc); } static inline void sk_mem_reclaim_partial(struct sock *sk) { if (!sk_has_account(sk)) return; if (sk->sk_forward_alloc > SK_MEM_QUANTUM) __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1); } static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk->sk_forward_alloc -= size; } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; /* Avoid a possible overflow. * TCP send queues can make this happen, if sk_mem_reclaim() * is not called and more than 2 GBytes are released at once. * * If we reach 2 MBytes, reclaim 1 MBytes right now, there is * no need to hold that much forward allocation anyway. */ if (unlikely(sk->sk_forward_alloc >= 1 << 21)) __sk_mem_reclaim(sk, 1 << 20); } DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && !sk->sk_tx_skb_cache && !skb_cloned(skb)) { skb_ext_reset(skb); skb_zcopy_clear(skb, true); sk->sk_tx_skb_cache = skb; return; } __kfree_skb(skb); } static inline void sock_release_ownership(struct sock *sk) { if (sk->sk_lock.owned) { sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } } #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) static inline void sk_owner_set(struct sock *sk, struct module *owner) { __module_get(owner); sk->sk_owner = owner; } static inline void sk_owner_clear(struct sock *sk) { sk->sk_owner = NULL; } static inline void sk_owner_put(struct sock *sk) { module_put(sk->sk_owner); } #else static inline void sk_owner_set(struct sock *sk, struct module *owner) { } static inline void sk_owner_clear(struct sock *sk) { } static inline void sk_owner_put(struct sock *sk) { } #endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. * * Mark both the sk_lock and the sk_lock.slock as a * per-address-family lock class. */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) #ifdef CONFIG_LOCKDEP static inline bool lockdep_sock_is_held(const struct sock *sk) { return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } #endif void lock_sock_nested(struct sock *sk, int subclass); static inline void lock_sock(struct sock *sk) { lock_sock_nested(sk, 0); } void __release_sock(struct sock *sk); void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock)) #define bh_lock_sock_nested(__sk) \ spin_lock_nested(&((__sk)->sk_lock.slock), \ SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) bool lock_sock_fast(struct sock *sk); /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket * @slow: slow mode * * fast unlock socket for user context. * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) { if (slow) release_sock(sk); else spin_unlock_bh(&sk->sk_lock.slock); } /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming * packets, so that we won't get any new data or any * packets that change the state of the socket. * * While locked, BH processing will add new packets to * the backlog queue. This queue is processed by the * owner of the socket lock right before it is released. * * Since ~2.3.5 it is also exclusive sleep lock serializing * accesses from user process context. */ static inline void sock_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks); #endif } static inline void sock_not_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); #endif } static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); return sk->sk_lock.owned; } static inline bool sock_owned_by_user_nocheck(const struct sock *sk) { return sk->sk_lock.owned; } /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); void sk_free_unlock_clone(struct sock *sk); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); #else #define sock_edemux sock_efree #endif int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); struct sockcm_cookie { u64 transmit_time; u32 mark; u16 tsflags; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; } int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); /* * Functions to fill in entries in struct proto_ops when a protocol * uses the inet style. */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); void sk_common_release(struct sock *sk); /* * Default socket callbacks and setup code */ /* Initialise core socket variables using an explicit uid. */ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); /* Initialise core socket variables. * Assumes struct socket *sock is embedded in a struct socket_alloc. */ void sock_init_data(struct socket *sock, struct sock *sk); /* * Socket reference counting postulates. * * * Each user of socket SHOULD hold a reference count. * * Each access point to socket (an hash table bucket, reference from a list, * running timer, skb in flight MUST hold a reference count. * * When reference count hits 0, it means it will never increase back. * * When reference count hits 0, it means that no references from * outside exist to this socket and current process on current CPU * is last user and may/should destroy this socket. * * sk_free is called from any context: process, BH, IRQ. When * it is called, socket has no references from outside -> sk_free * may release descendant resources allocated by the socket, but * to the time when it is called, socket is NOT referenced by any * hash tables, lists etc. * * Packets, delivered from outside (from network or from another process) * and enqueued on receive/error queues SHOULD NOT grab reference count, * when they sit in queue. Otherwise, packets will leak to hole, when * socket is looked up by one cpu and unhasing is made by another CPU. * It is true for udp/raw, netlink (leak to receive and error queues), tcp * (leak to backlog). Packet socket does all the processing inside * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets * use separate SMP lock, so that they are prone too. */ /* Ungrab socket and destroy it, if it was the last reference. */ static inline void sock_put(struct sock *sk) { if (refcount_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } static inline int sk_tx_queue_get(const struct sock *sk) { if (sk) { /* Paired with WRITE_ONCE() in sk_tx_queue_clear() * and sk_tx_queue_set(). */ int val = READ_ONCE(sk->sk_tx_queue_mapping); if (val != NO_QUEUE_MAPPING) return val; } return -1; } static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_XPS if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING)) return; sk->sk_rx_queue_mapping = rx_queue; } #endif } static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_XPS sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; #endif } #ifdef CONFIG_XPS static inline int sk_rx_queue_get(const struct sock *sk) { if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) return sk->sk_rx_queue_mapping; return -1; } #endif static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk->sk_socket = sock; } static inline wait_queue_head_t *sk_sleep(struct sock *sk) { BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, * we do not release it in this function, because protocol * probably wants some additional cleanups or even continuing * to work with this socket (TCP). */ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } kuid_t sock_i_uid(struct sock *sk); unsigned long __sock_i_ino(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); } static inline u32 net_tx_rndhash(void) { u32 v = prandom_u32(); return v ?: 1; } static inline void sk_set_txhash(struct sock *sk) { /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } static inline bool sk_rethink_txhash(struct sock *sk) { if (sk->sk_txhash) { sk_set_txhash(sk); return true; } return false; } static inline struct dst_entry * __sk_dst_get(struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, lockdep_sock_is_held(sk)); } static inline struct dst_entry * sk_dst_get(struct sock *sk) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); if (dst && !atomic_inc_not_zero(&dst->__refcnt)) dst = NULL; rcu_read_unlock(); return dst; } static inline void __dst_negative_advice(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->ops->negative_advice) dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) { sk_rethink_txhash(sk); __dst_negative_advice(sk); } static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void __sk_dst_reset(struct sock *sk) { __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { sk_dst_set(sk, NULL); } struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { if (!READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); } } bool sk_mc_loop(struct sock *sk); static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst); static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) { sk->sk_route_nocaps |= flags; sk->sk_route_caps &= ~flags; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; } static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, int copy) { int err, offset = skb->len; err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy), copy, offset); if (err) __skb_trim(skb, offset); return err; } static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from, struct sk_buff *skb, struct page *page, int off, int copy) { int err; err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off, copy, skb->len); if (err) return err; skb->len += copy; skb->data_len += copy; skb->truesize += copy; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } /** * sk_wmem_alloc_get - returns write allocations * @sk: socket * * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) - 1; } /** * sk_rmem_alloc_get - returns read allocations * @sk: socket * * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { return atomic_read(&sk->sk_rmem_alloc); } /** * sk_has_allocations - check if allocations are outstanding * @sk: socket * * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); } /** * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths:: * * CPU1 CPU2 * sys_select receive packet * ... ... * __add_wait_queue update tp->rcv_nxt * ... ... * tp->rcv_nxt check sock_def_readable * ... { * schedule rcu_read_lock(); * wq = rcu_dereference(sk->sk_wq); * if (wq && waitqueue_active(&wq->wait)) * wake_up_interruptible(&wq->wait) * ... * } * * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 * could then endup calling schedule and sleep forever if there are no more * data on the socket. * */ static inline bool skwq_has_sleeper(struct socket_wq *wq) { return wq && wq_has_sleeper(&wq->wait); } /** * sock_poll_wait - place memory barrier behind the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table * * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { if (!poll_does_not_wait(p)) { poll_wait(filp, &sock->wq.wait, p); /* We need to be sure we are in sync with the * socket flags modification. * * This memory barrier is paired in the wq_has_sleeper. */ smp_mb(); } } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { /* This pairs with WRITE_ONCE() in sk_set_txhash() */ u32 txhash = READ_ONCE(sk->sk_txhash); if (txhash) { skb->l4_hash = 1; skb->hash = txhash; } } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in * and play with them. * * Inlined as it's very short and called for pretty much every * packet ever received. */ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; return true; } return false; } static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) { skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (skb) { if (sk_rmem_schedule(sk, skb, skb->truesize)) { skb_set_owner_r(skb, sk); return skb; } __kfree_skb(skb); } return NULL; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); void sk_stop_timer(struct sock *sk, struct timer_list *timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); /* * Recover an error report and clear atomically */ static inline int sock_error(struct sock *sk) { int err; /* Avoid an atomic operation for the common case. * This is racy since another cpu/thread can change sk_err under us. */ if (likely(data_race(!sk->sk_err))) return 0; err = xchg(&sk->sk_err, 0); return -err; } static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc); if (amt < 0) amt = 0; } return amt; } /* Note: * We use sk->sk_wq_raw, from contexts knowing this * pointer is not NULL and cannot disappear/change. */ static inline void sk_set_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; clear_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_wake_async(const struct sock *sk, int how, int band) { if (sock_flag(sk, SOCK_FASYNC)) { rcu_read_lock(); sock_wake_async(rcu_dereference(sk->sk_wq), how, band); rcu_read_unlock(); } } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at * minimum. */ #define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff))) #define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2) #define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE static inline void sk_stream_moderate_sndbuf(struct sock *sk) { u32 val; if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, bool force_schedule); /** * sk_page_frag - return an appropriate page_frag * @sk: socket * * Use the per task page_frag instead of the per socket one for * optimization when we know that we're in process context and own * everything that's associated with %current. * * Both direct reclaim and page faults can nest inside other * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag * usage if the caller is potentially doing any of them. * This assumes that page fault handlers use the GFP_NOFS flags. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == (__GFP_DIRECT_RECLAIM | __GFP_FS)) return ¤t->task_frag; return &sk->sk_frag; } bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); } static inline gfp_t gfp_any(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; } static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_sndtimeo; } static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); return v ?: 1; } /* Alas, with timeout socket operations are not restartable. * Compare this to poll(). */ static inline int sock_intr_errno(long timeo) { return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } struct sock_skb_cb { u32 dropcount; }; /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its * alignement guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? atomic_read(&sk->sk_drops) : 0; } static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) { int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); atomic_add(segs, &sk->sk_drops); } static inline ktime_t sock_read_timestamp(struct sock *sk) { #if BITS_PER_LONG==32 unsigned int seq; ktime_t kt; do { seq = read_seqbegin(&sk->sk_stamp_seq); kt = sk->sk_stamp; } while (read_seqretry(&sk->sk_stamp_seq, seq)); return kt; #else return READ_ONCE(sk->sk_stamp); #endif } static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) { #if BITS_PER_LONG==32 write_seqlock(&sk->sk_stamp_seq); sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else WRITE_ONCE(sk->sk_stamp, kt); #endif } void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { ktime_t kt = skb->tstamp; struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); /* * generate control messages if * - receive time stamping in software requested * - software time stamp available and wanted * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid) __sock_recv_wifi_status(msg, sk, skb); } void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) __sock_recv_ts_and_drops(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @tsflags: timestamping flags to use * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, __u8 *tx_flags, __u32 *tskey) { if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) *tskey = sk->sk_tskey++; } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, __u8 *tx_flags) { _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); } static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) { _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (static_branch_unlikely(&tcp_rx_skb_cache_key) && !sk->sk_rx_skb_cache) { sk->sk_rx_skb_cache = skb; skb_orphan(skb); return; } __kfree_skb(skb); } static inline struct net *sock_net(const struct sock *sk) { return read_pnet(&sk->sk_net); } static inline void sock_net_set(struct sock *sk, struct net *net) { write_pnet(&sk->sk_net, net); } static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { #ifdef CONFIG_INET return skb->destructor == sock_pfree; #else return false; #endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, * ie _not_ a timewait or request socket. */ static inline bool sk_fullsock(const struct sock *sk) { return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } static inline bool sk_is_refcounted(struct sock *sk) { /* Only full sockets have sk->sk_flags. */ return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } /** * skb_steal_sock - steal a socket from an sk_buff * @skb: sk_buff to steal the socket from * @refcounted: is set to true if the socket is reference-counted */ static inline struct sock * skb_steal_sock(struct sk_buff *skb, bool *refcounted) { if (skb->sk) { struct sock *sk = skb->sk; *refcounted = true; if (skb_sk_is_prefetched(skb)) *refcounted = sk_is_refcounted(sk); skb->destructor = NULL; skb->sk = NULL; return sk; } *refcounted = false; return NULL; } /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. */ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); #ifdef CONFIG_TLS_DEVICE } else if (unlikely(skb->decrypted)) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; #endif } #endif return skb; } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) */ static inline bool sk_listener(const struct sock *sk) { return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap); bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); void sk_get_meminfo(const struct sock *sk, u32 *meminfo); /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; extern int sysctl_tstamp_allow_data; extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; #define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_wmem ? */ if (proto->sysctl_wmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset)); return READ_ONCE(*proto->sysctl_wmem); } static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_rmem ? */ if (proto->sysctl_rmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset)); return READ_ONCE(*proto->sysctl_rmem); } /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) * Some wifi drivers need to tweak it to get more chunks. * They can use this helper from their ndo_start_xmit() */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device * index is either the same or that the socket is bound to an L3 * master device and the given device index is also enslaved to * that L3 master */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { int mdif; if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); if (mdif && mdif == sk->sk_bound_dev_if) return true; return false; } void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); void sock_set_rcvbuf(struct sock *sk, int val); void sock_set_mark(struct sock *sk, u32 val); void sock_set_reuseaddr(struct sock *sk); void sock_set_reuseport(struct sock *sk); void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); static inline bool sk_is_readable(struct sock *sk) { const struct proto *prot = READ_ONCE(sk->sk_prot); if (prot->sock_is_readable) return prot->sock_is_readable(sk); return false; } #endif /* _SOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct list_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 #define PERF_PMU_CAP_EXTENDED_REGS 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 #define PERF_PMU_CAP_NO_EXCLUDE 0x80 #define PERF_PMU_CAP_AUX_OUTPUT 0x100 struct perf_output_handle; /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_context __percpu *pmu_cpu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to: event->hw.idx + 1. */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_context *prev, struct perf_event_context *next); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; #define for_each_sibling_event(sibling, event) \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ int pending_wakeup; int pending_kill; int pending_disable; struct irq_work pending; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { struct pmu *pmu; /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head active_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; struct list_head pinned_active; struct list_head flexible_active; int nr_events; int nr_active; int is_active; int nr_stat; int nr_freq; int rotate_disable; /* * Set when nr_events != nr_active, except tolerant to events not * necessary to be active due to scheduling constraints, such as cgroups. */ int rotate_necessary; refcount_t refcount; struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; int sched_cb_usage; int online; /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); struct perf_sample_data { /* * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ u64 addr; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; u64 weight; u64 txn; union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; u64 aux_size; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 phys_addr; u64 cgroup; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; data->period = period; data->weight = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) { if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } #define is_default_overflow_handler(event) \ __is_default_overflow_handler((event)->overflow_handler) #ifdef CONFIG_BPF_SYSCALL static inline bool uses_default_overflow_handler(struct perf_event *event) { if (likely(is_default_overflow_handler(event))) return true; return __is_default_overflow_handler(event->orig_overflow_handler); } #else #define uses_default_overflow_handler(event) \ is_default_overflow_handler(event) #endif extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } } extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) { if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS])) return true; return false; } static inline void perf_event_task_migrate(struct task_struct *task) { if (perf_sw_migrate_enabled()) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) { /* * Callbacks are RCU-protected and must be READ_ONCE to avoid reloading * the callbacks between a !NULL check and dereferences, to ensure * pending stores/changes to the callback pointers are visible before a * non-NULL perf_guest_cbs is visible to readers, and to prevent a * module from unloading callbacks while readers are active. */ return rcu_dereference(perf_guest_cbs); } extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_proc_update_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void __weak arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); #endif /* _LINUX_PERF_EVENT_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/xarray.h> /** * idr_alloc_u32() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @nextid: Pointer to an ID. * @max: The maximum ID to allocate (inclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @nextid and @max. * Note that @max is inclusive whereas the @end parameter to idr_alloc() * is exclusive. The new ID is assigned to @nextid before the pointer * is inserted into the IDR, so if @nextid points into the object pointed * to by @ptr, a concurrent lookup will not find an uninitialised ID. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. If an error occurred, * @nextid is unchanged. */ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, unsigned long max, gfp_t gfp) { struct radix_tree_iter iter; void __rcu **slot; unsigned int base = idr->idr_base; unsigned int id = *nextid; if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; if (max < base) return -ENOSPC; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base); if (IS_ERR(slot)) return PTR_ERR(slot); *nextid = iter.index + base; /* there is a memory barrier inside radix_tree_iter_replace() */ radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); return 0; } EXPORT_SYMBOL_GPL(idr_alloc_u32); /** * idr_alloc() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = start; int ret; if (WARN_ON_ONCE(start < 0)) return -EINVAL; ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp); if (ret) return ret; return id; } EXPORT_SYMBOL_GPL(idr_alloc); /** * idr_alloc_cyclic() - Allocate an ID cyclically. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * The search for an unused ID will start at the last ID allocated and will * wrap around to @start if no free IDs are found before reaching @end. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = idr->idr_next; int err, max = end > 0 ? end - 1 : INT_MAX; if ((int)id < start) id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); if ((err == -ENOSPC) && (id > start)) { id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); } if (err) return err; idr->idr_next = id + 1; return id; } EXPORT_SYMBOL(idr_alloc_cyclic); /** * idr_remove() - Remove an ID from the IDR. * @idr: IDR handle. * @id: Pointer ID. * * Removes this ID from the IDR. If the ID was not previously in the IDR, * this function returns %NULL. * * Since this function modifies the IDR, the caller should provide their * own locking to ensure that concurrent modification of the same IDR is * not possible. * * Return: The pointer formerly associated with this ID. */ void *idr_remove(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL); } EXPORT_SYMBOL_GPL(idr_remove); /** * idr_find() - Return pointer for given ID. * @idr: IDR handle. * @id: Pointer ID. * * Looks up the pointer associated with this ID. A %NULL pointer may * indicate that @id is not allocated or that the %NULL pointer was * associated with this ID. * * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. * * Return: The pointer associated with this ID. */ void *idr_find(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base); } EXPORT_SYMBOL_GPL(idr_find); /** * idr_for_each() - Iterate through all stored pointers. * @idr: IDR handle. * @fn: Function to be called for each pointer. * @data: Data passed to callback function. * * The callback function will be called for each entry in @idr, passing * the ID, the entry and @data. * * If @fn returns anything other than %0, the iteration stops and that * value is returned from this function. * * idr_for_each() can be called concurrently with idr_alloc() and * idr_remove() if protected by RCU. Newly added entries may not be * seen and deleted entries may be seen, but adding and removing entries * will not cause other entries to be skipped, nor spurious ones to be seen. */ int idr_for_each(const struct idr *idr, int (*fn)(int id, void *p, void *data), void *data) { struct radix_tree_iter iter; void __rcu **slot; int base = idr->idr_base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; unsigned long id = iter.index + base; if (WARN_ON_ONCE(id > INT_MAX)) break; ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } return 0; } EXPORT_SYMBOL(idr_for_each); /** * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { entry = rcu_dereference_raw(*slot); if (!entry) continue; if (!xa_is_internal(entry)) break; if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) break; slot = radix_tree_iter_retry(&iter); } if (!slot) return NULL; *nextid = iter.index + base; return entry; } EXPORT_SYMBOL(idr_get_next_ul); /** * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next(struct idr *idr, int *nextid) { unsigned long id = *nextid; void *entry = idr_get_next_ul(idr, &id); if (WARN_ON_ONCE(id > INT_MAX)) return NULL; *nextid = id; return entry; } EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. * @idr: IDR handle. * @ptr: New pointer to associate with the ID. * @id: ID to change. * * Replace the pointer registered with an ID and return the old value. * This function can be called under the RCU read lock concurrently with * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * * Returns: the old value on success. %-ENOENT indicates that @id was not * found. %-EINVAL indicates that @ptr was not valid. */ void *idr_replace(struct idr *idr, void *ptr, unsigned long id) { struct radix_tree_node *node; void __rcu **slot = NULL; void *entry; id -= idr->idr_base; entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); __radix_tree_replace(&idr->idr_rt, node, slot, ptr); return entry; } EXPORT_SYMBOL(idr_replace); /** * DOC: IDA description * * The IDA is an ID allocator which does not provide the ability to * associate an ID with a pointer. As such, it only needs to store one * bit per ID, and so is more space efficient than an IDR. To use an IDA, * define it using DEFINE_IDA() (or embed a &struct ida in a data structure, * then initialise it using ida_init()). To allocate a new ID, call * ida_alloc(), ida_alloc_min(), ida_alloc_max() or ida_alloc_range(). * To free an ID, call ida_free(). * * ida_destroy() can be used to dispose of an IDA without needing to * free the individual IDs in it. You can use ida_is_empty() to find * out whether the IDA has any IDs currently allocated. * * The IDA handles its own locking. It is safe to call any of the IDA * functions without synchronisation in your code. * * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward * limitation, it should be quite straightforward to raise the maximum. */ /* * Developer's notes: * * The IDA uses the functionality provided by the XArray to store bitmaps in * each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap * have been set. * * I considered telling the XArray that each slot is an order-10 node * and indexing by bit number, but the XArray can't allow a single multi-index * entry in the head, which would significantly increase memory consumption * for the IDA. So instead we divide the index by the number of bits in the * leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given * leaf, instead of allocating a 128-byte bitmap, we store the bits * as a value entry. Value entries never have the XA_FREE_MARK cleared * because we can always convert them into a bitmap entry. * * It would be possible to optimise further; once we've run out of a * single 128-byte bitmap, we currently switch to a 576-byte node, put * the 128-byte bitmap in the first entry and then start allocating extra * 128-byte entries. We could instead use the 512 bytes of the node's * data as a bitmap before moving to that scheme. I do not believe this * is a worthwhile optimisation; Rasmus Villemoes surveyed the current * users of the IDA and almost none of them use more than 1024 entries. * Those that do use more than the 8192 IDs that the 512 bytes would * provide. * * The IDA always uses a lock to alloc/free. If we add a 'test_bit' * equivalent, it will still need locking. Going to RCU lookup would require * using RCU to free bitmaps, and that's not trivial without embedding an * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte * bitmap, which is excessive. */ /** * ida_alloc_range() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and @max, inclusive. The allocated ID will * not exceed %INT_MAX, even if @max is larger. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, gfp_t gfp) { XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS); unsigned bit = min % IDA_BITMAP_BITS; unsigned long flags; struct ida_bitmap *bitmap, *alloc = NULL; if ((int)min < 0) return -ENOSPC; if ((int)max < 0) max = INT_MAX; retry: xas_lock_irqsave(&xas, flags); next: bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK); if (xas.xa_index > min / IDA_BITMAP_BITS) bit = 0; if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (xa_is_value(bitmap)) { unsigned long tmp = xa_to_value(bitmap); if (bit < BITS_PER_XA_VALUE) { bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit < BITS_PER_XA_VALUE) { tmp |= 1UL << bit; xas_store(&xas, xa_mk_value(tmp)); goto out; } } bitmap = alloc; if (!bitmap) bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); if (!bitmap) goto alloc; bitmap->bitmap[0] = tmp; xas_store(&xas, bitmap); if (xas_error(&xas)) { bitmap->bitmap[0] = 0; goto out; } } if (bitmap) { bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit == IDA_BITMAP_BITS) goto next; __set_bit(bit, bitmap->bitmap); if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) xas_clear_mark(&xas, XA_FREE_MARK); } else { if (bit < BITS_PER_XA_VALUE) { bitmap = xa_mk_value(1UL << bit); } else { bitmap = alloc; if (!bitmap) bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); if (!bitmap) goto alloc; __set_bit(bit, bitmap->bitmap); } xas_store(&xas, bitmap); } out: xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) { xas.xa_index = min / IDA_BITMAP_BITS; bit = min % IDA_BITMAP_BITS; goto retry; } if (bitmap != alloc) kfree(alloc); if (xas_error(&xas)) return xas_error(&xas); return xas.xa_index * IDA_BITMAP_BITS + bit; alloc: xas_unlock_irqrestore(&xas, flags); alloc = kzalloc(sizeof(*bitmap), gfp); if (!alloc) return -ENOMEM; xas_set(&xas, min / IDA_BITMAP_BITS); bit = min % IDA_BITMAP_BITS; goto retry; nospc: xas_unlock_irqrestore(&xas, flags); kfree(alloc); return -ENOSPC; } EXPORT_SYMBOL(ida_alloc_range); /** * ida_free() - Release an allocated ID. * @ida: IDA handle. * @id: Previously allocated ID. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_free(struct ida *ida, unsigned int id) { XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS); unsigned bit = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; unsigned long flags; if ((int)id < 0) return; xas_lock_irqsave(&xas, flags); bitmap = xas_load(&xas); if (xa_is_value(bitmap)) { unsigned long v = xa_to_value(bitmap); if (bit >= BITS_PER_XA_VALUE) goto err; if (!(v & (1UL << bit))) goto err; v &= ~(1UL << bit); if (!v) goto delete; xas_store(&xas, xa_mk_value(v)); } else { if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { kfree(bitmap); delete: xas_store(&xas, NULL); } } xas_unlock_irqrestore(&xas, flags); return; err: xas_unlock_irqrestore(&xas, flags); WARN(1, "ida_free called for id=%d which is not allocated.\n", id); } EXPORT_SYMBOL(ida_free); /** * ida_destroy() - Free all IDs. * @ida: IDA handle. * * Calling this function frees all IDs and releases all resources used * by an IDA. When this call returns, the IDA is empty and can be reused * or freed. If the IDA is already empty, there is no need to call this * function. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_destroy(struct ida *ida) { XA_STATE(xas, &ida->xa, 0); struct ida_bitmap *bitmap; unsigned long flags; xas_lock_irqsave(&xas, flags); xas_for_each(&xas, bitmap, ULONG_MAX) { if (!xa_is_value(bitmap)) kfree(bitmap); xas_store(&xas, NULL); } xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(ida_destroy); #ifndef __KERNEL__ extern void xa_dump_index(unsigned long index, unsigned int shift); #define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS) static void ida_dump_entry(void *entry, unsigned long index) { unsigned long i; if (!entry) return; if (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); unsigned int shift = node->shift + IDA_CHUNK_SHIFT + XA_CHUNK_SHIFT; xa_dump_index(index * IDA_BITMAP_BITS, shift); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) ida_dump_entry(node->slots[i], index | (i << node->shift)); } else if (xa_is_value(entry)) { xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG)); pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry); } else { struct ida_bitmap *bitmap = entry; xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT); pr_cont("bitmap: %p data", bitmap); for (i = 0; i < IDA_BITMAP_LONGS; i++) pr_cont(" %lx", bitmap->bitmap[i]); pr_cont("\n"); } } static void ida_dump(struct ida *ida) { struct xarray *xa = &ida->xa; pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head, xa->xa_flags >> ROOT_TAG_SHIFT); ida_dump_entry(xa->xa_head, 0); } #endif |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analagous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 | // SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) "watchdog: " fmt #include <linux/mm.h> #include <linux/cpu.h> #include <linux/nmi.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/tick.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/stop_machine.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) # define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) # define NMI_WATCHDOG_DEFAULT 1 #else # define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) # define NMI_WATCHDOG_DEFAULT 0 #endif unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly nmi_watchdog_available; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #ifdef CONFIG_HARDLOCKUP_DETECTOR # ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; # endif /* CONFIG_SMP */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ unsigned int __read_mostly hardlockup_panic = CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these * cases this function can be called to disable hard lockup detection. This * function should only be executed once by the boot processor before the * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ void __init hardlockup_detector_disable(void) { nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) { if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); #endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its * own hardlockup detector. * * watchdog_nmi_enable/disable can be implemented to start and stop when * softlockup watchdog threads start and stop. The arch must select the * SOFTLOCKUP_DETECTOR Kconfig. */ int __weak watchdog_nmi_enable(unsigned int cpu) { hardlockup_detector_perf_enable(); return 0; } void __weak watchdog_nmi_disable(unsigned int cpu) { hardlockup_detector_perf_disable(); } /* Return 0, if a NMI watchdog is available. Error code otherwise */ int __weak __init watchdog_nmi_probe(void) { return hardlockup_detector_perf_init(); } /** * watchdog_nmi_stop - Stop the watchdog for reconfiguration * * The reconfiguration steps are: * watchdog_nmi_stop(); * update_variables(); * watchdog_nmi_start(); */ void __weak watchdog_nmi_stop(void) { } /** * watchdog_nmi_start - Start the watchdog after reconfiguration * * Counterpart to watchdog_nmi_stop(). * * The following variables have been updated in update_variables() and * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask */ void __weak watchdog_nmi_start(void) { } /** * lockup_detector_update_enable - Update the sysctl enable bit * * Caller needs to make sure that the NMI/perf watchdogs are off, so this * can't race with watchdog_nmi_disable(). */ static void lockup_detector_update_enable(void) { watchdog_enabled = 0; if (!watchdog_user_enabled) return; if (nmi_watchdog_available && nmi_watchdog_user_enabled) watchdog_enabled |= NMI_WATCHDOG_ENABLED; if (soft_watchdog_user_enabled) watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } #ifdef CONFIG_SOFTLOCKUP_DETECTOR #define SOFTLOCKUP_RESET ULONG_MAX #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); static int __init watchdog_thresh_setup(char *str) { get_option(&str, &watchdog_thresh); return 1; } __setup("watchdog_thresh=", watchdog_thresh_setup); static void __lockup_detector_cleanup(void); /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally * want a higher threshold for soft lockups than for hard lockups. So we couple * the thresholds with a factor: we make the soft threshold twice the amount of * time the hard threshold is. */ static int get_softlockup_thresh(void) { return watchdog_thresh * 2; } /* * Returns seconds, approximately. We don't need nanosecond * resolution, and we don't need to waste time with a big divide when * 2^30ns == 1.074s. */ static unsigned long get_timestamp(void) { return running_clock() >> 30LL; /* 2^30 ~= 10^9 */ } static void set_sample_period(void) { /* * convert watchdog_thresh from seconds to ns * the divide by 5 is to give hrtimer several chances (two * or three with the current relation between the soft * and hard thresholds) to increment before the * hardlockup detector generates a warning */ sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); watchdog_update_hrtimer_threshold(sample_period); } /* Commands for resetting the watchdog */ static void update_touch_ts(void) { __this_cpu_write(watchdog_touch_ts, get_timestamp()); } /** * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls * * Call when the scheduler may have stalled for legitimate reasons * preventing the watchdog task from executing - e.g. the scheduler * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ notrace void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's timestamp * gets zeroed here, so use the raw_ operation. */ raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); } EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) { int cpu; /* * watchdog_mutex cannpt be taken here, as this might be called * from (soft)interrupt context, so the access to * watchdog_allowed_cpumask might race with a concurrent update. * * The watchdog time stamp can race against a concurrent real * update as well, the only side effect might be a cycle delay for * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; wq_watchdog_touch(-1); } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); __this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){ /* Warn about unreasonable delays. */ if (time_after(now, touch_ts + get_softlockup_thresh())) return now - touch_ts; } return 0; } /* watchdog detector functions */ bool is_hardlockup(void) { unsigned long hrint = __this_cpu_read(hrtimer_interrupts); if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) return true; __this_cpu_write(hrtimer_interrupts_saved, hrint); return false; } static void watchdog_interrupt_count(void) { __this_cpu_inc(hrtimer_interrupts); } static DEFINE_PER_CPU(struct completion, softlockup_completion); static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); /* * The watchdog thread function - touches the timestamp. * * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed * for more than 2*watchdog_thresh seconds then the debug-printout * triggers in watchdog_timer_fn(). */ static int softlockup_fn(void *data) { update_touch_ts(); complete(this_cpu_ptr(&softlockup_completion)); return 0; } /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ watchdog_interrupt_count(); /* kick the softlockup detector */ if (completion_done(this_cpu_ptr(&softlockup_completion))) { reinit_completion(this_cpu_ptr(&softlockup_completion)); stop_one_cpu_nowait(smp_processor_id(), softlockup_fn, NULL, this_cpu_ptr(&softlockup_stop_work)); } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); if (touch_ts == SOFTLOCKUP_RESET) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically * make sure the scheduler tick is up to date. */ __this_cpu_write(softlockup_touch_sync, false); sched_clock_tick(); } /* Clear the guest paused flag on watchdog reset */ kvm_check_and_clear_guest_paused(); update_touch_ts(); return HRTIMER_RESTART; } /* check for a softlockup * This is done by making sure a high priority task is * being scheduled. The task touches the watchdog to * indicate it is getting cpu time. If it hasn't then * this is a good indication some task is hogging the cpu */ duration = is_softlockup(touch_ts); if (unlikely(duration)) { /* * If a virtual machine is stopped by the host it can look to * the watchdog like a soft lockup, check to see if the host * stopped the vm before we issue the warning */ if (kvm_check_and_clear_guest_paused()) return HRTIMER_RESTART; /* * Prevent multiple soft-lockup reports if one cpu is already * engaged in dumping all cpu back traces. */ if (softlockup_all_cpu_backtrace) { if (test_and_set_bit_lock(0, &soft_lockup_nmi_warn)) return HRTIMER_RESTART; } /* Start period for the next softlockup warning. */ update_touch_ts(); pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); if (softlockup_all_cpu_backtrace) { trigger_allbutself_cpu_backtrace(); clear_bit_unlock(0, &soft_lockup_nmi_warn); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); } return HRTIMER_RESTART; } static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); struct completion *done = this_cpu_ptr(&softlockup_completion); WARN_ON_ONCE(cpu != smp_processor_id()); init_completion(done); complete(done); /* * Start the timer first to prevent the NMI watchdog triggering * before the timer has a chance to fire. */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer->function = watchdog_timer_fn; hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED_HARD); /* Initialize timestamp */ update_touch_ts(); /* Enable the perf event */ if (watchdog_enabled & NMI_WATCHDOG_ENABLED) watchdog_nmi_enable(cpu); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); WARN_ON_ONCE(cpu != smp_processor_id()); /* * Disable the perf event first. That prevents that a large delay * between disabling the timer and disabling the perf event causes * the perf NMI to detect a false positive. */ watchdog_nmi_disable(cpu); hrtimer_cancel(hrtimer); wait_for_completion(this_cpu_ptr(&softlockup_completion)); } static int softlockup_stop_fn(void *data) { watchdog_disable(smp_processor_id()); return 0; } static void softlockup_stop_all(void) { int cpu; if (!softlockup_initialized) return; for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); cpumask_clear(&watchdog_allowed_mask); } static int softlockup_start_fn(void *data) { watchdog_enable(smp_processor_id()); return 0; } static void softlockup_start_all(void) { int cpu; cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } int lockup_detector_online_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_disable(cpu); return 0; } static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) softlockup_start_all(); watchdog_nmi_start(); cpus_read_unlock(); /* * Must be called outside the cpus locked section to prevent * recursive locking in the perf code. */ __lockup_detector_cleanup(); } void lockup_detector_reconfigure(void) { mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(); mutex_unlock(&watchdog_mutex); } /* * Create the watchdog thread infrastructure and configure the detector(s). * * The threads are not unparked as watchdog_allowed_mask is empty. When * the threads are successfully initialized, take the proper locks and * unpark the threads in the watchdog_cpumask if the watchdog is enabled. */ static __init void lockup_detector_setup(void) { /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. */ lockup_detector_update_enable(); if (!IS_ENABLED(CONFIG_SYSCTL) && !(watchdog_enabled && watchdog_thresh)) return; mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(); softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); lockup_detector_update_enable(); watchdog_nmi_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { __lockup_detector_reconfigure(); } static inline void lockup_detector_setup(void) { __lockup_detector_reconfigure(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) { lockdep_assert_held(&watchdog_mutex); hardlockup_detector_perf_cleanup(); } /** * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes * * Caller must not hold the cpu hotplug rwsem. */ void lockup_detector_cleanup(void) { mutex_lock(&watchdog_mutex); __lockup_detector_cleanup(); mutex_unlock(&watchdog_mutex); } /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * * Special interface for parisc. It prevents lockup detector warnings from * the default pm_poweroff() function which busy loops forever. */ void lockup_detector_soft_poweroff(void) { watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL /* Propagate any changes to the watchdog threads */ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); __lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * * caller | table->data points to | 'which' * -------------------|----------------------------|-------------------------- * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | * | | SOFT_WATCHDOG_ENABLED * -------------------|----------------------------|-------------------------- * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED * -------------------|----------------------------|-------------------------- * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old, *param = table->data; mutex_lock(&watchdog_mutex); if (!write) { /* * On read synchronize the userspace interface. This is a * racy snapshot. */ *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && old != READ_ONCE(*param)) proc_watchdog_update(); } mutex_unlock(&watchdog_mutex); return err; } /* * /proc/sys/kernel/watchdog */ int proc_watchdog(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/nmi_watchdog */ int proc_nmi_watchdog(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!nmi_watchdog_available && write) return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/soft_watchdog */ int proc_soft_watchdog(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(SOFT_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/watchdog_thresh */ int proc_watchdog_thresh(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old; mutex_lock(&watchdog_mutex); old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && write && old != READ_ONCE(watchdog_thresh)) proc_watchdog_update(); mutex_unlock(&watchdog_mutex); return err; } /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ int proc_watchdog_cpumask(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) proc_watchdog_update(); mutex_unlock(&watchdog_mutex); return err; } #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { if (tick_nohz_full_enabled()) pr_info("Disabling watchdog on nohz_full cores by default\n"); cpumask_copy(&watchdog_cpumask, housekeeping_cpumask(HK_FLAG_TIMER)); if (!watchdog_nmi_probe()) nmi_watchdog_available = true; lockup_detector_setup(); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some * particular ordering. One way to make the compiler aware of ordering is to * put the two invocations of READ_ONCE or WRITE_ONCE in different C * statements. * * These two macros will also work on aggregate data types like structs or * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ #ifndef __ASM_GENERIC_RWONCE_H #define __ASM_GENERIC_RWONCE_H #ifndef __ASSEMBLY__ #include <linux/compiler_types.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will * actually be atomic in some cases (namely Armv7 + LPAE), but for others we * rely on the access being split into 2x32-bit accesses for a 32-bit quantity * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ "Unsupported access size for {READ,WRITE}_ONCE().") /* * Use __READ_ONCE() instead of READ_ONCE() if you do not require any * atomicity. Note that this may result in tears! */ #ifndef __READ_ONCE #define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #endif #define READ_ONCE(x) \ ({ \ compiletime_assert_rwonce_type(x); \ __READ_ONCE(x); \ }) #define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) #define WRITE_ONCE(x, val) \ do { \ compiletime_assert_rwonce_type(x); \ __WRITE_ONCE(x, val); \ } while (0) static __no_sanitize_or_inline unsigned long __read_once_word_nocheck(const void *addr) { return __READ_ONCE(*(unsigned long *)addr); } /* * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a * word from memory atomically but without telling KASAN/KCSAN. This is * usually used by unwinding code when walking the stack of a running process. */ #define READ_ONCE_NOCHECK(x) \ ({ \ compiletime_assert(sizeof(x) == sizeof(unsigned long), \ "Unsupported access size for READ_ONCE_NOCHECK()."); \ (typeof(x))__read_once_word_nocheck(&(x)); \ }) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) { kasan_check_read(addr, 1); return *(unsigned long *)addr; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_RWONCE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 | // SPDX-License-Identifier: GPL-2.0-or-later /* Provide a way to create a superblock configuration context within the kernel * that allows a superblock to be set up prior to mounting. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/magic.h> #include <linux/security.h> #include <linux/mnt_namespace.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <asm/sections.h> #include "mount.h" #include "internal.h" enum legacy_fs_param { LEGACY_FS_UNSET_PARAMS, LEGACY_FS_MONOLITHIC_PARAMS, LEGACY_FS_INDIVIDUAL_PARAMS, }; struct legacy_fs_context { char *legacy_data; /* Data page for legacy filesystems */ size_t data_size; enum legacy_fs_param param_type; }; static int legacy_init_fs_context(struct fs_context *fc); static const struct constant_table common_set_sb_flag[] = { { "dirsync", SB_DIRSYNC }, { "lazytime", SB_LAZYTIME }, { "mand", SB_MANDLOCK }, { "ro", SB_RDONLY }, { "sync", SB_SYNCHRONOUS }, { }, }; static const struct constant_table common_clear_sb_flag[] = { { "async", SB_SYNCHRONOUS }, { "nolazytime", SB_LAZYTIME }, { "nomand", SB_MANDLOCK }, { "rw", SB_RDONLY }, { }, }; /* * Check for a common mount option that manipulates s_flags. */ static int vfs_parse_sb_flag(struct fs_context *fc, const char *key) { unsigned int token; token = lookup_constant(common_set_sb_flag, key, 0); if (token) { fc->sb_flags |= token; fc->sb_flags_mask |= token; return 0; } token = lookup_constant(common_clear_sb_flag, key, 0); if (token) { fc->sb_flags &= ~token; fc->sb_flags_mask |= token; return 0; } return -ENOPARAM; } /** * vfs_parse_fs_param - Add a single parameter to a superblock config * @fc: The filesystem context to modify * @param: The parameter * * A single mount option in string form is applied to the filesystem context * being set up. Certain standard options (for example "ro") are translated * into flag bits without going to the filesystem. The active security module * is allowed to observe and poach options. Any other options are passed over * to the filesystem to parse. * * This may be called multiple times for a context. * * Returns 0 on success and a negative error code on failure. In the event of * failure, supplementary error information may have been set. */ int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param) { int ret; if (!param->key) return invalf(fc, "Unnamed parameter\n"); ret = vfs_parse_sb_flag(fc, param->key); if (ret != -ENOPARAM) return ret; ret = security_fs_context_parse_param(fc, param); if (ret != -ENOPARAM) /* Param belongs to the LSM or is disallowed by the LSM; so * don't pass to the FS. */ return ret; if (fc->ops->parse_param) { ret = fc->ops->parse_param(fc, param); if (ret != -ENOPARAM) return ret; } /* If the filesystem doesn't take any arguments, give it the * default handling of source. */ if (strcmp(param->key, "source") == 0) { if (param->type != fs_value_is_string) return invalf(fc, "VFS: Non-string source"); if (fc->source) return invalf(fc, "VFS: Multiple sources"); fc->source = param->string; param->string = NULL; return 0; } return invalf(fc, "%s: Unknown parameter '%s'", fc->fs_type->name, param->key); } EXPORT_SYMBOL(vfs_parse_fs_param); /** * vfs_parse_fs_string - Convenience function to just parse a string. */ int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value, size_t v_size) { int ret; struct fs_parameter param = { .key = key, .type = fs_value_is_flag, .size = v_size, }; if (value) { param.string = kmemdup_nul(value, v_size, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } ret = vfs_parse_fs_param(fc, ¶m); kfree(param.string); return ret; } EXPORT_SYMBOL(vfs_parse_fs_string); /** * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data * @ctx: The superblock configuration to fill in. * @data: The data to parse * * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be * called from the ->monolithic_mount_data() fs_context operation. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ int generic_parse_monolithic(struct fs_context *fc, void *data) { char *options = data, *key; int ret = 0; if (!options) return 0; ret = security_sb_eat_lsm_opts(options, &fc->security); if (ret) return ret; while ((key = strsep(&options, ",")) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); } ret = vfs_parse_fs_string(fc, key, value, v_len); if (ret < 0) break; } } return ret; } EXPORT_SYMBOL(generic_parse_monolithic); /** * alloc_fs_context - Create a filesystem context. * @fs_type: The filesystem type. * @reference: The dentry from which this one derives (or NULL) * @sb_flags: Filesystem/superblock flags (SB_*) * @sb_flags_mask: Applicable members of @sb_flags * @purpose: The purpose that this configuration shall be used for. * * Open a filesystem and create a mount context. The mount context is * initialised with the supplied flags and, if a submount/automount from * another superblock (referred to by @reference) is supplied, may have * parameters such as namespaces copied across from that superblock. */ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, struct dentry *reference, unsigned int sb_flags, unsigned int sb_flags_mask, enum fs_context_purpose purpose) { int (*init_fs_context)(struct fs_context *); struct fs_context *fc; int ret = -ENOMEM; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL_ACCOUNT); if (!fc) return ERR_PTR(-ENOMEM); fc->purpose = purpose; fc->sb_flags = sb_flags; fc->sb_flags_mask = sb_flags_mask; fc->fs_type = get_filesystem(fs_type); fc->cred = get_current_cred(); fc->net_ns = get_net(current->nsproxy->net_ns); fc->log.prefix = fs_type->name; mutex_init(&fc->uapi_mutex); switch (purpose) { case FS_CONTEXT_FOR_MOUNT: fc->user_ns = get_user_ns(fc->cred->user_ns); break; case FS_CONTEXT_FOR_SUBMOUNT: fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); break; case FS_CONTEXT_FOR_RECONFIGURE: atomic_inc(&reference->d_sb->s_active); fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); fc->root = dget(reference); break; } /* TODO: Make all filesystems support this unconditionally */ init_fs_context = fc->fs_type->init_fs_context; if (!init_fs_context) init_fs_context = legacy_init_fs_context; ret = init_fs_context(fc); if (ret < 0) goto err_fc; fc->need_free = true; return fc; err_fc: put_fs_context(fc); return ERR_PTR(ret); } struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, unsigned int sb_flags) { return alloc_fs_context(fs_type, NULL, sb_flags, 0, FS_CONTEXT_FOR_MOUNT); } EXPORT_SYMBOL(fs_context_for_mount); struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, unsigned int sb_flags, unsigned int sb_flags_mask) { return alloc_fs_context(dentry->d_sb->s_type, dentry, sb_flags, sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE); } EXPORT_SYMBOL(fs_context_for_reconfigure); struct fs_context *fs_context_for_submount(struct file_system_type *type, struct dentry *reference) { return alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT); } EXPORT_SYMBOL(fs_context_for_submount); void fc_drop_locked(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; dput(fc->root); fc->root = NULL; deactivate_locked_super(sb); } static void legacy_fs_context_free(struct fs_context *fc); /** * vfs_dup_fc_config: Duplicate a filesystem context. * @src_fc: The context to copy. */ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) { struct fs_context *fc; int ret; if (!src_fc->ops->dup) return ERR_PTR(-EOPNOTSUPP); fc = kmemdup(src_fc, sizeof(struct fs_context), GFP_KERNEL); if (!fc) return ERR_PTR(-ENOMEM); mutex_init(&fc->uapi_mutex); fc->fs_private = NULL; fc->s_fs_info = NULL; fc->source = NULL; fc->security = NULL; get_filesystem(fc->fs_type); get_net(fc->net_ns); get_user_ns(fc->user_ns); get_cred(fc->cred); if (fc->log.log) refcount_inc(&fc->log.log->usage); /* Can't call put until we've called ->dup */ ret = fc->ops->dup(fc, src_fc); if (ret < 0) goto err_fc; ret = security_fs_context_dup(fc, src_fc); if (ret < 0) goto err_fc; return fc; err_fc: put_fs_context(fc); return ERR_PTR(ret); } EXPORT_SYMBOL(vfs_dup_fs_context); /** * logfc - Log a message to a filesystem context * @fc: The filesystem context to log to. * @fmt: The format of the buffer. */ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...) { va_list va; struct va_format vaf = {.fmt = fmt, .va = &va}; va_start(va, fmt); if (!log) { switch (level) { case 'w': printk(KERN_WARNING "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; case 'e': printk(KERN_ERR "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; default: printk(KERN_NOTICE "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; } } else { unsigned int logsize = ARRAY_SIZE(log->buffer); u8 index; char *q = kasprintf(GFP_KERNEL, "%c %s%s%pV\n", level, prefix ? prefix : "", prefix ? ": " : "", &vaf); index = log->head & (logsize - 1); BUILD_BUG_ON(sizeof(log->head) != sizeof(u8) || sizeof(log->tail) != sizeof(u8)); if ((u8)(log->head - log->tail) == logsize) { /* The buffer is full, discard the oldest message */ if (log->need_free & (1 << index)) kfree(log->buffer[index]); log->tail++; } log->buffer[index] = q ? q : "OOM: Can't store error string"; if (q) log->need_free |= 1 << index; else log->need_free &= ~(1 << index); log->head++; } va_end(va); } EXPORT_SYMBOL(logfc); /* * Free a logging structure. */ static void put_fc_log(struct fs_context *fc) { struct fc_log *log = fc->log.log; int i; if (log) { if (refcount_dec_and_test(&log->usage)) { fc->log.log = NULL; for (i = 0; i <= 7; i++) if (log->need_free & (1 << i)) kfree(log->buffer[i]); kfree(log); } } } /** * put_fs_context - Dispose of a superblock configuration context. * @fc: The context to dispose of. */ void put_fs_context(struct fs_context *fc) { struct super_block *sb; if (fc->root) { sb = fc->root->d_sb; dput(fc->root); fc->root = NULL; deactivate_super(sb); } if (fc->need_free && fc->ops && fc->ops->free) fc->ops->free(fc); security_free_mnt_opts(&fc->security); put_net(fc->net_ns); put_user_ns(fc->user_ns); put_cred(fc->cred); put_fc_log(fc); put_filesystem(fc->fs_type); kfree(fc->source); kfree(fc); } EXPORT_SYMBOL(put_fs_context); /* * Free the config for a filesystem that doesn't support fs_context. */ static void legacy_fs_context_free(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; if (ctx) { if (ctx->param_type == LEGACY_FS_INDIVIDUAL_PARAMS) kfree(ctx->legacy_data); kfree(ctx); } } /* * Duplicate a legacy config. */ static int legacy_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { struct legacy_fs_context *ctx; struct legacy_fs_context *src_ctx = src_fc->fs_private; ctx = kmemdup(src_ctx, sizeof(*src_ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; if (ctx->param_type == LEGACY_FS_INDIVIDUAL_PARAMS) { ctx->legacy_data = kmemdup(src_ctx->legacy_data, src_ctx->data_size, GFP_KERNEL); if (!ctx->legacy_data) { kfree(ctx); return -ENOMEM; } } fc->fs_private = ctx; return 0; } /* * Add a parameter to a legacy config. We build up a comma-separated list of * options. */ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct legacy_fs_context *ctx = fc->fs_private; unsigned int size = ctx->data_size; size_t len = 0; if (strcmp(param->key, "source") == 0) { if (param->type != fs_value_is_string) return invalf(fc, "VFS: Legacy: Non-string source"); if (fc->source) return invalf(fc, "VFS: Legacy: Multiple sources"); fc->source = param->string; param->string = NULL; return 0; } if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS) return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options"); switch (param->type) { case fs_value_is_string: len = 1 + param->size; fallthrough; case fs_value_is_flag: len += strlen(param->key); break; default: return invalf(fc, "VFS: Legacy: Parameter type for '%s' not supported", param->key); } if (size + len + 2 > PAGE_SIZE) return invalf(fc, "VFS: Legacy: Cumulative options too large"); if (strchr(param->key, ',') || (param->type == fs_value_is_string && memchr(param->string, ',', param->size))) return invalf(fc, "VFS: Legacy: Option '%s' contained comma", param->key); if (!ctx->legacy_data) { ctx->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!ctx->legacy_data) return -ENOMEM; } if (size) ctx->legacy_data[size++] = ','; len = strlen(param->key); memcpy(ctx->legacy_data + size, param->key, len); size += len; if (param->type == fs_value_is_string) { ctx->legacy_data[size++] = '='; memcpy(ctx->legacy_data + size, param->string, param->size); size += param->size; } ctx->legacy_data[size] = '\0'; ctx->data_size = size; ctx->param_type = LEGACY_FS_INDIVIDUAL_PARAMS; return 0; } /* * Add monolithic mount data. */ static int legacy_parse_monolithic(struct fs_context *fc, void *data) { struct legacy_fs_context *ctx = fc->fs_private; if (ctx->param_type != LEGACY_FS_UNSET_PARAMS) { pr_warn("VFS: Can't mix monolithic and individual options\n"); return -EINVAL; } ctx->legacy_data = data; ctx->param_type = LEGACY_FS_MONOLITHIC_PARAMS; if (!ctx->legacy_data) return 0; if (fc->fs_type->fs_flags & FS_BINARY_MOUNTDATA) return 0; return security_sb_eat_lsm_opts(ctx->legacy_data, &fc->security); } /* * Get a mountable root with the legacy mount command. */ static int legacy_get_tree(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb; struct dentry *root; root = fc->fs_type->mount(fc->fs_type, fc->sb_flags, fc->source, ctx->legacy_data); if (IS_ERR(root)) return PTR_ERR(root); sb = root->d_sb; BUG_ON(!sb); fc->root = root; return 0; } /* * Handle remount. */ static int legacy_reconfigure(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb = fc->root->d_sb; if (!sb->s_op->remount_fs) return 0; return sb->s_op->remount_fs(sb, &fc->sb_flags, ctx ? ctx->legacy_data : NULL); } const struct fs_context_operations legacy_fs_context_ops = { .free = legacy_fs_context_free, .dup = legacy_fs_context_dup, .parse_param = legacy_parse_param, .parse_monolithic = legacy_parse_monolithic, .get_tree = legacy_get_tree, .reconfigure = legacy_reconfigure, }; /* * Initialise a legacy context for a filesystem that doesn't support * fs_context. */ static int legacy_init_fs_context(struct fs_context *fc) { fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL_ACCOUNT); if (!fc->fs_private) return -ENOMEM; fc->ops = &legacy_fs_context_ops; return 0; } int parse_monolithic_mount_data(struct fs_context *fc, void *data) { int (*monolithic_mount_data)(struct fs_context *, void *); monolithic_mount_data = fc->ops->parse_monolithic; if (!monolithic_mount_data) monolithic_mount_data = generic_parse_monolithic; return monolithic_mount_data(fc, data); } /* * Clean up a context after performing an action on it and put it into a state * from where it can be used to reconfigure a superblock. * * Note that here we do only the parts that can't fail; the rest is in * finish_clean_context() below and in between those fs_context is marked * FS_CONTEXT_AWAITING_RECONF. The reason for splitup is that after * successful mount or remount we need to report success to userland. * Trying to do full reinit (for the sake of possible subsequent remount) * and failing to allocate memory would've put us into a nasty situation. * So here we only discard the old state and reinitialization is left * until we actually try to reconfigure. */ void vfs_clean_context(struct fs_context *fc) { if (fc->need_free && fc->ops && fc->ops->free) fc->ops->free(fc); fc->need_free = false; fc->fs_private = NULL; fc->s_fs_info = NULL; fc->sb_flags = 0; security_free_mnt_opts(&fc->security); kfree(fc->source); fc->source = NULL; fc->purpose = FS_CONTEXT_FOR_RECONFIGURE; fc->phase = FS_CONTEXT_AWAITING_RECONF; } int finish_clean_context(struct fs_context *fc) { int error; if (fc->phase != FS_CONTEXT_AWAITING_RECONF) return 0; if (fc->fs_type->init_fs_context) error = fc->fs_type->init_fs_context(fc); else error = legacy_init_fs_context(fc); if (unlikely(error)) { fc->phase = FS_CONTEXT_FAILED; return error; } fc->need_free = true; fc->phase = FS_CONTEXT_RECONF_PARAMS; return 0; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memblock.h> #include <linux/mmdebug.h> #include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> #include <linux/vmalloc.h> #include "physaddr.h" #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } return x; } EXPORT_SYMBOL(__phys_addr); unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; if (y >= KERNEL_IMAGE_SIZE) return false; } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ if ((x > y) || !phys_addr_valid(x)) return false; } return pfn_valid(x >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #else #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); /* max_low_pfn is set early, but not _that_ early */ if (max_low_pfn) { VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); } return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) return false; if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #endif /* CONFIG_X86_64 */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef INT_BLK_MQ_H #define INT_BLK_MQ_H #include "blk-stat.h" #include "blk-mq-tag.h" struct blk_mq_tag_set; struct blk_mq_ctxs { struct kobject kobj; struct blk_mq_ctx __percpu *queue_ctx; }; /** * struct blk_mq_ctx - State for a software queue facing the submitting CPUs */ struct blk_mq_ctx { struct { spinlock_t lock; struct list_head rq_lists[HCTX_MAX_TYPES]; } ____cacheline_aligned_in_smp; unsigned int cpu; unsigned short index_hw[HCTX_MAX_TYPES]; struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES]; /* incremented at dispatch time */ unsigned long rq_dispatched[2]; unsigned long rq_merged; /* incremented at completion time */ unsigned long ____cacheline_aligned_in_smp rq_completed[2]; struct request_queue *queue; struct blk_mq_ctxs *ctxs; struct kobject kobj; } ____cacheline_aligned_in_smp; void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, unsigned int); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); void blk_mq_put_rq_ref(struct request *rq); /* * Internal helpers for allocating/freeing the request map */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags); struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags, unsigned int flags); int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth); /* * Internal helpers for request insertion into sw queues */ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head); void blk_mq_request_bypass_insert(struct request *rq, bool at_head, bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list); /* Used by blk_insert_cloned_request() to issue request directly */ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last); void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); /* * CPU -> queue mappings */ extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int); /* * blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue * @q: request queue * @type: the hctx type index * @cpu: CPU */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q, enum hctx_type type, unsigned int cpu) { return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]]; } /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue * @q: request queue * @flags: request command flags * @cpu: cpu ctx */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, unsigned int flags, struct blk_mq_ctx *ctx) { enum hctx_type type = HCTX_TYPE_DEFAULT; /* * The caller ensure that if REQ_HIPRI, poll must be enabled. */ if (flags & REQ_HIPRI) type = HCTX_TYPE_POLL; else if ((flags & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; return ctx->hctxs[type]; } /* * sysfs helpers */ extern void blk_mq_sysfs_init(struct request_queue *q); extern void blk_mq_sysfs_deinit(struct request_queue *q); extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q); extern int blk_mq_sysfs_register(struct request_queue *q); extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_release(struct request_queue *q); static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { return per_cpu_ptr(q->queue_ctx, cpu); } /* * This assumes per-cpu software queueing queues. They could be per-node * as well, for instance. For now this is hardcoded as-is. Note that we don't * care about preemption, since we know the ctx's are persistent. This does * mean that we can't rely on ctx always matching the currently running CPU. */ static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) { return __blk_mq_get_ctx(q, raw_smp_processor_id()); } struct blk_mq_alloc_data { /* input parameter */ struct request_queue *q; blk_mq_req_flags_t flags; unsigned int shallow_depth; unsigned int cmd_flags; /* input & output parameter */ struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; }; static inline bool blk_mq_is_sbitmap_shared(unsigned int flags) { return flags & BLK_MQ_F_TAG_HCTX_SHARED; } static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { if (data->q->elevator) return data->hctx->sched_tags; return data->hctx->tags; } static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { /* Fast path: hardware queue is not stopped most of the time. */ if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return false; /* * This barrier is used to order adding of dispatch list before and * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier * in blk_mq_start_stopped_hw_queue() so that dispatch code could * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not * empty to avoid missing dispatching requests. */ smp_mb(); return test_bit(BLK_MQ_S_STOPPED, &hctx->state); } static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) { return hctx->nr_ctx && hctx->tags; } unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part); void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q) { if (q->mq_ops->put_budget) q->mq_ops->put_budget(q); } static inline bool blk_mq_get_dispatch_budget(struct request_queue *q) { if (q->mq_ops->get_budget) return q->mq_ops->get_budget(q); return true; } static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap); else atomic_inc(&hctx->nr_active); } static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap); else atomic_dec(&hctx->nr_active); } static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap); return atomic_read(&hctx->nr_active); } static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = BLK_MQ_NO_TAG; if (rq->rq_flags & RQF_MQ_INFLIGHT) { rq->rq_flags &= ~RQF_MQ_INFLIGHT; __blk_mq_dec_active_requests(hctx); } } static inline void blk_mq_put_driver_tag(struct request *rq) { if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG) return; __blk_mq_put_driver_tag(rq->mq_hctx, rq); } static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) { int cpu; for_each_possible_cpu(cpu) qmap->mq_map[cpu] = 0; } /* * blk_mq_plug() - Get caller context plug * @q: request queue * @bio : the bio being submitted by the caller context * * Plugging, by design, may delay the insertion of BIOs into the elevator in * order to increase BIO merging opportunities. This however can cause BIO * insertion order to change from the order in which submit_bio() is being * executed in the case of multiple contexts concurrently issuing BIOs to a * device, even if these context are synchronized to tightly control BIO issuing * order. While this is not a problem with regular block devices, this ordering * change can cause write BIO failures with zoned block devices as these * require sequential write patterns to zones. Prevent this from happening by * ignoring the plug state of a BIO issuing context if the target request queue * is for a zoned block device and the BIO to plug is a write operation. * * Return current->plug if the bio can be plugged and NULL otherwise */ static inline struct blk_plug *blk_mq_plug(struct request_queue *q, struct bio *bio) { /* * For regular block devices or read operations, use the context plug * which may be NULL if blk_start_plug() was not executed. */ if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio))) return current->plug; /* Zoned block device write operation case: do not plug the BIO */ return NULL; } /* * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. */ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt) { unsigned int depth, users; if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; /* * Don't try dividing an ant */ if (bt->sb.depth == 1) return true; if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return true; users = atomic_read(&set->active_queues_shared_sbitmap); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return true; users = atomic_read(&hctx->tags->active_queues); } if (!users) return true; /* * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); return __blk_mq_active_requests(hctx) < depth; } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/uio.h> #include "kernfs-internal.h" /* * There's one kernfs_open_file for each open file and one kernfs_open_node * for each kernfs_node with one or more open files. * * kernfs_node->attr.open points to kernfs_open_node. attr.open is * protected by kernfs_open_node_lock. * * filp->private_data points to seq_file whose ->private points to * kernfs_open_file. kernfs_open_files are chained at * kernfs_open_node->files, which is protected by kernfs_open_file_mutex. */ static DEFINE_SPINLOCK(kernfs_open_node_lock); static DEFINE_MUTEX(kernfs_open_file_mutex); struct kernfs_open_node { atomic_t refcnt; atomic_t event; wait_queue_head_t poll; struct list_head files; /* goes through kernfs_open_file.list */ }; /* * kernfs_notify() may be called from any context and bounces notifications * through a work item. To minimize space overhead in kernfs_node, the * pending queue is implemented as a singly linked list of kernfs_nodes. * The list is terminated with the self pointer so that whether a * kernfs_node is on the list or not can be determined by testing the next * pointer for NULL. */ #define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) static DEFINE_SPINLOCK(kernfs_notify_lock); static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; } /* * Determine the kernfs_ops for the given kernfs_node. This function must * be called while holding an active reference. */ static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) { if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kn->attr.ops; } /* * As kernfs_seq_stop() is also called after kernfs_seq_start() or * kernfs_seq_next() failure, it needs to distinguish whether it's stopping * a seq_file iteration which is fully initialized with an active reference * or an aborted kernfs_seq_start() due to get_active failure. The * position pointer is the only context for each seq_file iteration and * thus the stop condition should be encoded in it. As the return value is * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable * choice to indicate get_active failure. * * Unfortunately, this is complicated due to the optional custom seq_file * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or * custom seq_file operations and thus can't decide whether put_active * should be performed or not only on ERR_PTR(-ENODEV). * * This is worked around by factoring out the custom seq_stop() and * put_active part into kernfs_seq_stop_active(), skipping it from * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures * that kernfs_seq_stop_active() is skipped only after get_active failure. */ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_stop) ops->seq_stop(sf, v); kernfs_put_active(of->kn); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); if (ops->seq_start) { void *next = ops->seq_start(sf, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(). Returns * !NULL if pos is at the beginning; otherwise, NULL. */ return NULL + !*ppos; } } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_next) { void *next = ops->seq_next(sf, v, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(), always * terminate after the initial read. */ ++*ppos; return NULL; } } static void kernfs_seq_stop(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; if (v != ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, v); mutex_unlock(&of->mutex); } static int kernfs_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; of->event = atomic_read(&of->kn->attr.open->event); return of->kn->attr.ops->seq_show(sf, v); } static const struct seq_operations kernfs_seq_ops = { .start = kernfs_seq_start, .next = kernfs_seq_next, .stop = kernfs_seq_stop, .show = kernfs_seq_show, }; /* * As reading a bin file can have side-effects, the exact offset and bytes * specified in read(2) call should be passed to the read callback making * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; } of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len < 0) goto out_free; if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) return seq_read_iter(iocb, iter); return kernfs_file_read_iter(iocb, iter); } /* * Copy data in from userland and pass it to the matching kernfs write * operation. * * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come on * the first write. Hint: if you're writing a value, first read the file, * modify only the the value you're changing, then write entire buffer * back. */ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; char *buf; if (of->atomic_write_len) { if (len > of->atomic_write_len) return -E2BIG; } else { len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } buf[len] = '\0'; /* guarantee string termination */ /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; } ops = kernfs_ops(of->kn); if (ops->write) len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len > 0) iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static void kernfs_vma_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); if (!of->vm_ops) return; if (!kernfs_get_active(of->kn)) return; if (of->vm_ops->open) of->vm_ops->open(vma); kernfs_put_active(of->kn); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); kernfs_put_active(of->kn); return ret; } static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = 0; if (of->vm_ops->page_mkwrite) ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); kernfs_put_active(of->kn); return ret; } static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return -EINVAL; if (!kernfs_get_active(of->kn)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); kernfs_put_active(of->kn); return ret; } #ifdef CONFIG_NUMA static int kernfs_vma_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return 0; if (!kernfs_get_active(of->kn)) return -EINVAL; ret = 0; if (of->vm_ops->set_policy) ret = of->vm_ops->set_policy(vma, new); kernfs_put_active(of->kn); return ret; } static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); struct mempolicy *pol; if (!of->vm_ops) return vma->vm_policy; if (!kernfs_get_active(of->kn)) return vma->vm_policy; pol = vma->vm_policy; if (of->vm_ops->get_policy) pol = of->vm_ops->get_policy(vma, addr); kernfs_put_active(of->kn); return pol; } #endif static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, #ifdef CONFIG_NUMA .set_policy = kernfs_vma_set_policy, .get_policy = kernfs_vma_get_policy, #endif }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; int rc; /* * mmap path and of->mutex are prone to triggering spurious lockdep * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the * comment in kernfs_file_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; mutex_lock(&of->mutex); rc = -ENODEV; if (!kernfs_get_active(of->kn)) goto out_unlock; ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); if (rc) goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() * to satisfy versions of X which crash if the mmap fails: that * substitutes a new vm_file, and we don't then want bin_vm_ops. */ if (vma->vm_file != file) goto out_put; rc = -EINVAL; if (of->mmapped && of->vm_ops != vma->vm_ops) goto out_put; /* * It is not possible to successfully wrap close. * So error if someone is trying to use close. */ rc = -EINVAL; if (vma->vm_ops && vma->vm_ops->close) goto out_put; rc = 0; of->mmapped = true; of->vm_ops = vma->vm_ops; vma->vm_ops = &kernfs_vm_ops; out_put: kernfs_put_active(of->kn); out_unlock: mutex_unlock(&of->mutex); return rc; } /** * kernfs_get_open_node - get or create kernfs_open_node * @kn: target kernfs_node * @of: kernfs_open_file for this instance of open * * If @kn->attr.open exists, increment its reference count; otherwise, * create one. @of is chained to the files list. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, -errno on failure. */ static int kernfs_get_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on, *new_on = NULL; retry: mutex_lock(&kernfs_open_file_mutex); spin_lock_irq(&kernfs_open_node_lock); if (!kn->attr.open && new_on) { kn->attr.open = new_on; new_on = NULL; } on = kn->attr.open; if (on) { atomic_inc(&on->refcnt); list_add_tail(&of->list, &on->files); } spin_unlock_irq(&kernfs_open_node_lock); mutex_unlock(&kernfs_open_file_mutex); if (on) { kfree(new_on); return 0; } /* not there, initialize a new one and retry */ new_on = kmalloc(sizeof(*new_on), GFP_KERNEL); if (!new_on) return -ENOMEM; atomic_set(&new_on->refcnt, 0); atomic_set(&new_on->event, 1); init_waitqueue_head(&new_on->poll); INIT_LIST_HEAD(&new_on->files); goto retry; } /** * kernfs_put_open_node - put kernfs_open_node * @kn: target kernfs_nodet * @of: associated kernfs_open_file * * Put @kn->attr.open and unlink @of from the files list. If * reference count reaches zero, disassociate and free it. * * LOCKING: * None. */ static void kernfs_put_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on = kn->attr.open; unsigned long flags; mutex_lock(&kernfs_open_file_mutex); spin_lock_irqsave(&kernfs_open_node_lock, flags); if (of) list_del(&of->list); if (atomic_dec_and_test(&on->refcnt)) kn->attr.open = NULL; else on = NULL; spin_unlock_irqrestore(&kernfs_open_node_lock, flags); mutex_unlock(&kernfs_open_file_mutex); kfree(on); } static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; int error = -EACCES; if (!kernfs_get_active(kn)) return -ENODEV; ops = kernfs_ops(kn); has_read = ops->seq_show || ops->read || ops->mmap; has_write = ops->write || ops->mmap; has_mmap = ops->mmap; /* see the flag definition for details */ if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { if ((file->f_mode & FMODE_WRITE) && (!(inode->i_mode & S_IWUGO) || !has_write)) goto err_out; if ((file->f_mode & FMODE_READ) && (!(inode->i_mode & S_IRUGO) || !has_read)) goto err_out; } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL); if (!of) goto err_out; /* * The following is done to give a different lockdep key to * @of->mutex for files which implement mmap. This is a rather * crude way to avoid false positive lockdep warning around * mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under * which mm->mmap_lock nests, while holding @of->mutex. As each * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * * Both paths of the branch look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); else mutex_init(&of->mutex); of->kn = kn; of->file = file; /* * Write path needs to atomic_write_len outside active reference. * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; error = -EINVAL; /* * ->seq_show is incompatible with ->prealloc, * as seq_read does its own allocation. * ->read must be used instead. */ if (ops->prealloc && ops->seq_show) goto err_free; if (ops->prealloc) { int len = of->atomic_write_len ?: PAGE_SIZE; of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL); error = -ENOMEM; if (!of->prealloc_buf) goto err_free; mutex_init(&of->prealloc_mutex); } /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. */ if (ops->seq_show) error = seq_open(file, &kernfs_seq_ops); else error = seq_open(file, NULL); if (error) goto err_free; of->seq_file = file->private_data; of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) file->f_mode |= FMODE_PWRITE; /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) goto err_seq_release; if (ops->open) { /* nobody has access to @of yet, skip @of->mutex */ error = ops->open(of); if (error) goto err_put_node; } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; err_put_node: kernfs_put_open_node(kn, of); err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); kfree(of); err_out: kernfs_put_active(kn); return error; } /* used from release/drain to ensure that ->release() is called exactly once */ static void kernfs_release_file(struct kernfs_node *kn, struct kernfs_open_file *of) { /* * @of is guaranteed to have no other file operations in flight and * we just want to synchronize release and drain paths. * @kernfs_open_file_mutex is enough. @of->mutex can't be used * here because drain path may be called from places which can * cause circular dependency. */ lockdep_assert_held(&kernfs_open_file_mutex); if (!of->released) { /* * A file is never detached without being released and we * need to be able to release files which are deactivated * and being drained. Don't use kernfs_ops(). */ kn->attr.ops->release(of); of->released = true; } } static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { mutex_lock(&kernfs_open_file_mutex); kernfs_release_file(kn, of); mutex_unlock(&kernfs_open_file_mutex); } kernfs_put_open_node(kn, of); seq_release(inode, filp); kfree(of->prealloc_buf); kfree(of); return 0; } void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE))) return; spin_lock_irq(&kernfs_open_node_lock); on = kn->attr.open; if (on) atomic_inc(&on->refcnt); spin_unlock_irq(&kernfs_open_node_lock); if (!on) return; mutex_lock(&kernfs_open_file_mutex); list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); if (kn->flags & KERNFS_HAS_MMAP) unmap_mapping_range(inode->i_mapping, 0, 0, 1); if (kn->flags & KERNFS_HAS_RELEASE) kernfs_release_file(kn, of); } mutex_unlock(&kernfs_open_file_mutex); kernfs_put_open_node(kn, NULL); } /* * Kernfs attribute files are pollable. The idea is that you read * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. * Reminder: this only works for attributes which actively support * it, and it is not possible to test an attribute from userspace * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ __poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) { struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); struct kernfs_open_node *on = kn->attr.open; poll_wait(of->file, &on->poll, wait); if (of->event != atomic_read(&on->event)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; return DEFAULT_POLLMASK; } static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; if (!kernfs_get_active(kn)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) ret = kn->attr.ops->poll(of, wait); else ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); return ret; } static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); kn = kernfs_notify_list; if (kn == KERNFS_NOTIFY_EOL) { spin_unlock_irq(&kernfs_notify_lock); return; } kernfs_notify_list = kn->attr.notify_next; kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); /* kick fsnotify */ mutex_lock(&kernfs_mutex); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; struct inode *inode; struct qstr name; /* * We want fsnotify_modify() on @kn but as the * modifications aren't originating from userland don't * have the matching @file available. Look up the inodes * and generate the events manually. */ inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, p_inode, &name, inode, 0); iput(p_inode); } kernfs_put(parent); } if (!p_inode) fsnotify_inode(inode, FS_MODIFY); iput(inode); } mutex_unlock(&kernfs_mutex); kernfs_put(kn); goto repeat; } /** * kernfs_notify - notify a kernfs file * @kn: file to notify * * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any * context. */ void kernfs_notify(struct kernfs_node *kn) { static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); unsigned long flags; struct kernfs_open_node *on; if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) return; /* kick poll immediately */ spin_lock_irqsave(&kernfs_open_node_lock, flags); on = kn->attr.open; if (on) { atomic_inc(&on->event); wake_up_interruptible(&on->poll); } spin_unlock_irqrestore(&kernfs_open_node_lock, flags); /* schedule work to kick fsnotify */ spin_lock_irqsave(&kernfs_notify_lock, flags); if (!kn->attr.notify_next) { kernfs_get(kn); kn->attr.notify_next = kernfs_notify_list; kernfs_notify_list = kn; schedule_work(&kernfs_notify_work); } spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, .llseek = generic_file_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, }; /** * __kernfs_create_file - kernfs internal function to create a file * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file * @uid: uid of the file * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file * @ns: optional namespace tag of the file * @key: lockdep key for the file's active_ref, %NULL to disable lockdep * * Returns the created node on success, ERR_PTR() value on error. */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { struct kernfs_node *kn; unsigned flags; int rc; flags = KERNFS_FILE; kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); kn->attr.ops = ops; kn->attr.size = size; kn->ns = ns; kn->priv = priv; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { lockdep_init_map(&kn->dep_map, "kn->active", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif /* * kn->attr.ops is accesible only while holding active ref. We * need to know whether some ops are implemented outside active * ref. Cache their existence in flags. */ if (ops->seq_show) kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; if (ops->release) kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); } return kn; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KERNEL_PRINTK_RINGBUFFER_H #define _KERNEL_PRINTK_RINGBUFFER_H #include <linux/atomic.h> #include <linux/dev_printk.h> /* * Meta information about each stored message. * * All fields are set by the printk code except for @seq, which is * set by the ringbuffer code. */ struct printk_info { u64 seq; /* sequence number */ u64 ts_nsec; /* timestamp in nanoseconds */ u16 text_len; /* length of text message */ u8 facility; /* syslog facility */ u8 flags:5; /* internal record flags */ u8 level:3; /* syslog level */ u32 caller_id; /* thread id or processor id */ struct dev_printk_info dev_info; }; /* * A structure providing the buffers, used by writers and readers. * * Writers: * Using prb_rec_init_wr(), a writer sets @text_buf_size before calling * prb_reserve(). On success, prb_reserve() sets @info and @text_buf to * buffers reserved for that writer. * * Readers: * Using prb_rec_init_rd(), a reader sets all fields before calling * prb_read_valid(). Note that the reader provides the @info and @text_buf, * buffers. On success, the struct pointed to by @info will be filled and * the char array pointed to by @text_buf will be filled with text data. */ struct printk_record { struct printk_info *info; char *text_buf; unsigned int text_buf_size; }; /* Specifies the logical position and span of a data block. */ struct prb_data_blk_lpos { unsigned long begin; unsigned long next; }; /* * A descriptor: the complete meta-data for a record. * * @state_var: A bitwise combination of descriptor ID and descriptor state. */ struct prb_desc { atomic_long_t state_var; struct prb_data_blk_lpos text_blk_lpos; }; /* A ringbuffer of "ID + data" elements. */ struct prb_data_ring { unsigned int size_bits; char *data; atomic_long_t head_lpos; atomic_long_t tail_lpos; }; /* A ringbuffer of "struct prb_desc" elements. */ struct prb_desc_ring { unsigned int count_bits; struct prb_desc *descs; struct printk_info *infos; atomic_long_t head_id; atomic_long_t tail_id; }; /* * The high level structure representing the printk ringbuffer. * * @fail: Count of failed prb_reserve() calls where not even a data-less * record was created. */ struct printk_ringbuffer { struct prb_desc_ring desc_ring; struct prb_data_ring text_data_ring; atomic_long_t fail; }; /* * Used by writers as a reserve/commit handle. * * @rb: Ringbuffer where the entry is reserved. * @irqflags: Saved irq flags to restore on entry commit. * @id: ID of the reserved descriptor. * @text_space: Total occupied buffer space in the text data ring, including * ID, alignment padding, and wrapping data blocks. * * This structure is an opaque handle for writers. Its contents are only * to be used by the ringbuffer implementation. */ struct prb_reserved_entry { struct printk_ringbuffer *rb; unsigned long irqflags; unsigned long id; unsigned int text_space; }; /* The possible responses of a descriptor state-query. */ enum desc_state { desc_miss = -1, /* ID mismatch (pseudo state) */ desc_reserved = 0x0, /* reserved, in use by writer */ desc_committed = 0x1, /* committed by writer, could get reopened */ desc_finalized = 0x2, /* committed, no further modification allowed */ desc_reusable = 0x3, /* free, not yet used by any writer */ }; #define _DATA_SIZE(sz_bits) (1UL << (sz_bits)) #define _DESCS_COUNT(ct_bits) (1U << (ct_bits)) #define DESC_SV_BITS (sizeof(unsigned long) * 8) #define DESC_FLAGS_SHIFT (DESC_SV_BITS - 2) #define DESC_FLAGS_MASK (3UL << DESC_FLAGS_SHIFT) #define DESC_STATE(sv) (3UL & (sv >> DESC_FLAGS_SHIFT)) #define DESC_SV(id, state) (((unsigned long)state << DESC_FLAGS_SHIFT) | id) #define DESC_ID_MASK (~DESC_FLAGS_MASK) #define DESC_ID(sv) ((sv) & DESC_ID_MASK) #define FAILED_LPOS 0x1 #define NO_LPOS 0x3 #define FAILED_BLK_LPOS \ { \ .begin = FAILED_LPOS, \ .next = FAILED_LPOS, \ } /* * Descriptor Bootstrap * * The descriptor array is minimally initialized to allow immediate usage * by readers and writers. The requirements that the descriptor array * initialization must satisfy: * * Req1 * The tail must point to an existing (committed or reusable) descriptor. * This is required by the implementation of prb_first_seq(). * * Req2 * Readers must see that the ringbuffer is initially empty. * * Req3 * The first record reserved by a writer is assigned sequence number 0. * * To satisfy Req1, the tail initially points to a descriptor that is * minimally initialized (having no data block, i.e. data-less with the * data block's lpos @begin and @next values set to FAILED_LPOS). * * To satisfy Req2, the initial tail descriptor is initialized to the * reusable state. Readers recognize reusable descriptors as existing * records, but skip over them. * * To satisfy Req3, the last descriptor in the array is used as the initial * head (and tail) descriptor. This allows the first record reserved by a * writer (head + 1) to be the first descriptor in the array. (Only the first * descriptor in the array could have a valid sequence number of 0.) * * The first time a descriptor is reserved, it is assigned a sequence number * with the value of the array index. A "first time reserved" descriptor can * be recognized because it has a sequence number of 0 but does not have an * index of 0. (Only the first descriptor in the array could have a valid * sequence number of 0.) After the first reservation, all future reservations * (recycling) simply involve incrementing the sequence number by the array * count. * * Hack #1 * Only the first descriptor in the array is allowed to have the sequence * number 0. In this case it is not possible to recognize if it is being * reserved the first time (set to index value) or has been reserved * previously (increment by the array count). This is handled by _always_ * incrementing the sequence number by the array count when reserving the * first descriptor in the array. In order to satisfy Req3, the sequence * number of the first descriptor in the array is initialized to minus * the array count. Then, upon the first reservation, it is incremented * to 0, thus satisfying Req3. * * Hack #2 * prb_first_seq() can be called at any time by readers to retrieve the * sequence number of the tail descriptor. However, due to Req2 and Req3, * initially there are no records to report the sequence number of * (sequence numbers are u64 and there is nothing less than 0). To handle * this, the sequence number of the initial tail descriptor is initialized * to 0. Technically this is incorrect, because there is no record with * sequence number 0 (yet) and the tail descriptor is not the first * descriptor in the array. But it allows prb_read_valid() to correctly * report the existence of a record for _any_ given sequence number at all * times. Bootstrapping is complete when the tail is pushed the first * time, thus finally pointing to the first descriptor reserved by a * writer, which has the assigned sequence number 0. */ /* * Initiating Logical Value Overflows * * Both logical position (lpos) and ID values can be mapped to array indexes * but may experience overflows during the lifetime of the system. To ensure * that printk_ringbuffer can handle the overflows for these types, initial * values are chosen that map to the correct initial array indexes, but will * result in overflows soon. * * BLK0_LPOS * The initial @head_lpos and @tail_lpos for data rings. It is at index * 0 and the lpos value is such that it will overflow on the first wrap. * * DESC0_ID * The initial @head_id and @tail_id for the desc ring. It is at the last * index of the descriptor array (see Req3 above) and the ID value is such * that it will overflow on the second wrap. */ #define BLK0_LPOS(sz_bits) (-(_DATA_SIZE(sz_bits))) #define DESC0_ID(ct_bits) DESC_ID(-(_DESCS_COUNT(ct_bits) + 1)) #define DESC0_SV(ct_bits) DESC_SV(DESC0_ID(ct_bits), desc_reusable) /* * Define a ringbuffer with an external text data buffer. The same as * DEFINE_PRINTKRB() but requires specifying an external buffer for the * text data. * * Note: The specified external buffer must be of the size: * 2 ^ (descbits + avgtextbits) */ #define _DEFINE_PRINTKRB(name, descbits, avgtextbits, text_buf) \ static struct prb_desc _##name##_descs[_DESCS_COUNT(descbits)] = { \ /* the initial head and tail */ \ [_DESCS_COUNT(descbits) - 1] = { \ /* reusable */ \ .state_var = ATOMIC_INIT(DESC0_SV(descbits)), \ /* no associated data block */ \ .text_blk_lpos = FAILED_BLK_LPOS, \ }, \ }; \ static struct printk_info _##name##_infos[_DESCS_COUNT(descbits)] = { \ /* this will be the first record reserved by a writer */ \ [0] = { \ /* will be incremented to 0 on the first reservation */ \ .seq = -(u64)_DESCS_COUNT(descbits), \ }, \ /* the initial head and tail */ \ [_DESCS_COUNT(descbits) - 1] = { \ /* reports the first seq value during the bootstrap phase */ \ .seq = 0, \ }, \ }; \ static struct printk_ringbuffer name = { \ .desc_ring = { \ .count_bits = descbits, \ .descs = &_##name##_descs[0], \ .infos = &_##name##_infos[0], \ .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ }, \ .text_data_ring = { \ .size_bits = (avgtextbits) + (descbits), \ .data = text_buf, \ .head_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ .tail_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ }, \ .fail = ATOMIC_LONG_INIT(0), \ } /** * DEFINE_PRINTKRB() - Define a ringbuffer. * * @name: The name of the ringbuffer variable. * @descbits: The number of descriptors as a power-of-2 value. * @avgtextbits: The average text data size per record as a power-of-2 value. * * This is a macro for defining a ringbuffer and all internal structures * such that it is ready for immediate use. See _DEFINE_PRINTKRB() for a * variant where the text data buffer can be specified externally. */ #define DEFINE_PRINTKRB(name, descbits, avgtextbits) \ static char _##name##_text[1U << ((avgtextbits) + (descbits))] \ __aligned(__alignof__(unsigned long)); \ _DEFINE_PRINTKRB(name, descbits, avgtextbits, &_##name##_text[0]) /* Writer Interface */ /** * prb_rec_init_wd() - Initialize a buffer for writing records. * * @r: The record to initialize. * @text_buf_size: The needed text buffer size. */ static inline void prb_rec_init_wr(struct printk_record *r, unsigned int text_buf_size) { r->info = NULL; r->text_buf = NULL; r->text_buf_size = text_buf_size; } bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r); bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size); void prb_commit(struct prb_reserved_entry *e); void prb_final_commit(struct prb_reserved_entry *e); void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int text_buf_size, struct prb_desc *descs, unsigned int descs_count_bits, struct printk_info *infos); unsigned int prb_record_text_space(struct prb_reserved_entry *e); /* Reader Interface */ /** * prb_rec_init_rd() - Initialize a buffer for reading records. * * @r: The record to initialize. * @info: A buffer to store record meta-data. * @text_buf: A buffer to store text data. * @text_buf_size: The size of @text_buf. * * Initialize all the fields that a reader is interested in. All arguments * (except @r) are optional. Only record data for arguments that are * non-NULL or non-zero will be read. */ static inline void prb_rec_init_rd(struct printk_record *r, struct printk_info *info, char *text_buf, unsigned int text_buf_size) { r->info = info; r->text_buf = text_buf; r->text_buf_size = text_buf_size; } /** * prb_for_each_record() - Iterate over the records of a ringbuffer. * * @from: The sequence number to begin with. * @rb: The ringbuffer to iterate over. * @s: A u64 to store the sequence number on each iteration. * @r: A printk_record to store the record on each iteration. * * This is a macro for conveniently iterating over a ringbuffer. * Note that @s may not be the sequence number of the record on each * iteration. For the sequence number, @r->info->seq should be checked. * * Context: Any context. */ #define prb_for_each_record(from, rb, s, r) \ for ((s) = from; prb_read_valid(rb, s, r); (s) = (r)->info->seq + 1) /** * prb_for_each_info() - Iterate over the meta data of a ringbuffer. * * @from: The sequence number to begin with. * @rb: The ringbuffer to iterate over. * @s: A u64 to store the sequence number on each iteration. * @i: A printk_info to store the record meta data on each iteration. * @lc: An unsigned int to store the text line count of each record. * * This is a macro for conveniently iterating over a ringbuffer. * Note that @s may not be the sequence number of the record on each * iteration. For the sequence number, @r->info->seq should be checked. * * Context: Any context. */ #define prb_for_each_info(from, rb, s, i, lc) \ for ((s) = from; prb_read_valid_info(rb, s, i, lc); (s) = (i)->seq + 1) bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r); bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count); u64 prb_first_valid_seq(struct printk_ringbuffer *rb); u64 prb_next_seq(struct printk_ringbuffer *rb); #endif /* _KERNEL_PRINTK_RINGBUFFER_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Socket Filter Data Structures */ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ #include <stdarg.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/capability.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <crypto/sha.h> #include <net/sch_generic.h> #include <asm/byteorder.h> #include <uapi/linux/filter.h> #include <uapi/linux/bpf.h> struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; struct ctl_table; struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */ #define BPF_REG_ARG1 BPF_REG_1 #define BPF_REG_ARG2 BPF_REG_2 #define BPF_REG_ARG3 BPF_REG_3 #define BPF_REG_ARG4 BPF_REG_4 #define BPF_REG_ARG5 BPF_REG_5 #define BPF_REG_CTX BPF_REG_6 #define BPF_REG_FP BPF_REG_10 /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 #define BPF_REG_TMP BPF_REG_2 /* scratch reg */ #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) #define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Speculative Store Bypass */ #define BPF_NOSPEC 0xc0 /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */ #define BPF_SYM_ELF_TYPE 't' /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ #define BPF_ALU64_REG(OP, DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_ALU32_REG(OP, DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM(OP, DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_ALU32_IMM(OP, DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ #define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 }) static inline bool insn_is_zext(const struct bpf_insn *insn) { return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) #define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ #define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ #define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Memory load, dst_reg = *(uint *) (src_reg + off16) */ #define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ #define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ #define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 }) /* Relative call */ #define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT }) /* Function call */ #define BPF_CAST_CALL(x) \ ((u64 (*)(u64, u64, u64, u64, u64))(x)) #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((FUNC) - __bpf_call_base) }) /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) /* Program exit */ #define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Speculation barrier */ #define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K)) #define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \ }) #define bpf_size_to_bytes(bpf_size) \ ({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \ }) #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ }) #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) #define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) #define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) #define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) #define __BPF_REG_0(...) __BPF_PAD(5) #define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) #define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) #define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) #define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) #define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) #define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) #define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) #define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a #define __BPF_V void #define __BPF_N #define __BPF_DECL_ARGS(t, a) t a #define __BPF_DECL_REGS(t, a) u64 a #define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) #define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define __NOATTR #define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) #define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 #if BITS_PER_LONG == 64 # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #else # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 #endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; struct sock_fprog_kern { u16 len; struct sock_filter *filter; }; /* Some arches need doubleword alignment for their instructions and/or data */ #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { u32 pages; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); /* Instructions for interpreter */ struct sock_filter insns[0]; struct bpf_insn insnsi[]; }; struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); #define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ u32 __ret; \ cant_migrate(); \ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ struct bpf_prog_stats *__stats; \ u64 __start = sched_clock(); \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ __stats = this_cpu_ptr(prog->aux->stats); \ u64_stats_update_begin(&__stats->syncp); \ __stats->cnt++; \ __stats->nsecs += sched_clock() - __start; \ u64_stats_update_end(&__stats->syncp); \ } else { \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ } \ __ret; }) #define BPF_PROG_RUN(prog, ctx) \ __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) /* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. * * For non RT enabled kernels migrate_disable/enable() maps to * preempt_disable/enable(), i.e. it disables also preemption. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) { u32 ret; migrate_disable(); ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func); migrate_enable(); return ret; } #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end; }; struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; }; }; struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; struct bpf_map *map; u32 kern_flags; struct bpf_nh_params nh; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; *saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb); } /* Restore data saved by bpf_compute_data_pointers(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; cb->data_end = saved_data_end; } static inline u8 *bpf_skb_cb(struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); } res = BPF_PROG_RUN(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u32 res; migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res; } static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { /* Caller needs to hold rcu_read_lock() (!), otherwise program * can be released while still running, or map elements could be * freed early while still having concurrent users. XDP fastpath * already takes rcu_read_lock() when fetching the program, so * it's not necessary here anymore. */ struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (ri->map) ri->map = NULL; return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); } static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) { /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC; } static inline u32 bpf_ctx_off_adjust_machine(u32 size) { const u32 size_machine = sizeof(unsigned long); if (size > size_machine && size % size_machine == 0) size = size_machine; return size; } static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { return size <= size_default && (size & (size - 1)) == 0; } static inline u8 bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN return access_off; #else return size_default - (access_off + size); #endif } #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); set_memory_ro((unsigned long)fp, fp->pages); } #endif } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); set_memory_ro((unsigned long)hdr, hdr->pages); set_memory_x((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) { unsigned long real_start = (unsigned long)fp->bpf_func; unsigned long addr = real_start & PAGE_MASK; return (void *)addr; } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { return sk_filter_trim_cap(sk, skb, 1); } struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); void bpf_prog_free_linfo(struct bpf_prog *prog); void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); void bpf_prog_free_jited_linfo(struct bpf_prog *prog); void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog); struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { __bpf_prog_free(fp); } typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen); int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); void bpf_clear_redirect_map(struct bpf_map *map); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { unsigned int len; if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE; return 0; } /* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); void xdp_do_flush(void); /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as * it is no longer only flushing maps. Keep this define for compatibility * until all drivers are updated - do not use xdp_do_flush_map() in new code! */ #define xdp_do_flush_map xdp_do_flush void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, u32 hash) { return NULL; } #endif #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { pr_err("flen=%u proglen=%u pass=%u image=%p from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } static inline bool bpf_jit_is_ebpf(void) { # ifdef CONFIG_HAVE_EBPF_JIT return true; # else return false; # endif } static inline bool ebpf_jit_enabled(void) { return bpf_jit_enable && bpf_jit_is_ebpf(); } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN)) return false; return true; } static inline bool bpf_jit_kallsyms_enabled(void) { /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true; return false; } const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { const char *ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; return ret; } void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ static inline bool ebpf_jit_enabled(void) { return false; } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { return false; } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } static inline int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { return -ENOTSUPP; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } static inline bool bpf_jit_kallsyms_enabled(void) { return false; } static inline const char * __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { return NULL; } static inline bool is_bpf_text_address(unsigned long addr) { return false; } static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { return NULL; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) { switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false; default: return true; } } static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: #define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; } } void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size); static inline void *bpf_load_pointer(const struct sk_buff *skb, int k, unsigned int size, void *buffer) { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); return bpf_internal_load_pointer_neg_helper(skb, k, size); } static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ }; struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */ }; struct bpf_sysctl_kern { struct ctl_table_header *head; struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; s32 retval; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; bool no_reuseport; }; extern struct static_key_false bpf_sk_lookup_enabled; /* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */ #define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #if IS_ENABLED(CONFIG_IPV6) static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* __LINUX_FILTER_H__ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PROCESSOR_H #define _ASM_X86_PROCESSOR_H #include <asm/processor-flags.h> /* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; struct io_bitmap; struct vm86; #include <asm/math_emu.h> #include <asm/segment.h> #include <asm/types.h> #include <uapi/asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> #include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> #include <asm/special_insns.h> #include <asm/fpu/types.h> #include <asm/unwind_hints.h> #include <asm/vmxfeatures.h> #include <asm/vdso/processor.h> #include <linux/personality.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/math64.h> #include <linux/err.h> #include <linux/irqflags.h> #include <linux/mem_encrypt.h> /* * We handle most unaligned accesses in hardware. On the other hand * unaligned DMA can be quite expensive on some Nehalem processors. * * Based on this we disable the IP header alignment in network drivers. */ #define NET_IP_ALIGN 0 #define HBP_NUM 4 /* * These alignment constraints are for performance in the vSMP case, * but in the task_struct case we must also meet hardware imposed * alignment requirements of the FPU state: */ #ifdef CONFIG_X86_VSMP # define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT) # define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT) #else # define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state) # define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif enum tlb_infos { ENTRIES, NR_INFO }; extern u16 __read_mostly tlb_lli_4k[NR_INFO]; extern u16 __read_mostly tlb_lli_2m[NR_INFO]; extern u16 __read_mostly tlb_lli_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_4k[NR_INFO]; extern u16 __read_mostly tlb_lld_2m[NR_INFO]; extern u16 __read_mostly tlb_lld_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_1g[NR_INFO]; /* * CPU type and hardware bug flags. Kept separately for each CPU. * Members of this structure are referenced in head_32.S, so think twice * before touching them. [mj] */ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; __u8 x86_stepping; #ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; #endif #ifdef CONFIG_X86_VMX_FEATURE_NAMES __u32 vmx_capability[NVMXINTS]; #endif __u8 x86_virt_bits; __u8 x86_phys_bits; /* CPUID returned core id bits: */ __u8 x86_coreid_bits; __u8 cu_id; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ int cpuid_level; /* * Align to size of unsigned long because the x86_capability array * is passed to bitops which require the alignment. Use unnamed * union to enforce the array is aligned to size of unsigned long. */ union { __u32 x86_capability[NCAPINTS + NBUGINTS]; unsigned long x86_capability_alignment; }; char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values, valid only on the BSP: */ int x86_cache_max_rmid; /* max index */ int x86_cache_occ_scale; /* scale to bytes */ int x86_cache_mbm_width_offset; int x86_power; unsigned long loops_per_jiffy; /* cpuid returned max cores value: */ u16 x86_max_cores; u16 apicid; u16 initial_apicid; u16 x86_clflush_size; /* number of cores as seen by the OS: */ u16 booted_cores; /* Physical processor id: */ u16 phys_proc_id; /* Logical processor id: */ u16 logical_proc_id; /* Core id: */ u16 cpu_core_id; u16 cpu_die_id; u16 logical_die_id; /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; /* Address space bits used by the cache internally */ u8 x86_cache_bits; unsigned initialized : 1; } __randomize_layout; struct cpuid_regs { u32 eax, ebx, ecx, edx; }; enum cpuid_regs_idx { CPUID_EAX = 0, CPUID_EBX, CPUID_ECX, CPUID_EDX, }; #define X86_VENDOR_INTEL 0 #define X86_VENDOR_CYRIX 1 #define X86_VENDOR_AMD 2 #define X86_VENDOR_UMC 3 #define X86_VENDOR_CENTAUR 5 #define X86_VENDOR_TRANSMETA 7 #define X86_VENDOR_NSC 8 #define X86_VENDOR_HYGON 9 #define X86_VENDOR_ZHAOXIN 10 #define X86_VENDOR_NUM 11 #define X86_VENDOR_UNKNOWN 0xff /* * capabilities of CPUs */ extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) #else #define cpu_info boot_cpu_data #define cpu_data(cpu) boot_cpu_data #endif extern const struct seq_operations cpuinfo_op; #define cache_line_size() (boot_cpu_data.x86_cache_alignment) extern void cpu_detect(struct cpuinfo_x86 *c); static inline unsigned long long l1tf_pfn_limit(void) { return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } void init_cpu_devs(void); void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); void print_cpu_msr(struct cpuinfo_x86 *); #ifdef CONFIG_X86_32 extern int have_cpuid_p(void); #else static inline int have_cpuid_p(void) { return 1; } #endif static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { /* ecx is often an input as well as an output. */ asm volatile("cpuid" : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx) : "0" (*eax), "2" (*ecx) : "memory"); } #define native_cpuid_reg(reg) \ static inline unsigned int native_cpuid_##reg(unsigned int op) \ { \ unsigned int eax = op, ebx, ecx = 0, edx; \ \ native_cpuid(&eax, &ebx, &ecx, &edx); \ \ return reg; \ } /* * Native CPUID functions returning a single datum. */ native_cpuid_reg(eax) native_cpuid_reg(ebx) native_cpuid_reg(ecx) native_cpuid_reg(edx) /* * Friendlier CR3 helpers. */ static inline unsigned long read_cr3_pa(void) { return __read_cr3() & CR3_ADDR_MASK; } static inline unsigned long native_read_cr3_pa(void) { return __native_read_cr3() & CR3_ADDR_MASK; } static inline void load_cr3(pgd_t *pgdir) { write_cr3(__sme_pa(pgdir)); } /* * Note that while the legacy 'TSS' name comes from 'Task State Segment', * on modern x86 CPUs the TSS also holds information important to 64-bit mode, * unrelated to the task-switch mechanism: */ #ifdef CONFIG_X86_32 /* This is the TSS defined by the hardware. */ struct x86_hw_tss { unsigned short back_link, __blh; unsigned long sp0; unsigned short ss0, __ss0h; unsigned long sp1; /* * We don't use ring 1, so ss1 is a convenient scratch space in * the same cacheline as sp0. We use ss1 to cache the value in * MSR_IA32_SYSENTER_CS. When we context switch * MSR_IA32_SYSENTER_CS, we first check if the new value being * written matches ss1, and, if it's not, then we wrmsr the new * value and update ss1. * * The only reason we context switch MSR_IA32_SYSENTER_CS is * that we set it to zero in vm86 tasks to avoid corrupting the * stack if we were to go through the sysenter path from vm86 * mode. */ unsigned short ss1; /* MSR_IA32_SYSENTER_CS */ unsigned short __ss1h; unsigned long sp2; unsigned short ss2, __ss2h; unsigned long __cr3; unsigned long ip; unsigned long flags; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long bx; unsigned long sp; unsigned long bp; unsigned long si; unsigned long di; unsigned short es, __esh; unsigned short cs, __csh; unsigned short ss, __ssh; unsigned short ds, __dsh; unsigned short fs, __fsh; unsigned short gs, __gsh; unsigned short ldt, __ldth; unsigned short trace; unsigned short io_bitmap_base; } __attribute__((packed)); #else struct x86_hw_tss { u32 reserved1; u64 sp0; /* * We store cpu_current_top_of_stack in sp1 so it's always accessible. * Linux does not use ring 1, so sp1 is not otherwise needed. */ u64 sp1; /* * Since Linux does not use ring 2, the 'sp2' slot is unused by * hardware. entry_SYSCALL_64 uses it as scratch space to stash * the user RSP value. */ u64 sp2; u64 reserved2; u64 ist[7]; u32 reserved3; u32 reserved4; u16 reserved5; u16 io_bitmap_base; } __attribute__((packed)); #endif /* * IO-bitmap sizes: */ #define IO_BITMAP_BITS 65536 #define IO_BITMAP_BYTES (IO_BITMAP_BITS / BITS_PER_BYTE) #define IO_BITMAP_LONGS (IO_BITMAP_BYTES / sizeof(long)) #define IO_BITMAP_OFFSET_VALID_MAP \ (offsetof(struct tss_struct, io_bitmap.bitmap) - \ offsetof(struct tss_struct, x86_tss)) #define IO_BITMAP_OFFSET_VALID_ALL \ (offsetof(struct tss_struct, io_bitmap.mapall) - \ offsetof(struct tss_struct, x86_tss)) #ifdef CONFIG_X86_IOPL_IOPERM /* * sizeof(unsigned long) coming from an extra "long" at the end of the * iobitmap. The limit is inclusive, i.e. the last valid byte. */ # define __KERNEL_TSS_LIMIT \ (IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \ sizeof(unsigned long) - 1) #else # define __KERNEL_TSS_LIMIT \ (offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1) #endif /* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */ #define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) struct entry_stack { char stack[PAGE_SIZE]; }; struct entry_stack_page { struct entry_stack stack; } __aligned(PAGE_SIZE); /* * All IO bitmap related data stored in the TSS: */ struct x86_io_bitmap { /* The sequence number of the last active bitmap. */ u64 prev_sequence; /* * Store the dirty size of the last io bitmap offender. The next * one will have to do the cleanup as the switch out to a non io * bitmap user will just set x86_tss.io_bitmap_base to a value * outside of the TSS limit. So for sane tasks there is no need to * actually touch the io_bitmap at all. */ unsigned int prev_max; /* * The extra 1 is there because the CPU will access an * additional byte beyond the end of the IO permission * bitmap. The extra byte must be all 1 bits, and must * be within the limit. */ unsigned long bitmap[IO_BITMAP_LONGS + 1]; /* * Special I/O bitmap to emulate IOPL(3). All bytes zero, * except the additional byte at the end. */ unsigned long mapall[IO_BITMAP_LONGS + 1]; }; struct tss_struct { /* * The fixed hardware portion. This must not cross a page boundary * at risk of violating the SDM's advice and potentially triggering * errata. */ struct x86_hw_tss x86_tss; struct x86_io_bitmap io_bitmap; } __aligned(PAGE_SIZE); DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); /* Per CPU interrupt stacks */ struct irq_stack { char stack[IRQ_STACK_SIZE]; } __aligned(IRQ_STACK_SIZE); DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); #else /* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ #define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 #endif #ifdef CONFIG_X86_64 struct fixed_percpu_data { /* * GCC hardcodes the stack canary as %gs:40. Since the * irq_stack is the object at %gs:0, we reserve the bottom * 48 bytes of the irq stack for the canary. * * Once we are willing to require -mstack-protector-guard-symbol= * support for x86_64 stackprotector, we can get rid of this. */ char gs_base[40]; unsigned long stack_canary; }; DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible; DECLARE_INIT_PER_CPU(fixed_percpu_data); static inline unsigned long cpu_kernelmode_gs_base(int cpu) { return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu); } DECLARE_PER_CPU(unsigned int, irq_count); extern asmlinkage void ignore_sysret(void); /* Save actual FS/GS selectors and bases to current->thread */ void current_save_fsgs(void); #else /* X86_64 */ #ifdef CONFIG_STACKPROTECTOR DECLARE_PER_CPU(unsigned long, __stack_chk_guard); #endif /* Per CPU softirq stack pointer */ DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr); #endif /* X86_64 */ extern unsigned int fpu_kernel_xstate_size; extern unsigned int fpu_user_xstate_size; struct perf_event; struct thread_struct { /* Cached TLS descriptors: */ struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; #ifdef CONFIG_X86_32 unsigned long sp0; #endif unsigned long sp; #ifdef CONFIG_X86_32 unsigned long sysenter_cs; #else unsigned short es; unsigned short ds; unsigned short fsindex; unsigned short gsindex; #endif #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; #else /* * XXX: this could presumably be unsigned short. Alternatively, * 32-bit kernels could be taught to use fsindex instead. */ unsigned long fs; unsigned long gs; #endif /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ unsigned long virtual_dr6; /* Keep track of the exact dr7 value set by the user */ unsigned long ptrace_dr7; /* Fault info: */ unsigned long cr2; unsigned long trap_nr; unsigned long error_code; #ifdef CONFIG_VM86 /* Virtual 86 mode info */ struct vm86 *vm86; #endif /* IO permissions: */ struct io_bitmap *io_bitmap; /* * IOPL. Priviledge level dependent I/O permission which is * emulated via the I/O bitmap to prevent user space from disabling * interrupts. */ unsigned long iopl_emul; unsigned int iopl_warn:1; /* Floating point and extended processor state */ struct fpu fpu; /* * WARNING: 'fpu' is dynamically-sized. It *MUST* be at * the end. */ }; /* Whitelist the FPU state from the task_struct for hardened usercopy. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = offsetof(struct thread_struct, fpu.state); *size = fpu_kernel_xstate_size; } static inline void native_load_sp0(unsigned long sp0) { this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } static __always_inline void native_swapgs(void) { #ifdef CONFIG_X86_64 asm volatile("swapgs" ::: "memory"); #endif } static inline unsigned long current_top_of_stack(void) { /* * We can't read directly from tss.sp0: sp0 on x86_32 is special in * and around vm86 mode and sp0 on x86_64 is special because of the * entry trampoline. */ return this_cpu_read_stable(cpu_current_top_of_stack); } static inline bool on_thread_stack(void) { return (unsigned long)(current_top_of_stack() - current_stack_pointer) < THREAD_SIZE; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define __cpuid native_cpuid static inline void load_sp0(unsigned long sp0) { native_load_sp0(sp0); } #endif /* CONFIG_PARAVIRT_XXL */ /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); /* * Generic CPUID function * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx * resulting in stale register contents being returned. */ static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { *eax = op; *ecx = 0; __cpuid(eax, ebx, ecx, edx); } /* Some CPUID calls want 'count' to be placed in ecx */ static inline void cpuid_count(unsigned int op, int count, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { *eax = op; *ecx = count; __cpuid(eax, ebx, ecx, edx); } /* * CPUID functions returning a single datum */ static inline unsigned int cpuid_eax(unsigned int op) { unsigned int eax, ebx, ecx, edx; cpuid(op, &eax, &ebx, &ecx, &edx); return eax; } static inline unsigned int cpuid_ebx(unsigned int op) { unsigned int eax, ebx, ecx, edx; cpuid(op, &eax, &ebx, &ecx, &edx); return ebx; } static inline unsigned int cpuid_ecx(unsigned int op) { unsigned int eax, ebx, ecx, edx; cpuid(op, &eax, &ebx, &ecx, &edx); return ecx; } static inline unsigned int cpuid_edx(unsigned int op) { unsigned int eax, ebx, ecx, edx; cpuid(op, &eax, &ebx, &ecx, &edx); return edx; } extern void select_idle_routine(const struct cpuinfo_x86 *c); extern void amd_e400_c1e_apic_setup(void); extern unsigned long boot_option_idle_override; enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, IDLE_POLL}; extern void enable_sep_cpu(void); extern int sysenter_setup(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; extern void switch_to_new_gdt(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); extern void cpu_init_secondary(void); extern void cpu_init_exception_handling(void); extern void cr4_init(void); static inline unsigned long get_debugctlmsr(void) { unsigned long debugctlmsr = 0; #ifndef CONFIG_X86_DEBUGCTLMSR if (boot_cpu_data.x86 < 6) return 0; #endif rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); return debugctlmsr; } static inline void update_debugctlmsr(unsigned long debugctlmsr) { #ifndef CONFIG_X86_DEBUGCTLMSR if (boot_cpu_data.x86 < 6) return; #endif wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } extern void set_task_blockstep(struct task_struct *task, bool on); /* Boot loader type from the setup header: */ extern int bootloader_type; extern int bootloader_version; extern char ignore_fpu_irq; #define HAVE_ARCH_PICK_MMAP_LAYOUT 1 #define ARCH_HAS_PREFETCHW #define ARCH_HAS_SPINLOCK_PREFETCH #ifdef CONFIG_X86_32 # define BASE_PREFETCH "" # define ARCH_HAS_PREFETCH #else # define BASE_PREFETCH "prefetcht0 %P1" #endif /* * Prefetch instructions for Pentium III (+) and AMD Athlon (+) * * It's not worth to care about 3dnow prefetches for the K6 * because they are microcoded there and very slow. */ static inline void prefetch(const void *x) { alternative_input(BASE_PREFETCH, "prefetchnta %P1", X86_FEATURE_XMM, "m" (*(const char *)x)); } /* * 3dnow prefetch to get an exclusive cache line. * Useful for spinlocks to avoid one state transition in the * cache coherency protocol: */ static __always_inline void prefetchw(const void *x) { alternative_input(BASE_PREFETCH, "prefetchw %P1", X86_FEATURE_3DNOWPREFETCH, "m" (*(const char *)x)); } static inline void spin_lock_prefetch(const void *x) { prefetchw(x); } #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ TOP_OF_KERNEL_STACK_PADDING) #define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1)) #define task_pt_regs(task) \ ({ \ unsigned long __ptr = (unsigned long)task_stack_page(task); \ __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ ((struct pt_regs *)__ptr) - 1; \ }) #ifdef CONFIG_X86_32 #define INIT_THREAD { \ .sp0 = TOP_OF_INIT_STACK, \ .sysenter_cs = __KERNEL_CS, \ } #define KSTK_ESP(task) (task_pt_regs(task)->sp) #else #define INIT_THREAD { } extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp); /* * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ #define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3)) #define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE_LOW) #define KSTK_EIP(task) (task_pt_regs(task)->ip) /* Get/set a process' ability to use the timestamp counter instruction */ #define GET_TSC_CTL(adr) get_tsc_mode((adr)) #define SET_TSC_CTL(val) set_tsc_mode((val)) extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); DECLARE_PER_CPU(u64, msr_misc_features_shadow); #ifdef CONFIG_CPU_SUP_AMD extern u16 amd_get_nb_id(int cpu); extern u32 amd_get_nodes_per_socket(void); extern bool cpu_has_ibpb_brtype_microcode(void); extern void amd_clear_divider(void); #else static inline u16 amd_get_nb_id(int cpu) { return 0; } static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } static inline void amd_clear_divider(void) { } #endif static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { uint32_t base, eax, signature[3]; for (base = 0x40000000; base < 0x40010000; base += 0x100) { cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); if (!memcmp(sig, signature, 12) && (leaves == 0 || ((eax - base) >= leaves))) return base; } return 0; } extern unsigned long arch_align_stack(unsigned long sp); void free_init_pages(const char *what, unsigned long begin, unsigned long end); extern void free_kernel_image_pages(const char *what, void *begin, void *end); void default_idle(void); #ifdef CONFIG_XEN bool xen_set_default_idle(void); #else #define xen_set_default_idle 0 #endif void __noreturn stop_this_cpu(void *dummy); void microcode_check(struct cpuinfo_x86 *prev_info); void store_cpu_caps(struct cpuinfo_x86 *info); enum l1tf_mitigations { L1TF_MITIGATION_OFF, L1TF_MITIGATION_FLUSH_NOWARN, L1TF_MITIGATION_FLUSH, L1TF_MITIGATION_FLUSH_NOSMT, L1TF_MITIGATION_FULL, L1TF_MITIGATION_FULL_FORCE }; extern enum l1tf_mitigations l1tf_mitigation; enum mds_mitigations { MDS_MITIGATION_OFF, MDS_MITIGATION_FULL, MDS_MITIGATION_VMWERV, }; extern bool gds_ucode_mitigated(void); /* * Make previous memory operations globally visible before * a WRMSR. * * MFENCE makes writes visible, but only affects load/store * instructions. WRMSR is unfortunately not a load/store * instruction and is unaffected by MFENCE. The LFENCE ensures * that the WRMSR is not reordered. * * Most WRMSRs are full serializing instructions themselves and * do not require this barrier. This is only required for the * IA32_TSC_DEADLINE and X2APIC MSRs. */ static inline void weak_wrmsr_fence(void) { alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE)); } #endif /* _ASM_X86_PROCESSOR_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { /* * Those arches which don't have hw access flag feature need to * implement their own helper. By default, "true" means pagefault * will be hit on old pte. */ return true; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { if (current->rss_stat.count[i]) { add_mm_counter(mm, i, current->rss_stat.count[i]); current->rss_stat.count[i] = 0; } } current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { struct task_struct *task = current; if (likely(task->mm == mm)) task->rss_stat.count[member] += val; else add_mm_counter(mm, member, val); } #define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) #define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) /* sync counter once per 64 page faults */ #define TASK_RSS_EVENTS_THRESH (64) static void check_sync_rss_stat(struct task_struct *task) { if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) static void check_sync_rss_stat(struct task_struct *task) { } #endif /* SPLIT_RSS_COUNTING */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); pmd_populate(mm, pmd, new); new = NULL; } spin_unlock(ptl); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; if (current->mm == mm) sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The disadvantage is that pages are refcounted * (which can be slower and simply not an option for some PFNMAP users). The * advantage is that we don't have to follow the strict linearity rule of * PFNMAP mappings in order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* * There is no pmd_special() but there may be special pmds, e.g. * in a direct-access (dax) mapping, so let's just replicate the * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #endif /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return entry.val; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = device_private_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ get_page(page); rss[mm_counter(page)]++; page_dup_rmap(page, false); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_write_device_private_entry(entry) && is_cow_mapping(vm_flags)) { make_device_private_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page if necessary. * * NOTE! The usual case is that this doesn't need to do * anything, and can just return a positive value. That * will let the caller know that it can just increase * the page refcount and re-use the pte the traditional * way. * * But _if_ we need to copy it because it needs to be * pinned in the parent (and the child should get its own * copy rather than just a reference to the same page), * we'll do that here and return zero to let the caller * know we're done. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; if (!is_cow_mapping(src_vma->vm_flags)) return 1; /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy * the page immediately so that we'll always guarantee * the pinned page won't be randomly replaced in the * future. * * The page pinning checks are just "has this mm ever * seen pinning", along with the (inexact) check of * the page count. That might give false positives for * for pinning, but it will work correctly. */ if (likely(!atomic_read(&src_mm->has_pinned))) return 1; if (likely(!page_maybe_dma_pinned(page))) return 1; /* * The vma->anon_vma of the child process may be NULL * because the entire vma does not contain anonymous pages. * A BUG will occur when the copy_present_page() passes * a copy of a non-anonymous page of that vma to the * page_add_new_anon_rmap() to set up new anonymous rmap. * Return 1 if the page is not an anonymous page. */ if (!PageAnon(page)) return 1; new_page = *prealloc; if (!new_page) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); page_add_new_anon_rmap(new_page, dst_vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, *src_pte)) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } /* * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page * is required to copy this pte. */ static inline int copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc) { struct mm_struct *src_mm = src_vma->vm_mm; unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, pte, page); if (retval <= 0) return retval; get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; } /* * If it's a COW mapping, write protect it both * in the parent and the child */ if (is_cow_mapping(vm_flags) && pte_write(pte)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } /* * If it's a shared mapping, mark it clean in * the child */ if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static inline struct page * page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr) { struct page *new_page; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); if (!new_page) return NULL; if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } cgroup_throttle_swaprate(new_page, GFP_KERNEL); return new_page; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct page *prealloc = NULL; again: progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } if (unlikely(!pte_present(*src_pte))) { entry.val = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (entry.val) break; progress += 8; continue; } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. */ if (unlikely(ret == -EAGAIN)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ put_page(prealloc); prealloc = NULL; } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (entry.val) { if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret) { WARN_ON_ONCE(ret != -EAGAIN); prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; /* We've captured and resolved the error. Reset, try again. */ ret = 0; } if (addr != end) goto again; out: if (unlikely(prealloc)) put_page(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; /* * Don't copy ptes where a page fault will fill them correctly. * Fork becomes much lighter when there are big shared or private * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && !src_vma->anon_vma) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ mmap_assert_write_locked(src_mm); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; /* Or, we zap COWed pages only if the caller wants to */ return !details->check_mapping; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { struct page *page; page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping && details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; addr += PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry)) { struct page *page = device_private_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping != page_rmapping(page)) continue; } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; page_remove_rmap(page, false); put_page(page); continue; } if (!non_swap_entry(entry)) { /* Genuine swap entry, hence a private anon page */ if (!should_zap_cows(details)) continue; rss[MM_SWAPENTS]--; } else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); if (details && details->check_mapping && details->check_mapping != page_rmapping(page)) continue; rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; tlb_flush_mmu(tlb); } if (addr != end) { cond_resched(); goto again; } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } else if (details && details->single_page && PageTransCompound(details->single_page) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is * none or trans huge it can change under us. This is * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); next: cond_resched(); } while (pmd++, addr = next, addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) unmap_single_vma(&tlb, vma, start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, start, range.end); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, address, range.end); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static int validate_page_before_insert(struct page *page) { if (PageAnon(page) || PageSlab(page) || page_has_type(page)) return -EINVAL; flush_dcache_page(page); return 0; } static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); return 0; } /* * This is the old fallback for page remapping. * * For historical reasons, it only allows reserved pages. Only * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); if (err) return err; return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. Arch *must* define pte_index. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } #endif /* ifdef pte_index */ /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { #ifdef pte_index const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); if (err) break; } *num = pgcount - idx; return err; #endif /* ifdef pte_index */ } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } entry = pte_mkyoung(*pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * See vmf_insert_mixed_prot() for a discussion of the implication of using * a value of @pgprot different from that of @vma->vm_page_prot. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot, bool mkwrite) { int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } /** * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and * encryption bits different than those of @vma->vm_page_prot, because * the caching- or encryption mode may not be known at mmap() time. * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot) { return __vm_insert_mixed(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_mixed_prot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pgd++, addr = next, addr != end); return 0; } /* * Variant of remap_pfn_range that does not call track_pfn_remap. The caller * must have pre-validated the caching bits of the pgprot_t. */ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); if (!error) return 0; /* * A partial pfn range mapping is dangerous: it does not * maintain page reference counts, and callers may free * pages due to the error. So zap it early. */ zap_page_range_single(vma, addr, size, NULL); return error; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int err; err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (err) untrack_pfn(vma, pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte; int err = 0; spinlock_t *ptl; if (create) { pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(*pte)) { err = fn(pte, addr, data); if (err) break; } } while (pte++, addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_huge(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (create || !pmd_none_or_clear_bad(pmd)) { err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (create || !pud_none_or_clear_bad(pud)) { err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (create || !p4d_none_or_clear_bad(p4d)) { err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (!create && pgd_none_or_clear_bad(pgd)) continue; err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spinlock_t *ptl = pte_lockptr(mm, pmd); spin_lock(ptl); same = pte_same(*page_table, orig_pte); spin_unlock(ptl); } #endif pte_unmap(page_table); return same; } static inline bool cow_user_page(struct page *dst, struct page *src, struct vm_fault *vmf) { bool ret; void *kaddr; void __user *uaddr; bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { copy_user_highpage(dst, src, addr, vma); return true; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_atomic(dst); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache(vma, addr, vmf->pte); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (locked) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = true; pte_unlock: if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) { vm_fault_t ret; struct page *page = vmf->page; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { lock_page(page); if (!page->mapping) { unlock_page(page); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_PAGE(!PageLocked(page), page); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = set_page_dirty(page); VM_BUG_ON_PAGE(PageAnon(page), page); /* * Take a local copy of the address_space - page.mapping may be zeroed * by truncate after unlock_page(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = page_rmapping(page); unlock_page(page); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_RETRY; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * Handle the case of a page which we actually need to copy to a new page. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) goto oom; if (!cow_user_page(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. */ put_page(new_page); if (old_page) put_page(old_page); return 0; } } if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry. This will avoid a race condition * seen in the presence of one thread doing SMC and another * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * page_remove_rmap with the ptp_clear_flush above. * Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in page_remove_rmap. * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) put_page(new_page); pte_unmap_unlock(vmf->pte, vmf->ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above ptep_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); unlock_page(old_page); } put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); return VM_FAULT_OOM; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); return VM_FAULT_WRITE; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } tmp = finish_mkwrite_fault(vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { unlock_page(vmf->page); put_page(vmf->page); return tmp; } } else { wp_page_reuse(vmf); lock_page(vmf->page); } ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); return ret; } /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary * COW. * * We also mark the page dirty at this point even though the page will * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } /* * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ if (PageAnon(vmf->page)) { struct page *page = vmf->page; /* PageKsm() doesn't necessarily raise the page refcount */ if (PageKsm(page) || page_count(page) != 1) goto copy; if (!trylock_page(page)) goto copy; if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { unlock_page(page); goto copy; } /* * Ok, we've got the only map reference, and the only * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ unlock_page(page); wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } copy: /* * Ok, we need to copy. Oh, well.. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = details->first_index; if (zba < vba) zba = vba; zea = details->last_index; if (zea > vea) zea = vea; unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_page() - Unmap single page from processes. * @page: The locked page to be unmapped. * * Unmap this page from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a page, it may find that * the page has been remapped again: and then uses unmap_mapping_page() * to unmap it finally. */ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); details.check_mapping = mapping; details.first_index = page->index; details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; details.check_mapping = even_cows ? NULL : mapping; details.first_index = start; details.last_index = start + nr - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_private_entry(entry)) { vmf->page = device_private_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { struct swap_info_struct *si = swp_swap_info(entry); if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (page) { int err; __SetPageLocked(page); __SetPageSwapBacked(page); set_page_private(page, entry.val); /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); if (err) { ret = VM_FAULT_OOM; goto out_page; } shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(page, shadow); lru_cache_add(page); swap_readpage(page, true); } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = page; } if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not * release the swapcache from under us. The page pin, and pte_same * test below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not changed. */ if (unlikely((!PageSwapCache(page) || page_private(page) != entry.val)) && swapcache) goto out_page; page = ksm_might_need_to_copy(page, vma, vmf->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* * The page isn't present yet, go ahead with the fault. * * Be careful about the sequence of operations here. * To get its accounting right, reuse_swap_page() must be called * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. */ inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) { pte = pte_mkuffd_wp(pte); pte = pte_wrprotect(pte); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); vmf->orig_pte = pte; /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); } swap_free(entry); if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ unlock_page(swapcache); put_page(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); out_release: put_page(page); if (page != swapcache && swapcache) { unlock_page(swapcache); put_page(swapcache); } return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* See the comment in pte_alloc_one_map() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!page) goto oom; if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_cache(vma, vmf->address, vmf->pte); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: put_page(page); goto unlock; oom_free_page: put_page(page); oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; if (unlikely(PageHWPoison(vmf->page))) { struct page *page = vmf->page; vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(page)) unmap_mapping_pages(page_mapping(page), page->index, 1, false); /* Retry if a clean page was removed from the cache. */ if (invalidate_inode_page(page)) poisonret = VM_FAULT_NOPAGE; unlock_page(page); } put_page(page); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf->page); else VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); return ret; } /* * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. * If we check pmd_trans_unstable() first we will trip the bad_pmd() check * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. */ static int pmd_devmap_trans_unstable(pmd_t *pmd) { return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); } static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (!pmd_none(*vmf->pmd)) goto map_pte; if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { spin_unlock(vmf->ptl); goto map_pte; } mm_inc_nr_ptes(vma->vm_mm); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); spin_unlock(vmf->ptl); vmf->prealloc_pte = NULL; } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; } map_pte: /* * If a huge pmd materialized under us just retry later. Use * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge * under us and then back to pmd_none, as a result of MADV_DONTNEED * running immediately after a huge pmd fault in a different thread of * this mm, in turn leading to a misleading pmd_trans_huge() retval. * All we have to ensure is that it is a regular pmd that we can walk * with pte_offset_map() and we can do that through an atomic read in * C, which is what pmd_trans_unstable() provides. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; /* * At this point we know that our vmf->pmd points to a page of ptes * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() * for the duration of the fault. If a racing MADV_DONTNEED runs and * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still * be valid and we will re-check to make sure the vmf->pte isn't * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); return 0; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) return ret; page = compound_head(page); if (compound_order(page) != HPAGE_PMD_ORDER) return ret; /* * Archs like ppc64 need additonal space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); page_add_file_rmap(page, true); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { BUILD_BUG(); return 0; } #endif /** * alloc_set_pte - setup new PTE entry for given page and add reverse page * mapping. If needed, the function allocates page table or use pre-allocated. * * @vmf: fault environment * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on * return. * * Target users are page handler itself and implementations of * vm_ops->map_pages. * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; pte_t entry; vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (!vmf->pte) { ret = pte_alloc_one_map(vmf); if (ret) return ret; } /* Re-check under ptl */ if (unlikely(!pte_none(*vmf->pte))) { update_mmu_tlb(vma, vmf->address, vmf->pte); return VM_FAULT_NOPAGE; } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, vmf->address, vmf->pte); return 0; } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct page *page; vm_fault_t ret = 0; /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vmf->vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vmf->vma->vm_flags & VM_SHARED)) ret = check_stable_address_space(vmf->vma->vm_mm); if (!ret) ret = alloc_set_pte(vmf, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_bytes __read_mostly = rounddown_pow_of_two(65536); #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_bytes; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; if (val > PAGE_SIZE) fault_around_bytes = rounddown_pow_of_two(val); else fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function is called with the page table lock taken. In the split ptlock * case the page table lock only protects only those entries which belong to * the page table corresponding to the fault address. * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * * fault_around_bytes defines how many bytes we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_bytes rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { unsigned long address = vmf->address, nr_pages, mask; pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; vm_fault_t ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; vmf->address = max(address & mask, vmf->vma->vm_start); off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* * end_pgoff is either the end of the page table, the end of * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) goto out; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); /* Huge page is mapped? Page fault is solved */ if (pmd_trans_huge(*vmf->pmd)) { ret = VM_FAULT_NOPAGE; goto out; } /* ->map_pages() haven't done anything useful. Cold page cache? */ if (!vmf->pte) goto out; /* check if the page fault is solved */ vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); if (!pte_none(*vmf->pte)) ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); out: vmf->address = address; vmf->pte = NULL; return ret; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { ret = do_fault_around(vmf); if (ret) return ret; } ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); unlock_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) put_page(vmf->page); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!vmf->cow_page) return VM_FAULT_OOM; if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); __SetPageUptodate(vmf->cow_page); ret |= finish_fault(vmf); unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: put_page(vmf->cow_page); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { unlock_page(vmf->page); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { unlock_page(vmf->page); put_page(vmf->page); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { /* * If we find a migration pmd entry or a none pmd entry, which * should never happen, return SIGBUS */ if (unlikely(!pmd_present(*vmf->pmd))) ret = VM_FAULT_SIGBUS; else { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(*vmf->pte))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(page, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; bool migrated = false; pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. */ vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; } /* * Make it present again, Depending on how arch implementes non * accessible ptes, some can allow access by kernel mode. */ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); if (!page) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* TODO: handle PTE-mapped THP */ if (PageCompound(page)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!pte_write(pte)) flags |= TNF_NO_GROUP; /* * Flag if the page is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); pte_unmap_unlock(vmf->pte, vmf->ptl); if (target_nid == NUMA_NO_NODE) { put_page(page); goto out; } /* Migrate to the requested node */ migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; } else flags |= TNF_MIGRATE_FAIL; out: if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) { if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf, orig_pmd); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) return VM_FAULT_FALLBACK; if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; } else { /* See comment in pte_alloc_one_map() */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge * pmd from under us anymore at this point because we hold the * mmap_lock read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; /* * some architectures can have larger ptes than wordsize, * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic * accesses. The code below just needs a consistent view * for the ifs and we later double check anyway with the * ptl lock held. So here a barrier will do. */ barrier(); if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(*vmf->pte, entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(vmf); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* NUMA case for anonymous PUDs would go here */ if (dirty && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pmd_t orig_pmd = *vmf.pmd; barrier(); if (unlikely(is_swap_pmd(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); if (is_pmd_migration_entry(orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); if (dirty && !pmd_write(orig_pmd)) { ret = wp_huge_pmd(&vmf, orig_pmd); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf, orig_pmd); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accountings * * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accountings. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* * We don't do accounting for some specific faults: * * - Unsuccessful faults (e.g. when the address wasn't valid). That * includes arch_vma_access_permitted() failing before reaching here. * So this is not a "this many hardware page faults" counter. We * should use the hw profiling for that. * * - Incomplete faults (VM_FAULT_RETRY). They will only be counted * once they're completed. */ if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; __set_current_state(TASK_RUNNING); count_vm_event(PGFAULT); count_memcg_event_mm(vma->vm_mm, PGFAULT); /* do counter updates before entering really critical section. */ check_sync_rss_stat(current); if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) return VM_FAULT_SIGSEGV; /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } mm_account_fault(regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ p4d_free(mm, new); else pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) goto out; pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); if (pmd_huge(*pmd)) { if (!pmdpp) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PMD_MASK, (address & PMD_MASK) + PMD_SIZE); mmu_notifier_invalidate_range_start(range); } *ptlp = pmd_lock(mm, pmd); if (pmd_huge(*pmd)) { *pmdpp = pmd; return 0; } spin_unlock(*ptlp); if (range) mmu_notifier_invalidate_range_end(range); } if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PAGE_MASK, (address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(range); } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; *ptepp = ptep; return 0; unlock: pte_unmap_unlock(ptep, *ptlp); if (range) mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } /** * follow_pte - look up PTE at a user virtual address * @mm: the mm_struct of the target address space * @address: user virtual address * @ptepp: location to store found PTE * @ptlp: location to store the lock for the PTE * * On a successful return, the pointer to the PTE is stored in @ptepp; * the corresponding lock is taken and its location is stored in @ptlp. * The contents of the PTE are only stable until @ptlp is released; * any further use, if any, must be protected against invalidation * with MMU notifiers. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read. * * KVM uses this function. While it is arguably less bad than ``follow_pfn``, * it is not a good general-purpose API. * * Return: zero on success, -ve otherwise. */ int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); } EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping * @address: user virtual address * @pfn: location to store found PFN * * Only IO mappings and raw PFN mappings are allowed. * * This function does not allow the caller to read the permissions * of the PTE. Do not use it. * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn) { int ret = -EINVAL; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) return ret; ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); if (ret) return ret; *pfn = pte_pfn(*ptep); pte_unmap_unlock(ptep, ptl); return 0; } EXPORT_SYMBOL(follow_pfn); #ifdef CONFIG_HAVE_IOREMAP_PROT int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys) { int ret = -EINVAL; pte_t *ptep, pte; spinlock_t *ptl; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) goto out; pte = *ptep; /* Never return PFNs of anon folios in COW mappings. */ if (vm_normal_page(vma, address, pte)) goto unlock; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; *prot = pgprot_val(pte_pgprot(pte)); *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: return ret; } int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; int offset = addr & (PAGE_SIZE-1); if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); iounmap(maddr); return len; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. If non-NULL, use the * given task for page fault accounting. */ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; void *maddr; struct page *page = NULL; ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT break; #else /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, len, write); if (ret <= 0) break; bytes = ret; #endif } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } kunmap(page); put_page(page); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = find_vma(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; char *buf = (char *)__get_free_page(GFP_NOWAIT); if (buf) { char *p; p = file_path(f, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; printk("%s%s[%lx+%lx]", prefix, kbasename(p), vma->vm_start, vma->vm_end - vma->vm_start); free_page((unsigned long)buf); } } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { /* * Some code (nfs/sunrpc) uses socket ops on kernel memory while * holding the mmap_lock, this is safe because kernel memory doesn't * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ if (uaccess_kernel()) return; if (pagefault_disabled()) return; __might_sleep(file, line, 0); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline void process_huge_page( unsigned long addr_hint, unsigned int pages_per_huge_page, void (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l; unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= pages_per_huge_page) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } else { /* If target subpage in second half of huge page */ base = pages_per_huge_page - 2 * (pages_per_huge_page - n); l = pages_per_huge_page - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); cond_resched(); process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); } } static void clear_gigantic_page(struct page *page, unsigned long addr, unsigned int pages_per_huge_page) { int i; struct page *p = page; might_sleep(); for (i = 0; i < pages_per_huge_page; i++, p = mem_map_next(p, page, i)) { cond_resched(); clear_user_highpage(p, addr + i * PAGE_SIZE); } } static void clear_subpage(unsigned long addr, int idx, void *arg) { struct page *page = arg; clear_user_highpage(page + idx, addr); } void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } static void copy_user_gigantic_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { int i; struct page *dst_base = dst; struct page *src_base = src; for (i = 0; i < pages_per_huge_page; ) { cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); i++; dst = mem_map_next(dst, dst_base, i); src = mem_map_next(src, src_base, i); } } struct copy_subpage_arg { struct page *dst; struct page *src; struct vm_area_struct *vma; }; static void copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, addr, copy_arg->vma); } void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { copy_user_gigantic_page(dst, src, addr, vma, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault) { void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; struct page *subpage = dst_page; for (i = 0; i < pages_per_huge_page; i++, subpage = mem_map_next(subpage, dst_page, i)) { if (allow_pagefault) page_kaddr = kmap(subpage); else page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, (const void __user *)(src + i * PAGE_SIZE), PAGE_SIZE); if (allow_pagefault) kunmap(subpage); else kunmap_atomic(page_kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct page *page) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; page->ptl = ptl; return true; } void ptlock_free(struct page *page) { kmem_cache_free(page_ptl_cachep, page->ptl); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel thread helper functions. * Copyright (C) 2004 IBM Corporation, Rusty Russell. * Copyright (C) 2009 Red Hat, Inc. * * Creation is done via kthreadd, so that we get a clean environment * even if we're invoked from userspace (think modprobe, hotplug cpu, * etc.). */ #include <uapi/linux/sched/types.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/kthread.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/unistd.h> #include <linux/file.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/numa.h> #include <linux/sched/isolation.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ int (*threadfn)(void *data); void *data; int node; /* Result passed back to kthread_create() from kthreadd. */ struct task_struct *result; struct completion *done; struct list_head list; }; struct kthread { unsigned long flags; unsigned int cpu; int (*threadfn)(void *); void *data; mm_segment_t oldfs; struct completion parked; struct completion exited; #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif }; enum KTHREAD_BITS { KTHREAD_IS_PER_CPU = 0, KTHREAD_SHOULD_STOP, KTHREAD_SHOULD_PARK, }; static inline void set_kthread_struct(void *kthread) { /* * We abuse ->set_child_tid to avoid the new member and because it * can't be wrongly copied by copy_process(). We also rely on fact * that the caller can't exec, so PF_KTHREAD can't be cleared. */ current->set_child_tid = (__force void __user *)kthread; } static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); return (__force void *)k->set_child_tid; } /* * Variant of to_kthread() that doesn't assume @p is a kthread. * * Per construction; when: * * (p->flags & PF_KTHREAD) && p->set_child_tid * * the task is both a kthread and struct kthread is persistent. However * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and * begin_new_exec()). */ static inline struct kthread *__to_kthread(struct task_struct *p) { void *kthread = (__force void *)p->set_child_tid; if (kthread && !(p->flags & PF_KTHREAD)) kthread = NULL; return kthread; } void free_kthread_struct(struct task_struct *k) { struct kthread *kthread; /* * Can be NULL if this kthread was created by kernel_thread() * or if kmalloc() in kthread() failed. */ kthread = to_kthread(k); #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread && kthread->blkcg_css); #endif kfree(kthread); } /** * kthread_should_stop - should this kthread return now? * * When someone calls kthread_stop() on your kthread, it will be woken * and this will return true. You should then return, and your return * value will be passed through to kthread_stop(). */ bool kthread_should_stop(void) { return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); } EXPORT_SYMBOL(kthread_should_stop); bool __kthread_should_park(struct task_struct *k) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags); } EXPORT_SYMBOL_GPL(__kthread_should_park); /** * kthread_should_park - should this kthread park now? * * When someone calls kthread_park() on your kthread, it will be woken * and this will return true. You should then do the necessary * cleanup and call kthread_parkme() * * Similar to kthread_should_stop(), but this keeps the thread alive * and in a park position. kthread_unpark() "restarts" the thread and * calls the thread function again. */ bool kthread_should_park(void) { return __kthread_should_park(current); } EXPORT_SYMBOL_GPL(kthread_should_park); /** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen * * kthread_should_stop() for freezable kthreads, which will enter * refrigerator if necessary. This function is safe from kthread_stop() / * freezer deadlock and freezable kthreads should use this function instead * of calling try_to_freeze() directly. */ bool kthread_freezable_should_stop(bool *was_frozen) { bool frozen = false; might_sleep(); if (unlikely(freezing(current))) frozen = __refrigerator(true); if (was_frozen) *was_frozen = frozen; return kthread_should_stop(); } EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); /** * kthread_func - return the function specified on kthread creation * @task: kthread task in question * * Returns NULL if the task is not a kthread. */ void *kthread_func(struct task_struct *task) { struct kthread *kthread = __to_kthread(task); if (kthread) return kthread->threadfn; return NULL; } EXPORT_SYMBOL_GPL(kthread_func); /** * kthread_data - return data value specified on kthread creation * @task: kthread task in question * * Return the data value specified when kthread @task was created. * The caller is responsible for ensuring the validity of @task when * calling this function. */ void *kthread_data(struct task_struct *task) { return to_kthread(task)->data; } EXPORT_SYMBOL_GPL(kthread_data); /** * kthread_probe_data - speculative version of kthread_data() * @task: possible kthread task in question * * @task could be a kthread task. Return the data value specified when it * was created if accessible. If @task isn't a kthread task or its data is * inaccessible for any reason, %NULL is returned. This function requires * that @task itself is safe to dereference. */ void *kthread_probe_data(struct task_struct *task) { struct kthread *kthread = __to_kthread(task); void *data = NULL; if (kthread) copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); return data; } static void __kthread_parkme(struct kthread *self) { for (;;) { /* * TASK_PARKED is a special state; we must serialize against * possible pending wakeups to avoid store-store collisions on * task->state. * * Such a collision might possibly result in the task state * changin from TASK_PARKED and us failing the * wait_task_inactive() in kthread_park(). */ set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; /* * Thread is going to call schedule(), do not preempt it, * or the caller of kthread_park() may spend more time in * wait_task_inactive(). */ preempt_disable(); complete(&self->parked); schedule_preempt_disabled(); preempt_enable(); } __set_current_state(TASK_RUNNING); } void kthread_parkme(void) { __kthread_parkme(to_kthread(current)); } EXPORT_SYMBOL_GPL(kthread_parkme); /** * kthread_exit - Cause the current kthread return @result to kthread_stop(). * @result: The integer value to return to kthread_stop(). * * While kthread_exit can be called directly, it exists so that * functions which do some additional work in non-modular code such as * module_put_and_kthread_exit can be implemented. * * Does not return. */ void __noreturn kthread_exit(long result) { do_exit(result); } static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; void *data = create->data; struct completion *done; struct kthread *self; int ret; self = kzalloc(sizeof(*self), GFP_KERNEL); set_kthread_struct(self); /* If user was SIGKILLed, I release the structure. */ done = xchg(&create->done, NULL); if (!done) { kfree(create); kthread_exit(-EINTR); } if (!self) { create->result = ERR_PTR(-ENOMEM); complete(done); kthread_exit(-ENOMEM); } self->threadfn = threadfn; self->data = data; init_completion(&self->exited); init_completion(&self->parked); current->vfork_done = &self->exited; /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; /* * Thread is going to call schedule(), do not preempt it, * or the creator may spend more time in wait_task_inactive(). */ preempt_disable(); complete(done); schedule_preempt_disabled(); preempt_enable(); ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } kthread_exit(ret); } /* called from do_fork() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA if (tsk == kthreadd_task) return tsk->pref_node_fork; #endif return NUMA_NO_NODE; } static void create_kthread(struct kthread_create_info *create) { int pid; #ifdef CONFIG_NUMA current->pref_node_fork = create->node; #endif /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { /* If user was SIGKILLed, I release the structure. */ struct completion *done = xchg(&create->done, NULL); if (!done) { kfree(create); return; } create->result = ERR_PTR(pid); complete(done); } } static __printf(4, 0) struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], va_list args) { DECLARE_COMPLETION_ONSTACK(done); struct task_struct *task; struct kthread_create_info *create = kmalloc(sizeof(*create), GFP_KERNEL); if (!create) return ERR_PTR(-ENOMEM); create->threadfn = threadfn; create->data = data; create->node = node; create->done = &done; spin_lock(&kthread_create_lock); list_add_tail(&create->list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); /* * Wait for completion in killable state, for I might be chosen by * the OOM killer while kthreadd is trying to allocate memory for * new kernel thread. */ if (unlikely(wait_for_completion_killable(&done))) { /* * If I was SIGKILLed before kthreadd (or new kernel thread) * calls complete(), leave the cleanup of this structure to * that thread. */ if (xchg(&create->done, NULL)) return ERR_PTR(-EINTR); /* * kthreadd (or new kernel thread) will call complete() * shortly. */ wait_for_completion(&done); } task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; char name[TASK_COMM_LEN]; /* * task is already visible to other tasks, so updating * COMM must be protected. */ vsnprintf(name, sizeof(name), namefmt, args); set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. */ sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); set_cpus_allowed_ptr(task, housekeeping_cpumask(HK_FLAG_KTHREAD)); } kfree(create); return task; } /** * kthread_create_on_node - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @node: task and thread structures for the thread are allocated on this node * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(). The new thread has SCHED_NORMAL policy and * is affine to all CPUs. * * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], ...) { struct task_struct *task; va_list args; va_start(args, namefmt); task = __kthread_create_on_node(threadfn, data, node, namefmt, args); va_end(args); return task; } EXPORT_SYMBOL(kthread_create_on_node); static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state) { unsigned long flags; if (!wait_task_inactive(p, state)) { WARN_ON(1); return; } /* It's safe because the task is inactive. */ raw_spin_lock_irqsave(&p->pi_lock, flags); do_set_cpus_allowed(p, mask); p->flags |= PF_NO_SETAFFINITY; raw_spin_unlock_irqrestore(&p->pi_lock, flags); } static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state) { __kthread_bind_mask(p, cpumask_of(cpu), state); } void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) { __kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE); } /** * kthread_bind - bind a just-created kthread to a cpu. * @p: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *p, unsigned int cpu) { __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(kthread_bind); /** * kthread_create_on_cpu - Create a cpu bound kthread * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @cpu: The cpu on which the thread should be bound, * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Description: This helper function creates and names a kernel thread */ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, const char *namefmt) { struct task_struct *p; p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, cpu); if (IS_ERR(p)) return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ to_kthread(p)->cpu = cpu; return p; } void kthread_set_per_cpu(struct task_struct *k, int cpu) { struct kthread *kthread = to_kthread(k); if (!kthread) return; WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); if (cpu < 0) { clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); return; } kthread->cpu = cpu; set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } bool kthread_is_per_cpu(struct task_struct *p) { struct kthread *kthread = __to_kthread(p); if (!kthread) return false; return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return false, wakes it, and * waits for it to return. If the thread is marked percpu then its * bound to the cpu again. */ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_kthread(k); /* * Newly created kthread was parked when the CPU was offline. * The binding was lost and we need to set it again. */ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); /** * kthread_park - park a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return true, wakes it, and * waits for it to return. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will park without * calling threadfn(). * * Returns 0 if the thread is parked, -ENOSYS if the thread exited. * If called by the kthread itself just the park bit is set. */ int kthread_park(struct task_struct *k) { struct kthread *kthread = to_kthread(k); if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) return -EBUSY; set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); /* * Wait for __kthread_parkme() to complete(), this means we * _will_ have TASK_PARKED and are about to call schedule(). */ wait_for_completion(&kthread->parked); /* * Now wait for that schedule() to complete and the task to * get scheduled out. */ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; } EXPORT_SYMBOL_GPL(kthread_park); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { struct kthread *kthread; int ret; trace_sched_kthread_stop(k); get_task_struct(k); kthread = to_kthread(k); set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); kthread_unpark(k); wake_up_process(k); wait_for_completion(&kthread->exited); ret = k->exit_code; put_task_struct(k); trace_sched_kthread_stop_ret(ret); return ret; } EXPORT_SYMBOL(kthread_stop); int kthreadd(void *unused) { struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; cgroup_init_kthreadd(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (list_empty(&kthread_create_list)) schedule(); __set_current_state(TASK_RUNNING); spin_lock(&kthread_create_lock); while (!list_empty(&kthread_create_list)) { struct kthread_create_info *create; create = list_entry(kthread_create_list.next, struct kthread_create_info, list); list_del_init(&create->list); spin_unlock(&kthread_create_lock); create_kthread(create); spin_lock(&kthread_create_lock); } spin_unlock(&kthread_create_lock); } return 0; } void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) { memset(worker, 0, sizeof(struct kthread_worker)); raw_spin_lock_init(&worker->lock); lockdep_set_class_and_name(&worker->lock, key, name); INIT_LIST_HEAD(&worker->work_list); INIT_LIST_HEAD(&worker->delayed_work_list); } EXPORT_SYMBOL_GPL(__kthread_init_worker); /** * kthread_worker_fn - kthread function to process kthread_worker * @worker_ptr: pointer to initialized kthread_worker * * This function implements the main cycle of kthread worker. It processes * work_list until it is stopped with kthread_stop(). It sleeps when the queue * is empty. * * The works are not allowed to keep any locks, disable preemption or interrupts * when they finish. There is defined a safe point for freezing when one work * finishes and before a new one is started. * * Also the works must not be handled by more than one worker at the same time, * see also kthread_queue_work(). */ int kthread_worker_fn(void *worker_ptr) { struct kthread_worker *worker = worker_ptr; struct kthread_work *work; /* * FIXME: Update the check and remove the assignment when all kthread * worker users are created using kthread_create_worker*() functions. */ WARN_ON(worker->task && worker->task != current); worker->task = current; if (worker->flags & KTW_FREEZABLE) set_freezable(); repeat: set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&worker->lock); worker->task = NULL; raw_spin_unlock_irq(&worker->lock); return 0; } work = NULL; raw_spin_lock_irq(&worker->lock); if (!list_empty(&worker->work_list)) { work = list_first_entry(&worker->work_list, struct kthread_work, node); list_del_init(&work->node); } worker->current_work = work; raw_spin_unlock_irq(&worker->lock); if (work) { kthread_work_func_t func = work->func; __set_current_state(TASK_RUNNING); trace_sched_kthread_work_execute_start(work); work->func(work); /* * Avoid dereferencing work after this point. The trace * event only cares about the address. */ trace_sched_kthread_work_execute_end(work, func); } else if (!freezing(current)) { schedule(); } else { /* * Handle the case where the current remains * TASK_INTERRUPTIBLE. try_to_freeze() expects * the current to be TASK_RUNNING. */ __set_current_state(TASK_RUNNING); } try_to_freeze(); cond_resched(); goto repeat; } EXPORT_SYMBOL_GPL(kthread_worker_fn); static __printf(3, 0) struct kthread_worker * __kthread_create_worker(int cpu, unsigned int flags, const char namefmt[], va_list args) { struct kthread_worker *worker; struct task_struct *task; int node = NUMA_NO_NODE; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) return ERR_PTR(-ENOMEM); kthread_init_worker(worker); if (cpu >= 0) node = cpu_to_node(cpu); task = __kthread_create_on_node(kthread_worker_fn, worker, node, namefmt, args); if (IS_ERR(task)) goto fail_task; if (cpu >= 0) kthread_bind(task, cpu); worker->flags = flags; worker->task = task; wake_up_process(task); return worker; fail_task: kfree(worker); return ERR_CAST(task); } /** * kthread_create_worker - create a kthread worker * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the kthread worker (task). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the worker was SIGKILLed. */ struct kthread_worker * kthread_create_worker(unsigned int flags, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); worker = __kthread_create_worker(-1, flags, namefmt, args); va_end(args); return worker; } EXPORT_SYMBOL(kthread_create_worker); /** * kthread_create_worker_on_cpu - create a kthread worker and bind it * to a given CPU and the associated NUMA node. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the kthread worker (task). * * Use a valid CPU number if you want to bind the kthread worker * to the given CPU and the associated NUMA node. * * A good practice is to add the cpu number also into the worker name. * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the worker was SIGKILLed. */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); worker = __kthread_create_worker(cpu, flags, namefmt, args); va_end(args); return worker; } EXPORT_SYMBOL(kthread_create_worker_on_cpu); /* * Returns true when the work could not be queued at the moment. * It happens when it is already pending in a worker list * or when it is being cancelled. */ static inline bool queuing_blocked(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); return !list_empty(&work->node) || work->canceling; } static void kthread_insert_work_sanity_check(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); WARN_ON_ONCE(!list_empty(&work->node)); /* Do not use a work with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker && work->worker != worker); } /* insert @work before @pos in @worker */ static void kthread_insert_work(struct kthread_worker *worker, struct kthread_work *work, struct list_head *pos) { kthread_insert_work_sanity_check(worker, work); trace_sched_kthread_work_queue_work(worker, work); list_add_tail(&work->node, pos); work->worker = worker; if (!worker->current_work && likely(worker->task)) wake_up_process(worker->task); } /** * kthread_queue_work - queue a kthread_work * @worker: target kthread_worker * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task * must have been created with kthread_worker_create(). Returns %true * if @work was successfully queued, %false if it was already pending. * * Reinitialize the work if it needs to be used by another worker. * For example, when the worker was stopped and started again. */ bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work) { bool ret = false; unsigned long flags; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { kthread_insert_work(worker, work, &worker->work_list); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_work); /** * kthread_delayed_work_timer_fn - callback that queues the associated kthread * delayed work when the timer expires. * @t: pointer to the expired timer * * The format of the function is defined by struct timer_list. * It should have been called from irqsafe timer with irq already off. */ void kthread_delayed_work_timer_fn(struct timer_list *t) { struct kthread_delayed_work *dwork = from_timer(dwork, t, timer); struct kthread_work *work = &dwork->work; struct kthread_worker *worker = work->worker; unsigned long flags; /* * This might happen when a pending work is reinitialized. * It means that it is used a wrong way. */ if (WARN_ON_ONCE(!worker)) return; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); if (!work->canceling) kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); static void __kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { kthread_insert_work(worker, work, &worker->work_list); return; } /* Be paranoid and try to detect possible races already now. */ kthread_insert_work_sanity_check(worker, work); list_add(&work->node, &worker->delayed_work_list); work->worker = worker; timer->expires = jiffies + delay; add_timer(timer); } /** * kthread_queue_delayed_work - queue the associated kthread work * after a delay. * @worker: target kthread_worker * @dwork: kthread_delayed_work to queue * @delay: number of jiffies to wait before queuing * * If the work has not been pending it starts a timer that will queue * the work after the given @delay. If @delay is zero, it queues the * work immediately. * * Return: %false if the @work has already been pending. It means that * either the timer was running or the work was queued. It returns %true * otherwise. */ bool kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; bool ret = false; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { __kthread_queue_delayed_work(worker, dwork, delay); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); struct kthread_flush_work { struct kthread_work work; struct completion done; }; static void kthread_flush_work_fn(struct kthread_work *work) { struct kthread_flush_work *fwork = container_of(work, struct kthread_flush_work, work); complete(&fwork->done); } /** * kthread_flush_work - flush a kthread_work * @work: work to flush * * If @work is queued or executing, wait for it to finish execution. */ void kthread_flush_work(struct kthread_work *work) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; struct kthread_worker *worker; bool noop = false; worker = work->worker; if (!worker) return; raw_spin_lock_irq(&worker->lock); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (!list_empty(&work->node)) kthread_insert_work(worker, &fwork.work, work->node.next); else if (worker->current_work == work) kthread_insert_work(worker, &fwork.work, worker->work_list.next); else noop = true; raw_spin_unlock_irq(&worker->lock); if (!noop) wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_work); /* * Make sure that the timer is neither set nor running and could * not manipulate the work list_head any longer. * * The function is called under worker->lock. The lock is temporary * released but the timer can't be set again in the meantime. */ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, unsigned long *flags) { struct kthread_delayed_work *dwork = container_of(work, struct kthread_delayed_work, work); struct kthread_worker *worker = work->worker; /* * del_timer_sync() must be called to make sure that the timer * callback is not running. The lock must be temporary released * to avoid a deadlock with the callback. In the meantime, * any queuing is blocked by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, *flags); del_timer_sync(&dwork->timer); raw_spin_lock_irqsave(&worker->lock, *flags); work->canceling--; } /* * This function removes the work from the worker queue. * * It is called under worker->lock. The caller must make sure that * the timer used by delayed work is not running, e.g. by calling * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. * * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ static bool __kthread_cancel_work(struct kthread_work *work) { /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. */ if (!list_empty(&work->node)) { list_del_init(&work->node); return true; } return false; } /** * kthread_mod_delayed_work - modify delay of or queue a kthread delayed work * @worker: kthread worker to use * @dwork: kthread delayed work to queue * @delay: number of jiffies to wait before queuing * * If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is zero, * @work is guaranteed to be queued immediately. * * Return: %false if @dwork was idle and queued, %true otherwise. * * A special case is when the work is being canceled in parallel. * It might be caused either by the real kthread_cancel_delayed_work_sync() * or yet another kthread_mod_delayed_work() call. We let the other command * win and return %true here. The return value can be used for reference * counting and the number of queued works stays the same. Anyway, the caller * is supposed to synchronize these operations a reasonable way. * * This function is safe to call from any context including IRQ handler. * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() * for details. */ bool kthread_mod_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; int ret; raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ if (!work->worker) { ret = false; goto fast_queue; } /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); /* * Temporary cancel the work but do not fight with another command * that is canceling the work as well. * * It is a bit tricky because of possible races with another * mod_delayed_work() and cancel_delayed_work() callers. * * The timer must be canceled first because worker->lock is released * when doing so. But the work can be removed from the queue (list) * only when it can be queued again so that the return value can * be used for reference counting. */ kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) { /* The number of works in the queue does not change. */ ret = true; goto out; } ret = __kthread_cancel_work(work); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) { struct kthread_worker *worker = work->worker; unsigned long flags; int ret = false; if (!worker) goto out; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (is_dwork) kthread_cancel_delayed_work_timer(work, &flags); ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; /* * The work is in progress and we need to wait with the lock released. * In the meantime, block any queuing by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, flags); kthread_flush_work(work); raw_spin_lock_irqsave(&worker->lock, flags); work->canceling--; out_fast: raw_spin_unlock_irqrestore(&worker->lock, flags); out: return ret; } /** * kthread_cancel_work_sync - cancel a kthread work and wait for it to finish * @work: the kthread work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself. On return from this * function, @work is guaranteed to be not pending or executing on any CPU. * * kthread_cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use kthread_cancel_delayed_work_sync() instead. * * The caller must ensure that the worker on which @work was last * queued can't be destroyed before this function returns. * * Return: %true if @work was pending, %false otherwise. */ bool kthread_cancel_work_sync(struct kthread_work *work) { return __kthread_cancel_work_sync(work, false); } EXPORT_SYMBOL_GPL(kthread_cancel_work_sync); /** * kthread_cancel_delayed_work_sync - cancel a kthread delayed work and * wait for it to finish. * @dwork: the kthread delayed work to cancel * * This is kthread_cancel_work_sync() for delayed works. * * Return: %true if @dwork was pending, %false otherwise. */ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork) { return __kthread_cancel_work_sync(&dwork->work, true); } EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync); /** * kthread_flush_worker - flush all current works on a kthread_worker * @worker: worker to flush * * Wait until all currently executing or pending works on @worker are * finished. */ void kthread_flush_worker(struct kthread_worker *worker) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; kthread_queue_work(worker, &fwork.work); wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_worker); /** * kthread_destroy_worker - destroy a kthread worker * @worker: worker to be destroyed * * Flush and destroy @worker. The simple flush is enough because the kthread * worker API is used only in trivial scenarios. There are no multi-step state * machines needed. */ void kthread_destroy_worker(struct kthread_worker *worker) { struct task_struct *task; task = worker->task; if (WARN_ON(!task)) return; kthread_flush_worker(worker); kthread_stop(task); WARN_ON(!list_empty(&worker->work_list)); kfree(worker); } EXPORT_SYMBOL(kthread_destroy_worker); /** * kthread_use_mm - make the calling kthread operate on an address space * @mm: address space to operate on */ void kthread_use_mm(struct mm_struct *mm) { struct mm_struct *active_mm; struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); task_lock(tsk); /* Hold off tlb flush IPIs while switching mm's */ local_irq_disable(); active_mm = tsk->active_mm; if (active_mm != mm) { mmgrab(mm); tsk->active_mm = mm; } tsk->mm = mm; switch_mm_irqs_off(active_mm, mm, tsk); local_irq_enable(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); #endif if (active_mm != mm) mmdrop(active_mm); to_kthread(tsk)->oldfs = force_uaccess_begin(); } EXPORT_SYMBOL_GPL(kthread_use_mm); /** * kthread_unuse_mm - reverse the effect of kthread_use_mm() * @mm: address space to operate on */ void kthread_unuse_mm(struct mm_struct *mm) { struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(!tsk->mm); force_uaccess_end(to_kthread(tsk)->oldfs); task_lock(tsk); sync_mm_rss(mm); local_irq_disable(); tsk->mm = NULL; /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); local_irq_enable(); task_unlock(tsk); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); #ifdef CONFIG_BLK_CGROUP /** * kthread_associate_blkcg - associate blkcg to current kthread * @css: the cgroup info * * Current thread must be a kthread. The thread is running jobs on behalf of * other threads. In some cases, we expect the jobs attach cgroup info of * original threads instead of that of current thread. This function stores * original thread's cgroup info in current kthread context for later * retrieval. */ void kthread_associate_blkcg(struct cgroup_subsys_state *css) { struct kthread *kthread; if (!(current->flags & PF_KTHREAD)) return; kthread = to_kthread(current); if (!kthread) return; if (kthread->blkcg_css) { css_put(kthread->blkcg_css); kthread->blkcg_css = NULL; } if (css) { css_get(css); kthread->blkcg_css = css; } } EXPORT_SYMBOL(kthread_associate_blkcg); /** * kthread_blkcg - get associated blkcg css of current kthread * * Current thread must be a kthread. */ struct cgroup_subsys_state *kthread_blkcg(void) { struct kthread *kthread; if (current->flags & PF_KTHREAD) { kthread = to_kthread(current); if (kthread) return kthread->blkcg_css; } return NULL; } EXPORT_SYMBOL(kthread_blkcg); #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; unsigned long low, min; long delta; if (!c->parent) return; min = READ_ONCE(c->min); if (min || atomic_long_read(&c->min_usage)) { protected = min(usage, min); old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } low = READ_ONCE(c->low); if (low || atomic_long_read(&c->low_usage)) { protected = min(usage, low); old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); propagate_protected_usage(counter, new); /* More uncharges than charges? */ WARN_ON_ONCE(new < 0); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = atomic_long_read(&counter->usage); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (atomic_long_read(&counter->usage) <= usage) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.rst for more details. */ #ifndef __LINUX_LOCKDEP_H #define __LINUX_LOCKDEP_H #include <linux/lockdep_types.h> #include <linux/smp.h> #include <asm/percpu.h> struct task_struct; /* for sysctl */ extern int prove_locking; extern int lock_stat; #ifdef CONFIG_LOCKDEP #include <linux/linkage.h> #include <linux/list.h> #include <linux/debug_locks.h> #include <linux/stacktrace.h> static inline void lockdep_copy_map(struct lockdep_map *to, struct lockdep_map *from) { int i; *to = *from; /* * Since the class cache can be modified concurrently we could observe * half pointers (64bit arch using 32bit copy insns). Therefore clear * the caches and take the performance hit. * * XXX it doesn't work well with lockdep_set_class_and_subclass(), since * that relies on cache abuse. */ for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) to->class_cache[i] = NULL; } /* * Every lock has a list of other locks that were taken after it. * We only grow the list, never remove from it: */ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; const struct lock_trace *trace; u16 distance; /* bitmap of different dependencies from head to this */ u8 dep; /* used by BFS to record whether "prev -> this" only has -(*R)-> */ u8 only_xr; /* * The parent field is used to implement breadth-first search, and the * bit 0 is reused to indicate if the lock has been accessed in BFS. */ struct lock_list *parent; }; /** * struct lock_chain - lock dependency chain record * * @irq_context: the same as irq_context in held_lock below * @depth: the number of held locks in this chain * @base: the index in chain_hlocks for this chain * @entry: the collided lock chains in lock_chain hash list * @chain_key: the hash key of this lock_chain */ struct lock_chain { /* see BUILD_BUG_ON()s in add_chain_cache() */ unsigned int irq_context : 2, depth : 6, base : 24; /* 4 byte hole */ struct hlist_node entry; u64 chain_key; }; #define MAX_LOCKDEP_KEYS_BITS 13 #define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) #define INITIAL_CHAIN_KEY -1 struct held_lock { /* * One-way hash of the dependency chain up to this point. We * hash the hashes step by step as the dependency chain grows. * * We use it for dependency-caching and we skip detection * passes and dependency-updates if there is a cache-hit, so * it is absolutely critical for 100% coverage of the validator * to have a unique key value for every unique dependency path * that can occur in the system, to make a unique hash value * as likely as possible - hence the 64-bit width. * * The task struct holds the current hash value (initialized * with zero), here we store the previous hash value: */ u64 prev_chain_key; unsigned long acquire_ip; struct lockdep_map *instance; struct lockdep_map *nest_lock; #ifdef CONFIG_LOCK_STAT u64 waittime_stamp; u64 holdtime_stamp; #endif /* * class_idx is zero-indexed; it points to the element in * lock_classes this held lock instance belongs to. class_idx is in * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. */ unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; /* * The lock-stack is unified in that the lock chains of interrupt * contexts nest ontop of process context chains, but we 'separate' * the hashes by starting with 0 if we cross into an interrupt * context, and we also keep do not add cross-context lock * dependencies - the lock usage graph walking covers that area * anyway, and we'd just unnecessarily increase the number of * dependencies otherwise. [Note: hardirq and softirq contexts * are separated from each other too.] * * The following field is used to detect when we cross into an * interrupt context: */ unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ unsigned int trylock:1; /* 16 bits */ unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ unsigned int pin_count; }; /* * Initialization, self-test and debugging-output methods: */ extern void lockdep_init(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); extern asmlinkage void lockdep_sys_exit(void); extern void lockdep_set_selftest_task(struct task_struct *task); extern void lockdep_init_task(struct task_struct *task); /* * Split the recrursion counter in two to readily detect 'off' vs recursion. */ #define LOCKDEP_RECURSION_BITS 16 #define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS) #define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1) /* * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due * to header dependencies. */ #define lockdep_off() \ do { \ current->lockdep_recursion += LOCKDEP_OFF; \ } while (0) #define lockdep_on() \ do { \ current->lockdep_recursion -= LOCKDEP_OFF; \ } while (0) extern void lockdep_register_key(struct lock_class_key *key); extern void lockdep_unregister_key(struct lock_class_key *key); /* * These methods are used by specific locking variants (spinlocks, * rwlocks, mutexes and rwsems) to pass init/acquire/release events * to lockdep: */ extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type); static inline void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer) { lockdep_init_map_type(lock, name, key, subclass, inner, outer, LD_LOCK_NORMAL); } static inline void lockdep_init_map_wait(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner) { lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV); } static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass) { lockdep_init_map_wait(lock, name, key, subclass, LD_WAIT_INV); } /* * Reinitialize a lock key - for cases where there is special locking or * special initialization of locks so that the validator gets the scope * of dependencies wrong: they are either too broad (they need a class-split) * or they are too narrow (they suffer from a false class-split): */ #define lockdep_set_class(lock, key) \ lockdep_init_map_type(&(lock)->dep_map, #key, key, 0, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_class_and_name(lock, key, name) \ lockdep_init_map_type(&(lock)->dep_map, name, key, 0, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_class_and_subclass(lock, key, sub) \ lockdep_init_map_type(&(lock)->dep_map, #key, key, sub, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_subclass(lock, sub) \ lockdep_init_map_type(&(lock)->dep_map, (lock)->dep_map.name, (lock)->dep_map.key, sub,\ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_novalidate_class(lock) \ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) /* * Compare locking classes */ #define lockdep_match_class(lock, key) lockdep_match_key(&(lock)->dep_map, key) static inline int lockdep_match_key(struct lockdep_map *lock, struct lock_class_key *key) { return lock->key == key; } /* * Acquire a lock. * * Values for "read": * * 0: exclusive (write) acquire * 1: read-acquire (no recursion allowed) * 2: read-acquire with same-instance recursion allowed * * Values for check: * * 0: simple checks (freeing, held-at-exit-time, etc.) * 1: full validation */ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); extern void lock_release(struct lockdep_map *lock, unsigned long ip); /* * Same "read" as for lock_acquire(), except -1 means any. */ extern int lock_is_held_type(const struct lockdep_map *lock, int read); static inline int lock_is_held(const struct lockdep_map *lock) { return lock_is_held_type(lock, -1); } #define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) #define lockdep_is_held_type(lock, r) lock_is_held_type(&(lock)->dep_map, (r)) extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, unsigned long ip); static inline void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, unsigned long ip) { lock_set_class(lock, lock->name, lock->key, subclass, ip); } extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); #define NIL_COOKIE (struct pin_cookie){ .val = 0U, } extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) #define lockdep_assert_held(l) do { \ WARN_ON(debug_locks && !lockdep_is_held(l)); \ } while (0) #define lockdep_assert_held_write(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 0)); \ } while (0) #define lockdep_assert_held_read(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 1)); \ } while (0) #define lockdep_assert_held_once(l) do { \ WARN_ON_ONCE(debug_locks && !lockdep_is_held(l)); \ } while (0) #define lockdep_assert_none_held_once() do { \ WARN_ON_ONCE(debug_locks && current->lockdep_depth); \ } while (0) #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) #define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) { } static inline void lockdep_off(void) { } static inline void lockdep_on(void) { } static inline void lockdep_set_selftest_task(struct task_struct *task) { } # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_wait(lock, name, key, sub, inner) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) # define lockdep_set_class_and_name(lock, key, name) \ do { (void)(key); (void)(name); } while (0) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) #define lockdep_set_subclass(lock, sub) do { } while (0) #define lockdep_set_novalidate_class(lock) do { } while (0) /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP * case since the result is not well defined and the caller should rather * #ifdef the call himself. */ # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) # define lockdep_sys_exit() do { } while (0) static inline void lockdep_register_key(struct lock_class_key *key) { } static inline void lockdep_unregister_key(struct lock_class_key *key) { } #define lockdep_depth(tsk) (0) #define lockdep_is_held_type(l, r) (1) #define lockdep_assert_held(l) do { (void)(l); } while (0) #define lockdep_assert_held_write(l) do { (void)(l); } while (0) #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_assert_none_held_once() do { } while (0) #define lockdep_recursing(tsk) (0) #define NIL_COOKIE (struct pin_cookie){ } #define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) #endif /* !LOCKDEP */ enum xhlock_context_t { XHLOCK_HARD, XHLOCK_SOFT, XHLOCK_CTX_NR, }; #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) /* * To initialize a lockdep_map statically use this macro. * Note that _name must not be NULL. */ #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_free_task(struct task_struct *task) {} #ifdef CONFIG_LOCK_STAT extern void lock_contended(struct lockdep_map *lock, unsigned long ip); extern void lock_acquired(struct lockdep_map *lock, unsigned long ip); #define LOCK_CONTENDED(_lock, try, lock) \ do { \ if (!try(_lock)) { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ lock(_lock); \ } \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ } while (0) #define LOCK_CONTENDED_RETURN(_lock, try, lock) \ ({ \ int ____err = 0; \ if (!try(_lock)) { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ ____err = lock(_lock); \ } \ if (!____err) \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ ____err; \ }) #else /* CONFIG_LOCK_STAT */ #define lock_contended(lockdep_map, ip) do {} while (0) #define lock_acquired(lockdep_map, ip) do {} while (0) #define LOCK_CONTENDED(_lock, try, lock) \ lock(_lock) #define LOCK_CONTENDED_RETURN(_lock, try, lock) \ lock(_lock) #endif /* CONFIG_LOCK_STAT */ #ifdef CONFIG_LOCKDEP /* * On lockdep we dont want the hand-coded irq-enable of * _raw_*_lock_flags() code, because lockdep assumes * that interrupts are not re-enabled during lock-acquire: */ #define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ LOCK_CONTENDED((_lock), (try), (lock)) #else /* CONFIG_LOCKDEP */ #define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ lockfl((_lock), (flags)) #endif /* CONFIG_LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING extern void print_irqtrace_events(struct task_struct *curr); #else static inline void print_irqtrace_events(struct task_struct *curr) { } #endif /* Variable used to make lockdep treat read_lock() as recursive in selftests */ #ifdef CONFIG_DEBUG_LOCKING_API_SELFTESTS extern unsigned int force_read_lock_recursive; #else /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ #define force_read_lock_recursive 0 #endif /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ #ifdef CONFIG_LOCKDEP extern bool read_lock_is_recursive(void); #else /* CONFIG_LOCKDEP */ /* If !LOCKDEP, the value is meaningless */ #define read_lock_is_recursive() 0 #endif /* * For trivial one-depth nesting of a lock-class, the following * global define can be used. (Subsystems with multiple levels * of nesting should define their own lock-nesting subclasses.) */ #define SINGLE_DEPTH_NESTING 1 /* * Map the dependency ops to NOP or to real lockdep ops, depending * on the per lock-class debug mode: */ #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define spin_release(l, i) lock_release(l, i) #define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwlock_acquire_read(l, s, t, i) \ do { \ if (read_lock_is_recursive()) \ lock_acquire_shared_recursive(l, s, t, NULL, i); \ else \ lock_acquire_shared(l, s, t, NULL, i); \ } while (0) #define rwlock_release(l, i) lock_release(l, i) #define seqcount_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define seqcount_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) #define seqcount_release(l, i) lock_release(l, i) #define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define mutex_release(l, i) lock_release(l, i) #define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_nested(lock, subclass) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL, \ _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); DECLARE_PER_CPU(unsigned int, lockdep_recursion); #define __lockdep_enabled (debug_locks && !this_cpu_read(lockdep_recursion)) #define lockdep_assert_irqs_enabled() \ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ WARN_ON_ONCE(__lockdep_enabled && this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() != 0 || \ !this_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() == 0 && \ this_cpu_read(hardirqs_enabled))); \ } while (0) #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) # define might_lock_nested(lock, subclass) do { } while (0) # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING # define lockdep_assert_RT_in_threaded_ctx() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ lockdep_hardirq_context() && \ !(current->hardirq_threaded || current->irq_config), \ "Not in threaded context on PREEMPT_RT as expected\n"); \ } while (0) #else # define lockdep_assert_RT_in_threaded_ctx() do { } while (0) #endif #ifdef CONFIG_LOCKDEP void lockdep_rcu_suspicious(const char *file, const int line, const char *s); #else static inline void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { } #endif #endif /* __LINUX_LOCKDEP_H */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return *fsnotify_conn_mask_p(conn); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; return fsnotify_update_iref(conn, want_iref); } static bool fsnotify_conn_watches_children( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return false; return fsnotify_inode_watches_children(fsnotify_conn_inode(conn)); } static void fsnotify_conn_set_children_dentry_flags( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return; fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn)); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { bool update_children; if (!conn) return; spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); __fsnotify_recalc_mask(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* * Set children's PARENT_WATCHED flags only if parent started watching. * When parent stops watching, we clear false positive PARENT_WATCHED * flags lazily in __fsnotify_parent(). */ if (update_children) fsnotify_conn_set_children_dentry_flags(conn); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void fsnotify_put_inode_ref(struct inode *inode) { struct super_block *sb = inode->i_sb; iput(inode); if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb) atomic_long_inc(&sb->s_fsnotify_connectors); } static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } fsnotify_put_sb_connectors(conn); rcu_assign_pointer(*(conn->obj), NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, unsigned int obj_type, __kernel_fsid_t *fsid) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->type = obj_type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ if (fsid) { conn->fsid = *fsid; conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID; } else { conn->fsid.val[0] = conn->fsid.val[1] = 0; conn->flags = 0; } fsnotify_get_sb_connectors(conn); /* * cmpxchg() provides the barrier so that readers of *connp can see * only initialized structure */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ fsnotify_put_sb_connectors(conn); kmem_cache_free(fsnotify_mark_connector_cachep, conn); } return 0; } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; int idx; idx = srcu_read_lock(&fsnotify_mark_srcu); conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn) goto out; spin_lock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) { spin_unlock(&conn->lock); srcu_read_unlock(&fsnotify_mark_srcu, idx); return NULL; } out: srcu_read_unlock(&fsnotify_mark_srcu, idx); return conn; } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; int cmp; int err = 0; if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* Backend is expected to check for zero fsid (e.g. tmpfs) */ if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1])) return -ENODEV; restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); err = fsnotify_attach_connector_to_object(connp, obj_type, fsid); if (err) return err; goto restart; } else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) { conn->fsid = *fsid; /* Pairs with smp_rmb() in fanotify_get_fsid() */ smp_wmb(); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID; } else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) && (fsid->val[0] != conn->fsid.val[0] || fsid->val[1] != conn->fsid.val[1])) { /* * Backend is expected to check for non uniform fsid * (e.g. btrfs), but maybe we missed something? * Only allow setting conn->fsid once to non zero fsid. * inotify and non-fid fanotify groups do not set nor test * conn->fsid. */ pr_warn_ratelimited("%s: fsid mismatch on object of type %u: " "%x.%x != %x.%x\n", __func__, conn->type, fsid->val[0], fsid->val[1], conn->fsid.val[0], conn->fsid.val[1]); err = -EXDEV; goto out_err; } /* is mark the first mark? */ if (hlist_empty(&conn->list)) { hlist_add_head_rcu(&mark->obj_list, &conn->list); goto added; } /* should mark be in the middle of the current list? */ hlist_for_each_entry(lmark, &conn->list, obj_list) { last = lmark; if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } cmp = fsnotify_compare_groups(lmark->group, mark->group); if (cmp >= 0) { hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list); goto added; } } BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone * seeing mark->connector set. */ WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); return err; } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; int ret = 0; fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! * group->mark_mutex * mark->lock * mark->connector->lock */ spin_lock(&mark->lock); mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED; list_add(&mark->g_list, &group->marks_list); fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid); if (ret) goto err; fsnotify_recalc_mask(mark->connector); return ret; err: spin_lock(&mark->lock); mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED); list_del_init(&mark->g_list); spin_unlock(&mark->lock); fsnotify_put_mark(mark); return ret; } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; fsnotify_group_lock(group); ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid); fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark; conn = fsnotify_grab_connector(connp); if (!conn) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group && (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); return mark; } } spin_unlock(&conn->lock); return NULL; } EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } /* * We have to be really careful here. Anytime we drop mark_mutex, e.g. * fsnotify_clear_marks_by_inode() can come and free marks. Even in our * to_free list so we have to use mark_mutex even when accessing that * list. And freeing mark requires us to drop mark_mutex. So we can * reliably free only the first mark in the list. That's why we first * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } fsnotify_group_unlock(group); clear: while (1) { fsnotify_group_lock(group); if (list_empty(head)) { fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; void *objp; unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) return; /* * We have to be careful since we can race with e.g. * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the * list can get modified. However we are holding mark reference and * thus our mark cannot be removed from obj_list so we can continue * iteration after regaining conn->lock. */ hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); old_mark = mark; fsnotify_destroy_mark(mark, mark->group); spin_lock(&conn->lock); } /* * Detach list from object now so that we don't pin inode until all * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp); } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { memset(mark, 0, sizeof(*mark)); spin_lock_init(&mark->lock); refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; WRITE_ONCE(mark->connector, NULL); } EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; spin_lock(&destroy_lock); /* exchange the list head */ list_replace_init(&destroy_list, &private_destroy_list); spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { list_del_init(&mark->g_list); fsnotify_final_mark_destroy(mark); } } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { flush_delayed_work(&reaper_work); } EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/tracepoint-defs.h> /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_ATOMIC) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) void page_writeback_init(void); /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ int mmap_file(struct file *file, struct vm_area_struct *vma); /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ void vma_close(struct vm_area_struct *vma); vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_size); void force_page_cache_ra(struct readahead_control *, struct file_ra_state *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, mapping, index); force_page_cache_ra(&ractl, &file->f_ra, nr_to_read); } struct page *find_get_entry(struct address_space *mapping, pgoff_t index); struct page *find_lock_entry(struct address_space *mapping, pgoff_t index); /** * page_evictable - test whether a page is evictable * @page: the page to test * * Test whether page is evictable--i.e., should be placed on active/inactive * lists vs unevictable list. * * Reasons page might not be evictable: * (1) page's mapping marked unevictable * (2) page is part of an mlocked VMA * */ static inline bool page_evictable(struct page *page) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); /* * in mm/rmap.c: */ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages_nodemask() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages_nodemask() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock or sched contention */ bool rescan; /* Rescanning the same pageblock */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); unsigned long isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); #endif /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area - atomatically grows in one direction * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return (flags & VM_STACK) == VM_STACK; } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev); void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *nonblocking); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) { munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end); } /* * must be called with vma's mmap_lock held for read or write, and page locked. */ extern void mlock_vma_page(struct page *page); extern unsigned int munlock_vma_page(struct page *page); /* * Clear the page's PageMlocked(). This can be useful in a situation where * we want to unconditionally remove a page from the pagecache -- e.g., * on truncation or freeing. * * It is legal to call this function for any page, mlocked or not. * If called for a page that is still mapped by mlocked vmas, all we do * is revert to lazy LRU behaviour -- semantics are not broken. */ extern void clear_page_mlock(struct page *page); /* * mlock_migrate_page - called only from migrate_misplaced_transhuge_page() * (because that does not go through the full procedure of migration ptes): * to migrate the Mlocked page flag; update statistics. */ static inline void mlock_migrate_page(struct page *newpage, struct page *page) { if (TestClearPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* Holding pmd lock, no change in irq context: __mod is safe */ __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); SetPageMlocked(newpage); __mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages); } } extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* * At what user virtual address is page expected in vma? * Returns -EFAULT if all of the page is outside the range of vma. * If page is a compound head, the entire compound page is considered. */ static inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff; unsigned long address; VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ pgoff = page_to_pgoff(page); if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (PageHead(page) && pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the page be found in vma? * Assumes that vma_address() already returned a good starting address. * If page is a compound head, the entire compound page is considered. */ static inline unsigned long vma_address_end(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff; unsigned long address; VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ pgoff = page_to_pgoff(page) + compound_nr(page); address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); mmap_read_unlock(vmf->vma->vm_mm); } return fpin; } #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } #endif /* !CONFIG_MMU */ /* * Return the mem_map entry representing the 'offset' subpage within * the maximally aligned gigantic page 'base'. Handle any discontiguity * in the mem_map at MAX_ORDER_NR_PAGES boundaries. */ static inline struct page *mem_map_offset(struct page *base, int offset) { if (unlikely(offset >= MAX_ORDER_NR_PAGES)) return nth_page(base, offset); return base + offset; } /* * Iterator over all subpages within the maximally aligned gigantic * page 'base'. Handle any discontiguity in the mem_map. */ static inline struct page *mem_map_next(struct page *iter, struct page *base, int offset) { if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) { unsigned long pfn = page_to_pfn(base) + offset; if (!pfn_valid(pfn)) return NULL; return pfn_to_page(pfn); } return iter + 1; } /* Memory initialisation debug and verification */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ /* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ #if defined(CONFIG_SPARSEMEM) extern void mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn); #else static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { } #endif /* CONFIG_SPARSEMEM */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } #endif extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } static inline bool is_migrate_highatomic_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; }; #endif /* __MM_INTERNAL_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> #include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> #include <linux/mmdebug.h> #include <linux/perf_event.h> #include <linux/audit.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/rbtree_augmented.h> #include <linux/notifier.h> #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #define CREATE_TRACE_POINTS #include <trace/events/mmap.h> #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes */ pgprot_t protection_map[16] __ro_after_init = { __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 }; #ifndef CONFIG_ARCH_HAS_FILTER_PGPROT static inline pgprot_t arch_filter_pgprot(pgprot_t prot) { return prot; } #endif pgprot_t vm_get_page_prot(unsigned long vm_flags) { pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | pgprot_val(arch_vm_get_page_prot(vm_flags))); return arch_filter_pgprot(ret); } EXPORT_SYMBOL(vm_get_page_prot); static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { if (vma->vm_flags & VM_DENYWRITE) allow_write_access(file); if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, file, mapping); i_mmap_unlock_write(mapping); } } /* * Close a vm structure and free it, returning the next. */ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) { struct vm_area_struct *next = vma->vm_next; might_sleep(); vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); vm_area_free(vma); return next; } static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long retval; unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *next; unsigned long min_brk; bool populate; bool downgraded = false; LIST_HEAD(uf); if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* * Always allow shrinking brk. * __do_munmap() may downgrade mmap_lock to read. */ if (brk <= mm->brk) { int ret; /* * mm->brk must to be protected by write mmap_lock so update it * before downgrading mmap_lock. When __do_munmap() fails, * mm->brk will be restored from origbrk. */ mm->brk = brk; ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true); if (ret < 0) { mm->brk = origbrk; goto out; } else if (ret == 1) { downgraded = true; } goto success; } /* Check against existing mmap mappings. */ next = find_vma(mm, oldbrk); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; /* Ok, looks good - let it rip. */ if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0) goto out; mm->brk = brk; success: populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; if (downgraded) mmap_read_unlock(mm); else mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: retval = origbrk; mmap_write_unlock(mm); return retval; } static inline unsigned long vma_compute_gap(struct vm_area_struct *vma) { unsigned long gap, prev_end; /* * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we * allow two stack_guard_gaps between them here, and when choosing * an unmapped area; whereas when expanding we only require one. * That's a little inconsistent, but keeps the code here simpler. */ gap = vm_start_gap(vma); if (vma->vm_prev) { prev_end = vm_end_gap(vma->vm_prev); if (gap > prev_end) gap -= prev_end; else gap = 0; } return gap; } #ifdef CONFIG_DEBUG_VM_RB static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma) { unsigned long max = vma_compute_gap(vma), subtree_gap; if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; if (subtree_gap > max) max = subtree_gap; } if (vma->vm_rb.rb_right) { subtree_gap = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb)->rb_subtree_gap; if (subtree_gap > max) max = subtree_gap; } return max; } static int browse_rb(struct mm_struct *mm) { struct rb_root *root = &mm->mm_rb; int i = 0, j, bug = 0; struct rb_node *nd, *pn = NULL; unsigned long prev = 0, pend = 0; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); if (vma->vm_start < prev) { pr_emerg("vm_start %lx < prev %lx\n", vma->vm_start, prev); bug = 1; } if (vma->vm_start < pend) { pr_emerg("vm_start %lx < pend %lx\n", vma->vm_start, pend); bug = 1; } if (vma->vm_start > vma->vm_end) { pr_emerg("vm_start %lx > vm_end %lx\n", vma->vm_start, vma->vm_end); bug = 1; } spin_lock(&mm->page_table_lock); if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { pr_emerg("free gap %lx, correct %lx\n", vma->rb_subtree_gap, vma_compute_subtree_gap(vma)); bug = 1; } spin_unlock(&mm->page_table_lock); i++; pn = nd; prev = vma->vm_start; pend = vma->vm_end; } j = 0; for (nd = pn; nd; nd = rb_prev(nd)) j++; if (i != j) { pr_emerg("backwards %d, forwards %d\n", j, i); bug = 1; } return bug ? -1 : i; } static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) { struct rb_node *nd; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); VM_BUG_ON_VMA(vma != ignore && vma->rb_subtree_gap != vma_compute_subtree_gap(vma), vma); } } static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; unsigned long highest_address = 0; struct vm_area_struct *vma = mm->mmap; while (vma) { struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } highest_address = vm_end_gap(vma); vma = vma->vm_next; i++; } if (i != mm->map_count) { pr_emerg("map_count %d vm_next %d\n", mm->map_count, i); bug = 1; } if (highest_address != mm->highest_vm_end) { pr_emerg("mm->highest_vm_end %lx, found %lx\n", mm->highest_vm_end, highest_address); bug = 1; } i = browse_rb(mm); if (i != mm->map_count) { if (i != -1) pr_emerg("map_count %d rb %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #else #define validate_mm_rb(root, ignore) do { } while (0) #define validate_mm(mm) do { } while (0) #endif RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, unsigned long, rb_subtree_gap, vma_compute_gap) /* * Update augmented rbtree rb_subtree_gap values after vma->vm_start or * vma->vm_prev->vm_end values changed, without modifying the vma's position * in the rbtree. */ static void vma_gap_update(struct vm_area_struct *vma) { /* * As it turns out, RB_DECLARE_CALLBACKS_MAX() already created * a callback function that does exactly what we want. */ vma_gap_callbacks_propagate(&vma->vm_rb, NULL); } static inline void vma_rb_insert(struct vm_area_struct *vma, struct rb_root *root) { /* All rb_subtree_gap values must be consistent prior to insertion */ validate_mm_rb(root, NULL); rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) { /* * Note rb_erase_augmented is a fairly large inline function, * so make sure we instantiate it only once with our desired * augmented rbtree callbacks. */ rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, struct rb_root *root, struct vm_area_struct *ignore) { /* * All rb_subtree_gap values must be consistent prior to erase, * with the possible exception of * * a. the "next" vma being erased if next->vm_start was reduced in * __vma_adjust() -> __vma_unlink() * b. the vma being erased in detach_vmas_to_be_unmapped() -> * vma_rb_erase() */ validate_mm_rb(root, ignore); __vma_rb_erase(vma, root); } static __always_inline void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) { vma_rb_erase_ignore(vma, root, vma); } /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static inline void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static inline void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } static int find_vma_links(struct mm_struct *mm, unsigned long addr, unsigned long end, struct vm_area_struct **pprev, struct rb_node ***rb_link, struct rb_node **rb_parent) { struct rb_node **__rb_link, *__rb_parent, *rb_prev; __rb_link = &mm->mm_rb.rb_node; rb_prev = __rb_parent = NULL; while (*__rb_link) { struct vm_area_struct *vma_tmp; __rb_parent = *__rb_link; vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb); if (vma_tmp->vm_end > addr) { /* Fail if an existing vma overlaps the area */ if (vma_tmp->vm_start < end) return -ENOMEM; __rb_link = &__rb_parent->rb_left; } else { rb_prev = __rb_parent; __rb_link = &__rb_parent->rb_right; } } *pprev = NULL; if (rb_prev) *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); *rb_link = __rb_link; *rb_parent = __rb_parent; return 0; } /* * vma_next() - Get the next VMA. * @mm: The mm_struct. * @vma: The current vma. * * If @vma is NULL, return the first vma in the mm. * * Returns: The next VMA after @vma. */ static inline struct vm_area_struct *vma_next(struct mm_struct *mm, struct vm_area_struct *vma) { if (!vma) return mm->mmap; return vma->vm_next; } /* * munmap_vma_range() - munmap VMAs that overlap a range. * @mm: The mm struct * @start: The start of the range. * @len: The length of the range. * @pprev: pointer to the pointer that will be set to previous vm_area_struct * @rb_link: the rb_node * @rb_parent: the parent rb_node * * Find all the vm_area_struct that overlap from @start to * @end and munmap them. Set @pprev to the previous vm_area_struct. * * Returns: -ENOMEM on munmap failure or 0 on success. */ static inline int munmap_vma_range(struct mm_struct *mm, unsigned long start, unsigned long len, struct vm_area_struct **pprev, struct rb_node ***link, struct rb_node **parent, struct list_head *uf) { while (find_vma_links(mm, start, start + len, pprev, link, parent)) if (do_munmap(mm, start, len, uf)) return -ENOMEM; return 0; } static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { unsigned long nr_pages = 0; struct vm_area_struct *vma; /* Find first overlaping mapping */ vma = find_vma_intersection(mm, addr, end); if (!vma) return 0; nr_pages = (min(end, vma->vm_end) - max(addr, vma->vm_start)) >> PAGE_SHIFT; /* Iterate over the rest of the overlaps */ for (vma = vma->vm_next; vma; vma = vma->vm_next) { unsigned long overlap_len; if (vma->vm_start > end) break; overlap_len = min(end, vma->vm_end) - vma->vm_start; nr_pages += overlap_len >> PAGE_SHIFT; } return nr_pages; } void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { /* Update tracking information for the gap following the new vma. */ if (vma->vm_next) vma_gap_update(vma->vm_next); else mm->highest_vm_end = vm_end_gap(vma); /* * vma->vm_prev wasn't known when we followed the rbtree to find the * correct insertion point for that vma. As a result, we could not * update the vma vm_rb parents rb_subtree_gap values on the way down. * So, we first insert the vma with a zero rb_subtree_gap value * (to be consistent with what we did on the way down), and then * immediately update the gap to the correct value. Finally we * rebalance the rbtree after all augmented values have been set. */ rb_link_node(&vma->vm_rb, rb_parent, rb_link); vma->rb_subtree_gap = 0; vma_gap_update(vma); vma_rb_insert(vma, &mm->mm_rb); } static void __vma_link_file(struct vm_area_struct *vma) { struct file *file; file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) put_write_access(file_inode(file)); if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } static void __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { __vma_link_list(mm, vma, prev); __vma_link_rb(mm, vma, rb_link, rb_parent); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { struct address_space *mapping = NULL; if (vma->vm_file) { mapping = vma->vm_file->f_mapping; i_mmap_lock_write(mapping); } __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); if (mapping) i_mmap_unlock_write(mapping); mm->map_count++; validate_mm(mm); } /* * Helper for vma_adjust() in the split_vma insert case: insert a vma into the * mm's list and rbtree. It has already been inserted into the interval tree. */ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev; struct rb_node **rb_link, *rb_parent; if (find_vma_links(mm, vma->vm_start, vma->vm_end, &prev, &rb_link, &rb_parent)) BUG(); __vma_link(mm, vma, prev, rb_link, rb_parent); mm->map_count++; } static __always_inline void __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *ignore) { vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); __vma_unlink_list(mm, vma); /* Kill the cache */ vmacache_invalidate(mm); } /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. * The following helper function should be used when such adjustments * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; struct address_space *mapping = NULL; struct rb_root_cached *root = NULL; struct anon_vma *anon_vma = NULL; struct file *file = vma->vm_file; bool start_changed = false, end_changed = false; long adjust_next = 0; int remove_next = 0; if (next && !insert) { struct vm_area_struct *exporter = NULL, *importer = NULL; if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). * The only other cases that gets here are * case 1, case 7 and case 8. */ if (next == expand) { /* * The only case where we don't expand "vma" * and we expand "next" instead is case 8. */ VM_WARN_ON(end != next->vm_end); /* * remove_next == 3 means we're * removing "vma" and that to do so we * swapped "vma" and "next". */ remove_next = 3; VM_WARN_ON(file != next->vm_file); swap(vma, next); } else { VM_WARN_ON(expand != vma); /* * case 1, 6, 7, remove_next == 2 is case 6, * remove_next == 1 is case 1 or 7. */ remove_next = 1 + (end > next->vm_end); VM_WARN_ON(remove_next == 2 && end != next->vm_next->vm_end); /* trim end to next, for case 6 first pass */ end = next->vm_end; } exporter = next; importer = vma; /* * If next doesn't have anon_vma, import from vma after * next, if the vma overlaps with it. */ if (remove_next == 2 && !next->anon_vma) exporter = next->vm_next; } else if (end > next->vm_start) { /* * vma expands, overlapping part of the next: * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start); exporter = next; importer = vma; VM_WARN_ON(expand != importer); } else if (end < vma->vm_end) { /* * vma shrinks, and !insert tells it's not * split_vma inserting another: so it must be * mprotect case 4 shifting the boundary down. */ adjust_next = -(vma->vm_end - end); exporter = vma; importer = next; VM_WARN_ON(expand != importer); } /* * Easily overlooked: when mprotect shifts the boundary, * make sure the expanding vma has anon_vma set if the * shrinking vma had, to cover any anon pages imported. */ if (exporter && exporter->anon_vma && !importer->anon_vma) { int error; importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); if (error) return error; } } again: /* * Get rid of huge pages and shared page tables straddling the split * boundary. */ vma_adjust_trans_huge(orig_vma, start, end, adjust_next); if (is_vm_hugetlb_page(orig_vma)) { hugetlb_split(orig_vma, start); hugetlb_split(orig_vma, end); } if (file) { mapping = file->f_mapping; root = &mapping->i_mmap; uprobe_munmap(vma, vma->vm_start, vma->vm_end); if (adjust_next) uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(insert); } } anon_vma = vma->anon_vma; if (!anon_vma && adjust_next) anon_vma = next->anon_vma; if (anon_vma) { VM_WARN_ON(adjust_next && next->anon_vma && anon_vma != next->anon_vma); anon_vma_lock_write(anon_vma); anon_vma_interval_tree_pre_update_vma(vma); if (adjust_next) anon_vma_interval_tree_pre_update_vma(next); } if (file) { flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, root); if (adjust_next) vma_interval_tree_remove(next, root); } if (start != vma->vm_start) { vma->vm_start = start; start_changed = true; } if (end != vma->vm_end) { vma->vm_end = end; end_changed = true; } vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; } if (file) { if (adjust_next) vma_interval_tree_insert(next, root); vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } if (remove_next) { /* * vma_merge has merged next into vma, and needs * us to remove next before dropping the locks. */ if (remove_next != 3) __vma_unlink(mm, next, next); else /* * vma is not before next if they've been * swapped. * * pre-swap() next->vm_start was reduced so * tell validate_mm_rb to ignore pre-swap() * "next" (which is stored in post-swap() * "vma"). */ __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); } else if (insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ __insert_vm_struct(mm, insert); } else { if (start_changed) vma_gap_update(vma); if (end_changed) { if (!next) mm->highest_vm_end = vm_end_gap(vma); else if (!adjust_next) vma_gap_update(next); } } if (anon_vma) { anon_vma_interval_tree_post_update_vma(vma); if (adjust_next) anon_vma_interval_tree_post_update_vma(next); anon_vma_unlock_write(anon_vma); } if (file) { i_mmap_unlock_write(mapping); uprobe_mmap(vma); if (adjust_next) uprobe_mmap(next); } if (remove_next) { if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); } if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter * up the code too much to do both in one go. */ if (remove_next != 3) { /* * If "next" was removed and vma->vm_end was * expanded (up) over it, in turn * "next->vm_prev->vm_end" changed and the * "vma->vm_next" gap must be updated. */ next = vma->vm_next; } else { /* * For the scope of the comment "next" and * "vma" considered pre-swap(): if "vma" was * removed, next->vm_start was expanded (down) * over it and the "next" gap must be updated. * Because of the swap() the post-swap() "vma" * actually points to pre-swap() "next" * (post-swap() "next" as opposed is now a * dangling pointer). */ next = vma; } if (remove_next == 2) { remove_next = 1; end = next->vm_end; goto again; } else if (next) vma_gap_update(next); else { /* * If remove_next == 2 we obviously can't * reach this path. * * If remove_next == 3 we can't reach this * path because pre-swap() next is always not * NULL. pre-swap() "next" is not being * removed and its next->vm_end is not altered * (and furthermore "end" already matches * next->vm_end in remove_next == 3). * * We reach this only in the remove_next == 1 * case if the "next" vma that was removed was * the highest vma of the mm. However in such * case next->vm_end == "end" and the extended * "vma" has vma->vm_end == next->vm_end so * mm->highest_vm_end doesn't need any update * in remove_next == 1 case. */ VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } } if (insert && file) uprobe_mmap(insert); validate_mm(mm); return 0; } /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those. */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return 0; if (vma->vm_file != file) return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; return 1; } static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return 1; return anon_vma1 == anon_vma2; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. */ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; } return 0; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. */ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return 1; } return 0; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out * whether that can be merged with its predecessor or its successor. * Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when * called for mprotect, it is certain to be already mapped (either at * an offset within prev, or at the start of next), and the flags of * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * * The following mprotect cases have to be considered, where AAAA is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: * * AAAA AAAA AAAA * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN * cannot merge might become might become * PPNNNNNNNNNN PPPPPPPPPPNN * mmap, brk or case 4 below case 5 below * mremap move: * AAAA AAAA * PPPP NNNN PPPPNNNNXXXX * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or * PPPPPPPPNNNN 2 or PPPPPPPPXXXX 7 or * PPPPNNNNNNNN 3 PPPPXXXXXXXX 8 * * It is important for case 8 that the vma NNNN overlapping the * region AAAA is never going to extended over XXXX. Instead XXXX must * be extended in region AAAA and NNNN must be removed. This way in * all cases where vma_merge succeeds, the moment vma_adjust drops the * rmap_locks, the properties of the merged vma will be already * correct for the whole merged range. Some of those properties like * vm_page_prot/vm_flags may be accessed by rmap_walks and they must * be correct for the whole merged range immediately after the * rmap_locks are released. Otherwise if XXXX would be removed and * NNNN would be extended over the XXXX range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; int err; /* * We later require that vma->vm_flags == vm_flags, * so this tests vma->vm_flags & VM_SPECIAL, too. */ if (vm_flags & VM_SPECIAL) return NULL; next = vma_next(mm, prev); area = next; if (area && area->vm_end == end) /* cases 6, 7, 8 */ next = next->vm_next; /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(area && end > area->vm_end); VM_WARN_ON(addr >= end); /* * Can it merge with the predecessor? */ if (prev && prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, vm_userfaultfd_ctx)) { /* * OK, it can. Can we now merge in the successor as well? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ err = __vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, prev); } else /* cases 2, 5, 7 */ err = __vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL, prev); if (err) return NULL; khugepaged_enter_vma_merge(prev, vm_flags); return prev; } /* * Can this new request be merged in front of next? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); else { /* cases 3, 8 */ err = __vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL, next); /* * In case 3 area is already equal to next and * this is a noop, but in case 8 "area" has * been removed and next was expanded over it. */ area = next; } if (err) return NULL; khugepaged_enter_vma_merge(area, vm_flags); return area; } return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mm_sem held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mm_sem. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; /* Try next first. */ if (vma->vm_next) { anon_vma = reusable_anon_vma(vma->vm_next, vma, vma->vm_next); if (anon_vma) return anon_vma; } /* Try prev next. */ if (vma->vm_prev) anon_vma = reusable_anon_vma(vma->vm_prev, vma->vm_prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } static inline int mlock_future_check(struct mm_struct *mm, unsigned long flags, unsigned long len) { unsigned long locked, lock_limit; /* mlock MCL_FUTURE? */ if (flags & VM_LOCKED) { locked = len >> PAGE_SHIFT; locked += mm->locked_vm; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } return 0; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_mode & FMODE_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /* * The caller must write-lock current->mm->mmap_lock. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; vm_flags_t vm_flags; int pkey = 0; *populate = 0; if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we dont add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = get_unmapped_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { struct vm_area_struct *vma = find_vma(mm, addr); if (vma && vma->vm_start < addr + len) return -EEXIST; } if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (mlock_future_check(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; /* * Make sure there are no mandatory locks on the file. */ if (locks_verify_locked(file)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); else if (is_readonly_sealed(seals, vm_flags)) vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!file->f_op->mmap) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct user_struct *user = NULL; struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called * A dummy user value is used because we are not locking * memory so no accounting is necessary */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { vm_flags_t vm_flags = vma->vm_flags; const struct vm_operations_struct *vm_ops = vma->vm_ops; /* If it was private or non-writable, the write bit is already clear */ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) return 0; /* The backer wishes to know when pages are first written to? */ if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite)) return 1; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) && !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ if (vm_flags & VM_PFNMAP) return 0; /* Can the mapping track the dirty pages? */ return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return 0; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev, *merge; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; /* Check against address space limit. */ if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* * MAP_FIXED may remove pages of mappings that intersects with * requested mapping. Account for the pages it would unmap. */ nr_pages = count_vma_pages_range(mm, addr, addr + len); if (!may_expand_vm(mm, vm_flags, (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) return -ENOMEM; /* * Private writable mapping: check memory availability */ if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; } /* * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); if (vma) goto out; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; if (file) { if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; } /* ->mmap() can change vma->vm_file, but must guarantee that * vma_link() below can deny write-access if VM_DENYWRITE is set * and map writably if VM_SHARED is set. This usually means the * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); error = mmap_file(file, vma); if (error) goto unmap_and_free_file_vma; /* Can addr have changed?? * * Answer: Yes, several device drivers can do it in their * f_op->mmap method. -DaveM * Bug: If addr is changed, prev, rb_link, rb_parent should * be updated for vma_link() */ WARN_ON_ONCE(addr != vma->vm_start); /* * Drivers should not permit writability when previously it was * disallowed. */ VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && !(vm_flags & VM_MAYWRITE) && (vma->vm_flags & VM_MAYWRITE)); addr = vma->vm_start; /* If vm_flags changed after mmap_file(), we should try merge vma again * as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); if (merge) { /* ->mmap() can change vma->vm_file and fput the original file. So * fput the vma->vm_file here or we would add an extra fput for file * and cause general protection fault ultimately. */ fput(vma->vm_file); vm_area_free(vma); vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } else { vma_set_anonymous(vma); } #ifdef CONFIG_SPARC64 /* TODO: Fix SPARC ADI! */ WARN_ON_ONCE(!arch_validate_flags(vm_flags)); #endif vma_link(mm, vma, prev, rb_link, rb_parent); if (file) { unmap_writable: if (vm_flags & VM_DENYWRITE) allow_write_access(file); } file = vma->vm_file; out: perf_event_mmap(vma); vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) vma->vm_flags &= VM_LOCKED_CLEAR_MASK; else mm->locked_vm += (len >> PAGE_SHIFT); } if (file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vma->vm_flags |= VM_SOFTDIRTY; vma_set_page_prot(vma); return addr; unmap_and_free_file_vma: vma->vm_file = NULL; fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); return error; } static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { /* * We implement the search by looking for an rbtree node that * immediately follows a suitable gap. That is, * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length; * - gap_end = vma->vm_start >= info->low_limit + length; * - gap_end - gap_start >= length */ struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; /* Adjust search limits by the desired length */ if (info->high_limit < length) return -ENOMEM; high_limit = info->high_limit - length; if (info->low_limit > high_limit) return -ENOMEM; low_limit = info->low_limit + length; /* Check if rbtree root looks promising */ if (RB_EMPTY_ROOT(&mm->mm_rb)) goto check_highest; vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); if (vma->rb_subtree_gap < length) goto check_highest; while (true) { /* Visit left subtree if it looks promising */ gap_end = vm_start_gap(vma); if (gap_end >= low_limit && vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb); if (left->rb_subtree_gap >= length) { vma = left; continue; } } gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) return -ENOMEM; if (gap_end >= low_limit && gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit right subtree if it looks promising */ if (vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb); if (right->rb_subtree_gap >= length) { vma = right; continue; } } /* Go back up the rbtree to find next candidate node */ while (true) { struct rb_node *prev = &vma->vm_rb; if (!rb_parent(prev)) goto check_highest; vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { gap_start = vm_end_gap(vma->vm_prev); gap_end = vm_start_gap(vma); goto check_current; } } } check_highest: /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; gap_end = ULONG_MAX; /* Only for VM_BUG_ON below */ if (gap_start > high_limit) return -ENOMEM; found: /* We found a suitable gap. Clip it with the original low_limit. */ if (gap_start < info->low_limit) gap_start = info->low_limit; /* Adjust gap address to the desired alignment */ gap_start += (info->align_offset - gap_start) & info->align_mask; VM_BUG_ON(gap_start + info->length > info->high_limit); VM_BUG_ON(gap_start + info->length > gap_end); return gap_start; } static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; /* * Adjust search limits by the desired length. * See implementation comment at top of unmapped_area(). */ gap_end = info->high_limit; if (gap_end < length) return -ENOMEM; high_limit = gap_end - length; if (info->low_limit > high_limit) return -ENOMEM; low_limit = info->low_limit + length; /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; if (gap_start <= high_limit) goto found_highest; /* Check if rbtree root looks promising */ if (RB_EMPTY_ROOT(&mm->mm_rb)) return -ENOMEM; vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); if (vma->rb_subtree_gap < length) return -ENOMEM; while (true) { /* Visit right subtree if it looks promising */ gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; if (gap_start <= high_limit && vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb); if (right->rb_subtree_gap >= length) { vma = right; continue; } } check_current: /* Check if current node has a suitable gap */ gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; if (gap_start <= high_limit && gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit left subtree if it looks promising */ if (vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb); if (left->rb_subtree_gap >= length) { vma = left; continue; } } /* Go back up the rbtree to find next candidate node */ while (true) { struct rb_node *prev = &vma->vm_rb; if (!rb_parent(prev)) return -ENOMEM; vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_right) { gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; goto check_current; } } } found: /* We found a suitable gap. Clip it with the original high_limit. */ if (gap_end > info->high_limit) gap_end = info->high_limit; found_highest: /* Compute highest gap address at the desired alignment */ gap_end -= info->length; gap_end -= (gap_end - info->align_offset) & info->align_mask; VM_BUG_ON(gap_end < info->low_limit); VM_BUG_ON(gap_end < gap_start); return gap_end; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; const unsigned long mmap_end = arch_get_mmap_end(addr); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.align_mask = 0; info.align_offset = 0; return vm_unmapped_area(&info); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info; const unsigned long mmap_end = arch_get_mmap_end(addr); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.align_mask = 0; info.align_offset = 0; addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #endif unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; get_area = current->mm->get_unmapped_area; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. * do_mmap() will clear pgoff, so match alignment. */ pgoff = 0; get_area = shmem_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { struct rb_node *rb_node; struct vm_area_struct *vma; /* Check the cache first. */ vma = vmacache_find(mm, addr); if (likely(vma)) return vma; rb_node = mm->mm_rb.rb_node; while (rb_node) { struct vm_area_struct *tmp; tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); if (tmp->vm_end > addr) { vma = tmp; if (tmp->vm_start <= addr) break; rb_node = rb_node->rb_left; } else rb_node = rb_node->rb_right; } if (vma) vmacache_update(addr, vma); return vma; } EXPORT_SYMBOL(find_vma); /* * Same as find_vma, but also return a pointer to the previous VMA in *pprev. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; vma = find_vma(mm, addr); if (vma) { *pprev = vma->vm_prev; } else { struct rb_node *rb_node = rb_last(&mm->mm_rb); *pprev = rb_node ? rb_entry(rb_node, struct vm_area_struct, vm_rb) : NULL; } return vma; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (vma->vm_flags & VM_LOCKED) { unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; limit = rlimit(RLIMIT_MEMLOCK); limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; } /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) /* * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = vma->vm_next; if (next && next->vm_start < gap_addr && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * vma_gap_update() doesn't support concurrent * updates, but we only hold a shared mmap_lock * lock here, so we need to protect against * concurrent vma expansions. * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard * against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; anon_vma_interval_tree_post_update_vma(vma); if (vma->vm_next) vma_gap_update(vma->vm_next); else mm->highest_vm_end = vm_end_gap(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; int error = 0; address &= PAGE_MASK; if (address < mmap_min_addr) return -EPERM; /* Enforce stack_guard_gap */ prev = vma->vm_prev; /* Check that both stack segments have the same anon_vma? */ if (prev && !(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev)) { if (address - prev->vm_end < stack_guard_gap) return -ENOMEM; } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * vma_gap_update() doesn't support concurrent * updates, but we only hold a shared mmap_lock * lock here, so we need to protect against * concurrent vma expansions. * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard * against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; anon_vma_interval_tree_post_update_vma(vma); vma_gap_update(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; static int __init cmdline_parse_stack_guard_gap(char *p) { unsigned long val; char *endptr; val = simple_strtoul(p, &endptr, 10); if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); #ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct * find_extend_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; /* don't alter vm_end if the coredump is running */ if (!prev || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } struct vm_area_struct * find_extend_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm, addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif EXPORT_SYMBOL_GPL(find_extend_vma); /* * Ok - we have the memory areas we should free on the vma list, * so release them, and do the vma updates. * * Called with the mm semaphore held. */ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) { unsigned long nr_accounted = 0; /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); do { long nrpages = vma_pages(vma); if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; vm_stat_account(mm, vma->vm_flags, -nrpages); vma = remove_vma(vma); } while (vma); vm_unacct_memory(nr_accounted); validate_mm(mm); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end) { struct vm_area_struct *next = vma_next(mm, prev); struct mmu_gather tlb; struct vm_area_struct *cur_vma; lru_add_drain(); tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); /* * Ensure we have no stale TLB entries by the time this mapping is * removed from the rmap. * Note that we don't have to worry about nested flushes here because * we're holding the mm semaphore for removing the mapping - so any * concurrent flush in this region has to be coming through the rmap, * and we synchronize against that using the rmap lock. */ for (cur_vma = vma; cur_vma; cur_vma = cur_vma->vm_next) { if ((cur_vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) { tlb_flush_mmu(&tlb); break; } } free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); } /* * Create a list of vma's touched by the unmap, removing them from the mm's * vma list as we go.. */ static bool detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long end) { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; do { vma_rb_erase(vma, &mm->mm_rb); mm->map_count--; tail_vma = vma; vma = vma->vm_next; } while (vma && vma->vm_start < end); *insertion_point = vma; if (vma) { vma->vm_prev = prev; vma_gap_update(vma); } else mm->highest_vm_end = prev ? vm_end_gap(prev) : 0; tail_vma->vm_next = NULL; /* Kill the cache */ vmacache_invalidate(mm); /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or * VM_GROWSUP VMA. Such VMAs can change their size under * down_read(mmap_lock) and collide with the VMA we are about to unmap. */ if (vma && (vma->vm_flags & VM_GROWSDOWN)) return false; if (prev && (prev->vm_flags & VM_GROWSUP)) return false; return true; } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. */ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vm_area_struct *new; int err; if (vma->vm_ops && vma->vm_ops->split) { err = vma->vm_ops->split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) new->vm_end = addr; else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = vma_dup_policy(vma, new); if (err) goto out_free_vma; err = anon_vma_clone(new, vma); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); if (new_below) err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); /* Success. */ if (!err) return 0; /* Clean everything up if vma_adjust failed. */ vma_close(new); if (new->vm_file) fput(new->vm_file); unlink_anon_vmas(new); out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: vm_area_free(new); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(mm, vma, addr, new_below); } /* Munmap is split into 2 main parts -- this part which finds * what needs doing, and the areas themselves, which do the * work. This now handles partial unmappings. * Jeremy Fitzhardinge <jeremy@goop.org> */ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma, *prev, *last; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (len == 0) return -EINVAL; /* * arch_unmap() might do unmaps itself. It must be called * and finish any rbtree manipulation before this code * runs and also starts to manipulate the rbtree. */ arch_unmap(mm, start, end); /* Find the first overlapping VMA */ vma = find_vma(mm, start); if (!vma) return 0; prev = vma->vm_prev; /* we have start < vma->vm_end */ /* if it doesn't overlap, we have nothing.. */ if (vma->vm_start >= end) return 0; /* * If we need to split any vma, do it now to save pain later. * * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially * unmapped vm_area_struct will remain in use: so lower split_vma * places tmp vma above, and higher split_vma places tmp vma below. */ if (start > vma->vm_start) { int error; /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) return -ENOMEM; error = __split_vma(mm, vma, start, 0); if (error) return error; prev = vma; } /* Does it split the last one? */ last = find_vma(mm, end); if (last && end > last->vm_start) { int error = __split_vma(mm, last, end, 1); if (error) return error; } vma = vma_next(mm, prev); if (unlikely(uf)) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain splitted, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ int error = userfaultfd_unmap_prep(vma, start, end, uf); if (error) return error; } /* * unlock any mlock()ed ranges before detaching vmas */ if (mm->locked_vm) { struct vm_area_struct *tmp = vma; while (tmp && tmp->vm_start < end) { if (tmp->vm_flags & VM_LOCKED) { mm->locked_vm -= vma_pages(tmp); munlock_vma_pages_all(tmp); } tmp = tmp->vm_next; } } /* Detach vmas from rbtree */ if (!detach_vmas_to_be_unmapped(mm, vma, prev, end)) downgrade = false; if (downgrade) mmap_write_downgrade(mm); unmap_region(mm, vma, prev, start, end); /* Fix up all other VM information */ remove_vma_list(mm, vma); return downgrade ? 1 : 0; } int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { return __do_munmap(mm, start, len, uf, false); } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { unsigned long ret; bool writable_file_mapping = false; /* Allow architectures to sanity-check the vm_flags. */ if (!arch_validate_flags(vm_flags)) return -EINVAL; /* Map writable and ensure this isn't a sealed memfd. */ if (file && is_shared_maywrite(vm_flags)) { int error = mapping_map_writable(file->f_mapping); if (error) return error; writable_file_mapping = true; } ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); /* Clear our write mapping regardless of error. */ if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); validate_mm(current->mm); return ret; } static int __vm_munmap(unsigned long start, size_t len, bool downgrade) { int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); if (mmap_write_lock_killable(mm)) return -EINTR; ret = __do_munmap(mm, start, len, &uf, downgrade); /* * Returning 1 indicates mmap_lock is downgraded. * But 1 is not legal return value of vm_munmap() and munmap(), reset * it to 0 before return. */ if (ret == 1) { mmap_read_unlock(mm); ret = 0; } else mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); return ret; } int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); profile_munmap(addr); return __vm_munmap(addr, len, true); } /* * Emulation of deprecated remap_file_pages() syscall. */ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_write_lock_killable(mm)) return -EINTR; vma = find_vma(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; if (start < vma->vm_start) goto out; if (start + size > vma->vm_end) { struct vm_area_struct *next; for (next = vma->vm_next; next; next = next->vm_next) { /* hole between vmas ? */ if (next->vm_start != next->vm_prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; } if (!next) goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { struct vm_area_struct *tmp; flags |= MAP_LOCKED; /* drop PG_Mlocked flag for over-mapped range */ for (tmp = vma; tmp->vm_start >= start + size; tmp = tmp->vm_next) { /* * Split pmd and munlock page on the border * of the range. */ vma_adjust_trans_huge(tmp, start, start + size, 0); munlock_vma_pages_range(tmp, max(tmp->vm_start, start), min(tmp->vm_end, start + size)); } } file = get_file(vma->vm_file); ret = do_mmap(vma->vm_file, start, size, prot, flags, pgoff, &populate, NULL); fput(file); out: mmap_write_unlock(mm); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } /* * this is really a simplified "do_mmap". it only handles * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; unsigned long mapped_addr; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; error = mlock_future_check(mm, mm->def_flags, len); if (error) return error; /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) return -ENOMEM; /* Check against address space limits *after* clearing old maps... */ if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); if (vma) goto out; /* * create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; vma->vm_flags = flags; vma->vm_page_prot = vm_get_page_prot(flags); vma_link(mm, vma, prev, rb_link, rb_parent); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vma->vm_flags |= VM_SOFTDIRTY; return 0; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; unsigned long len; int ret; bool populate; LIST_HEAD(uf); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_brk_flags(addr, len, flags, &uf); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; } EXPORT_SYMBOL(vm_brk_flags); int vm_brk(unsigned long addr, unsigned long len) { return vm_brk_flags(addr, len, 0); } EXPORT_SYMBOL(vm_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); if (unlikely(mm_is_oom_victim(mm))) { /* * Manually reap the mm to free as much memory as possible. * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard * this mm from further consideration. Taking mm->mmap_lock for * write after setting MMF_OOM_SKIP will guarantee that the oom * reaper will not run on this mm again after mmap_lock is * dropped. * * Nothing can be holding mm->mmap_lock here and the above call * to mmu_notifier_release(mm) ensures mmu notifier callbacks in * __oom_reap_task_mm() will not block. * * This needs to be done before calling munlock_vma_pages_all(), * which clears VM_LOCKED, otherwise the oom reaper cannot * reliably test it. */ (void)__oom_reap_task_mm(mm); set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mmap_write_unlock(mm); } if (mm->locked_vm) { vma = mm->mmap; while (vma) { if (vma->vm_flags & VM_LOCKED) munlock_vma_pages_all(vma); vma = vma->vm_next; } } arch_exit_mmap(mm); vma = mm->mmap; if (!vma) /* Can happen if dup_mmap() received an OOM */ return; lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu(&tlb, mm, 0, -1); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); /* * Walk the list again, actually closing and freeing it, * with preemption enabled, without holding any MM locks. */ while (vma) { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma = remove_vma(vma); cond_resched(); } vm_unacct_memory(nr_accounted); } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev; struct rb_node **rb_link, *rb_parent; if (find_vma_links(mm, vma->vm_start, vma->vm_end, &prev, &rb_link, &rb_parent)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, vma_pages(vma))) return -ENOMEM; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap and in do_brk_flags. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } vma_link(mm, vma, prev, rb_link, rb_parent); return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; bool faulted_in_anon_vma = true; /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); *need_rmap_locks = false; } return new_vma; out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { mm->total_vm += npages; if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, }; static const struct vm_operations_struct legacy_special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; if (vma->vm_ops == &legacy_special_mapping_vmops) { pages = vma->vm_private_data; } else { struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; } for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); return vma; out: vm_area_free(vma); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && (vma->vm_ops == &special_mapping_vmops || vma->vm_ops == &legacy_special_mapping_vmops); } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { struct vm_area_struct *vma = __install_special_mapping( mm, addr, len, vm_flags, (void *)pages, &legacy_special_mapping_vmops); return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; BUG_ON(mmap_read_trylock(mm)); mutex_lock(&mm_all_locks_mutex); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; BUG_ON(mmap_read_trylock(mm)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * initialise the percpu counter for VM */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (0 < tmp && tmp < (1UL << 17)) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (0 < tmp && tmp < (1UL << 13)) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static struct notifier_block reserve_mem_nb = { .notifier_call = reserve_mem_notifier, }; static int __meminit init_reserve_notifier(void) { if (register_hotmemory_notifier(&reserve_mem_nb)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Facebook * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/sched.h> #include <linux/random.h> #include <linux/sbitmap.h> #include <linux/seq_file.h> /* * See if we have deferred clears that we can batch move */ static inline bool sbitmap_deferred_clear(struct sbitmap *sb, int index) { unsigned long mask, val; bool ret = false; unsigned long flags; spin_lock_irqsave(&sb->map[index].swap_lock, flags); if (!sb->map[index].cleared) goto out_unlock; /* * First get a stable cleared mask, setting the old mask to 0. */ mask = xchg(&sb->map[index].cleared, 0); /* * Now clear the masked bits in our free word */ do { val = sb->map[index].word; } while (cmpxchg(&sb->map[index].word, val, val & ~mask) != val); ret = true; out_unlock: spin_unlock_irqrestore(&sb->map[index].swap_lock, flags); return ret; } int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node) { unsigned int bits_per_word; unsigned int i; if (shift < 0) { shift = ilog2(BITS_PER_LONG); /* * If the bitmap is small, shrink the number of bits per word so * we spread over a few cachelines, at least. If less than 4 * bits, just forget about it, it's not going to work optimally * anyway. */ if (depth >= 4) { while ((4U << shift) > depth) shift--; } } bits_per_word = 1U << shift; if (bits_per_word > BITS_PER_LONG) return -EINVAL; sb->shift = shift; sb->depth = depth; sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word); if (depth == 0) { sb->map = NULL; return 0; } sb->map = kcalloc_node(sb->map_nr, sizeof(*sb->map), flags, node); if (!sb->map) return -ENOMEM; for (i = 0; i < sb->map_nr; i++) { sb->map[i].depth = min(depth, bits_per_word); depth -= sb->map[i].depth; spin_lock_init(&sb->map[i].swap_lock); } return 0; } EXPORT_SYMBOL_GPL(sbitmap_init_node); void sbitmap_resize(struct sbitmap *sb, unsigned int depth) { unsigned int bits_per_word = 1U << sb->shift; unsigned int i; for (i = 0; i < sb->map_nr; i++) sbitmap_deferred_clear(sb, i); sb->depth = depth; sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word); for (i = 0; i < sb->map_nr; i++) { sb->map[i].depth = min(depth, bits_per_word); depth -= sb->map[i].depth; } } EXPORT_SYMBOL_GPL(sbitmap_resize); static int __sbitmap_get_word(unsigned long *word, unsigned long depth, unsigned int hint, bool wrap) { unsigned int orig_hint = hint; int nr; while (1) { nr = find_next_zero_bit(word, depth, hint); if (unlikely(nr >= depth)) { /* * We started with an offset, and we didn't reset the * offset to 0 in a failure case, so start from 0 to * exhaust the map. */ if (orig_hint && hint && wrap) { hint = orig_hint = 0; continue; } return -1; } if (!test_and_set_bit_lock(nr, word)) break; hint = nr + 1; if (hint >= depth - 1) hint = 0; } return nr; } static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, unsigned int alloc_hint, bool round_robin) { int nr; do { nr = __sbitmap_get_word(&sb->map[index].word, sb->map[index].depth, alloc_hint, !round_robin); if (nr != -1) break; if (!sbitmap_deferred_clear(sb, index)) break; } while (1); return nr; } int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin) { unsigned int i, index; int nr = -1; index = SB_NR_TO_INDEX(sb, alloc_hint); /* * Unless we're doing round robin tag allocation, just use the * alloc_hint to find the right word index. No point in looping * twice in find_next_zero_bit() for that case. */ if (round_robin) alloc_hint = SB_NR_TO_BIT(sb, alloc_hint); else alloc_hint = 0; for (i = 0; i < sb->map_nr; i++) { nr = sbitmap_find_bit_in_index(sb, index, alloc_hint, round_robin); if (nr != -1) { nr += index << sb->shift; break; } /* Jump to next index. */ alloc_hint = 0; if (++index >= sb->map_nr) index = 0; } return nr; } EXPORT_SYMBOL_GPL(sbitmap_get); int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, unsigned long shallow_depth) { unsigned int i, index; int nr = -1; index = SB_NR_TO_INDEX(sb, alloc_hint); for (i = 0; i < sb->map_nr; i++) { again: nr = __sbitmap_get_word(&sb->map[index].word, min(sb->map[index].depth, shallow_depth), SB_NR_TO_BIT(sb, alloc_hint), true); if (nr != -1) { nr += index << sb->shift; break; } if (sbitmap_deferred_clear(sb, index)) goto again; /* Jump to next index. */ index++; alloc_hint = index << sb->shift; if (index >= sb->map_nr) { index = 0; alloc_hint = 0; } } return nr; } EXPORT_SYMBOL_GPL(sbitmap_get_shallow); bool sbitmap_any_bit_set(const struct sbitmap *sb) { unsigned int i; for (i = 0; i < sb->map_nr; i++) { if (sb->map[i].word & ~sb->map[i].cleared) return true; } return false; } EXPORT_SYMBOL_GPL(sbitmap_any_bit_set); static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set) { unsigned int i, weight = 0; for (i = 0; i < sb->map_nr; i++) { const struct sbitmap_word *word = &sb->map[i]; if (set) weight += bitmap_weight(&word->word, word->depth); else weight += bitmap_weight(&word->cleared, word->depth); } return weight; } static unsigned int sbitmap_weight(const struct sbitmap *sb) { return __sbitmap_weight(sb, true); } static unsigned int sbitmap_cleared(const struct sbitmap *sb) { return __sbitmap_weight(sb, false); } void sbitmap_show(struct sbitmap *sb, struct seq_file *m) { seq_printf(m, "depth=%u\n", sb->depth); seq_printf(m, "busy=%u\n", sbitmap_weight(sb) - sbitmap_cleared(sb)); seq_printf(m, "cleared=%u\n", sbitmap_cleared(sb)); seq_printf(m, "bits_per_word=%u\n", 1U << sb->shift); seq_printf(m, "map_nr=%u\n", sb->map_nr); } EXPORT_SYMBOL_GPL(sbitmap_show); static inline void emit_byte(struct seq_file *m, unsigned int offset, u8 byte) { if ((offset & 0xf) == 0) { if (offset != 0) seq_putc(m, '\n'); seq_printf(m, "%08x:", offset); } if ((offset & 0x1) == 0) seq_putc(m, ' '); seq_printf(m, "%02x", byte); } void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m) { u8 byte = 0; unsigned int byte_bits = 0; unsigned int offset = 0; int i; for (i = 0; i < sb->map_nr; i++) { unsigned long word = READ_ONCE(sb->map[i].word); unsigned long cleared = READ_ONCE(sb->map[i].cleared); unsigned int word_bits = READ_ONCE(sb->map[i].depth); word &= ~cleared; while (word_bits > 0) { unsigned int bits = min(8 - byte_bits, word_bits); byte |= (word & (BIT(bits) - 1)) << byte_bits; byte_bits += bits; if (byte_bits == 8) { emit_byte(m, offset, byte); byte = 0; byte_bits = 0; offset++; } word >>= bits; word_bits -= bits; } } if (byte_bits) { emit_byte(m, offset, byte); offset++; } if (offset) seq_putc(m, '\n'); } EXPORT_SYMBOL_GPL(sbitmap_bitmap_show); static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq, unsigned int depth) { unsigned int wake_batch; unsigned int shallow_depth; /* * For each batch, we wake up one queue. We need to make sure that our * batch size is small enough that the full depth of the bitmap, * potentially limited by a shallow depth, is enough to wake up all of * the queues. * * Each full word of the bitmap has bits_per_word bits, and there might * be a partial word. There are depth / bits_per_word full words and * depth % bits_per_word bits left over. In bitwise arithmetic: * * bits_per_word = 1 << shift * depth / bits_per_word = depth >> shift * depth % bits_per_word = depth & ((1 << shift) - 1) * * Each word can be limited to sbq->min_shallow_depth bits. */ shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth); depth = ((depth >> sbq->sb.shift) * shallow_depth + min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth)); wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1, SBQ_WAKE_BATCH); return wake_batch; } int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, int shift, bool round_robin, gfp_t flags, int node) { int ret; int i; ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node); if (ret) return ret; sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); if (!sbq->alloc_hint) { sbitmap_free(&sbq->sb); return -ENOMEM; } if (depth && !round_robin) { for_each_possible_cpu(i) *per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth; } sbq->min_shallow_depth = UINT_MAX; sbq->wake_batch = sbq_calc_wake_batch(sbq, depth); atomic_set(&sbq->wake_index, 0); atomic_set(&sbq->ws_active, 0); sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node); if (!sbq->ws) { free_percpu(sbq->alloc_hint); sbitmap_free(&sbq->sb); return -ENOMEM; } for (i = 0; i < SBQ_WAIT_QUEUES; i++) { init_waitqueue_head(&sbq->ws[i].wait); atomic_set(&sbq->ws[i].wait_cnt, sbq->wake_batch); } sbq->round_robin = round_robin; return 0; } EXPORT_SYMBOL_GPL(sbitmap_queue_init_node); static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq, unsigned int depth) { unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth); int i; if (sbq->wake_batch != wake_batch) { WRITE_ONCE(sbq->wake_batch, wake_batch); /* * Pairs with the memory barrier in sbitmap_queue_wake_up() * to ensure that the batch size is updated before the wait * counts. */ smp_mb(); for (i = 0; i < SBQ_WAIT_QUEUES; i++) atomic_set(&sbq->ws[i].wait_cnt, 1); } } void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth) { sbitmap_queue_update_wake_batch(sbq, depth); sbitmap_resize(&sbq->sb, depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_resize); int __sbitmap_queue_get(struct sbitmap_queue *sbq) { unsigned int hint, depth; int nr; hint = this_cpu_read(*sbq->alloc_hint); depth = READ_ONCE(sbq->sb.depth); if (unlikely(hint >= depth)) { hint = depth ? prandom_u32() % depth : 0; this_cpu_write(*sbq->alloc_hint, hint); } nr = sbitmap_get(&sbq->sb, hint, sbq->round_robin); if (nr == -1) { /* If the map is full, a hint won't do us much good. */ this_cpu_write(*sbq->alloc_hint, 0); } else if (nr == hint || unlikely(sbq->round_robin)) { /* Only update the hint if we used it. */ hint = nr + 1; if (hint >= depth - 1) hint = 0; this_cpu_write(*sbq->alloc_hint, hint); } return nr; } EXPORT_SYMBOL_GPL(__sbitmap_queue_get); int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int shallow_depth) { unsigned int hint, depth; int nr; WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth); hint = this_cpu_read(*sbq->alloc_hint); depth = READ_ONCE(sbq->sb.depth); if (unlikely(hint >= depth)) { hint = depth ? prandom_u32() % depth : 0; this_cpu_write(*sbq->alloc_hint, hint); } nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth); if (nr == -1) { /* If the map is full, a hint won't do us much good. */ this_cpu_write(*sbq->alloc_hint, 0); } else if (nr == hint || unlikely(sbq->round_robin)) { /* Only update the hint if we used it. */ hint = nr + 1; if (hint >= depth - 1) hint = 0; this_cpu_write(*sbq->alloc_hint, hint); } return nr; } EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow); void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq, unsigned int min_shallow_depth) { sbq->min_shallow_depth = min_shallow_depth; sbitmap_queue_update_wake_batch(sbq, sbq->sb.depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth); static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) { int i, wake_index; if (!atomic_read(&sbq->ws_active)) return NULL; wake_index = atomic_read(&sbq->wake_index); for (i = 0; i < SBQ_WAIT_QUEUES; i++) { struct sbq_wait_state *ws = &sbq->ws[wake_index]; if (waitqueue_active(&ws->wait)) { if (wake_index != atomic_read(&sbq->wake_index)) atomic_set(&sbq->wake_index, wake_index); return ws; } wake_index = sbq_index_inc(wake_index); } return NULL; } static bool __sbq_wake_up(struct sbitmap_queue *sbq) { struct sbq_wait_state *ws; unsigned int wake_batch; int wait_cnt; ws = sbq_wake_ptr(sbq); if (!ws) return false; wait_cnt = atomic_dec_return(&ws->wait_cnt); if (wait_cnt <= 0) { int ret; wake_batch = READ_ONCE(sbq->wake_batch); /* * Pairs with the memory barrier in sbitmap_queue_resize() to * ensure that we see the batch size update before the wait * count is reset. */ smp_mb__before_atomic(); /* * For concurrent callers of this, the one that failed the * atomic_cmpxhcg() race should call this function again * to wakeup a new batch on a different 'ws'. */ ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch); if (ret == wait_cnt) { sbq_index_atomic_inc(&sbq->wake_index); wake_up_nr(&ws->wait, wake_batch); return false; } return true; } return false; } void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) { while (__sbq_wake_up(sbq)) ; } EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu) { /* * Once the clear bit is set, the bit may be allocated out. * * Orders READ/WRITE on the asssociated instance(such as request * of blk_mq) by this bit for avoiding race with re-allocation, * and its pair is the memory barrier implied in __sbitmap_get_word. * * One invariant is that the clear bit has to be zero when the bit * is in use. */ smp_mb__before_atomic(); sbitmap_deferred_clear_bit(&sbq->sb, nr); /* * Pairs with the memory barrier in set_current_state() to ensure the * proper ordering of clear_bit_unlock()/waitqueue_active() in the waker * and test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the * waiter. See the comment on waitqueue_active(). */ smp_mb__after_atomic(); sbitmap_queue_wake_up(sbq); if (likely(!sbq->round_robin && nr < sbq->sb.depth)) *per_cpu_ptr(sbq->alloc_hint, cpu) = nr; } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); void sbitmap_queue_wake_all(struct sbitmap_queue *sbq) { int i, wake_index; /* * Pairs with the memory barrier in set_current_state() like in * sbitmap_queue_wake_up(). */ smp_mb(); wake_index = atomic_read(&sbq->wake_index); for (i = 0; i < SBQ_WAIT_QUEUES; i++) { struct sbq_wait_state *ws = &sbq->ws[wake_index]; if (waitqueue_active(&ws->wait)) wake_up(&ws->wait); wake_index = sbq_index_inc(wake_index); } } EXPORT_SYMBOL_GPL(sbitmap_queue_wake_all); void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) { bool first; int i; sbitmap_show(&sbq->sb, m); seq_puts(m, "alloc_hint={"); first = true; for_each_possible_cpu(i) { if (!first) seq_puts(m, ", "); first = false; seq_printf(m, "%u", *per_cpu_ptr(sbq->alloc_hint, i)); } seq_puts(m, "}\n"); seq_printf(m, "wake_batch=%u\n", sbq->wake_batch); seq_printf(m, "wake_index=%d\n", atomic_read(&sbq->wake_index)); seq_printf(m, "ws_active=%d\n", atomic_read(&sbq->ws_active)); seq_puts(m, "ws={\n"); for (i = 0; i < SBQ_WAIT_QUEUES; i++) { struct sbq_wait_state *ws = &sbq->ws[i]; seq_printf(m, "\t{.wait_cnt=%d, .wait=%s},\n", atomic_read(&ws->wait_cnt), waitqueue_active(&ws->wait) ? "active" : "inactive"); } seq_puts(m, "}\n"); seq_printf(m, "round_robin=%d\n", sbq->round_robin); seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_show); void sbitmap_add_wait_queue(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait) { if (!sbq_wait->sbq) { sbq_wait->sbq = sbq; atomic_inc(&sbq->ws_active); add_wait_queue(&ws->wait, &sbq_wait->wait); } } EXPORT_SYMBOL_GPL(sbitmap_add_wait_queue); void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait) { list_del_init(&sbq_wait->wait.entry); if (sbq_wait->sbq) { atomic_dec(&sbq_wait->sbq->ws_active); sbq_wait->sbq = NULL; } } EXPORT_SYMBOL_GPL(sbitmap_del_wait_queue); void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait, int state) { if (!sbq_wait->sbq) { atomic_inc(&sbq->ws_active); sbq_wait->sbq = sbq; } prepare_to_wait_exclusive(&ws->wait, &sbq_wait->wait, state); } EXPORT_SYMBOL_GPL(sbitmap_prepare_to_wait); void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait) { finish_wait(&ws->wait, &sbq_wait->wait); if (sbq_wait->sbq) { atomic_dec(&sbq->ws_active); sbq_wait->sbq = NULL; } } EXPORT_SYMBOL_GPL(sbitmap_finish_wait); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) static inline void * __must_check ERR_PTR(long error) { return (void *) error; } static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. * Dave Platt : Interrupt stacking fix. * Richard Kooijman : Timestamp fixes. * Alan Cox : Changed buffer format. * Alan Cox : destructor hook for AF_UNIX etc. * Linus Torvalds : Better skb_clone. * Alan Cox : Added skb_copy. * Alan Cox : Added all the changed routines Linus * only put in the headers * Ray VanTassle : Fixed --skb->lock in free * Alan Cox : skb_copy copy arp field * Andi Kleen : slabified it. * Robert Olsson : Removed skb_head_pool * * NOTE: * The __skb_ routines should be called with interrupts * disabled, or you better be *real* sure that the operation is atomic * with respect to whatever list is being frobbed (e.g. via lock_sock() * or via disabling bottom half handlers, etc). */ /* * The functions in this file will not compile correctly with gcc 2.4.x */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> #include <linux/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> #include <linux/indirect_call_wrapper.h> #include "datagram.h" #include "sock_destructor.h" struct kmem_cache *skbuff_head_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support * @skb: buffer * @sz: size * @addr: address * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). * Keep out of line to prevent kernel bloat. * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, const char msg[]) { pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n", msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : "<NULL>"); BUG(); } static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells * the caller if emergency pfmemalloc reserves are being used. If it is and * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ #define kmalloc_reserve(size, gfp, node, pfmemalloc) \ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, bool *pfmemalloc) { void *obj; bool ret_pfmemalloc = false; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; obj = kmalloc_node_track_caller(size, flags, node); out: if (pfmemalloc) *pfmemalloc = ret_pfmemalloc; return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. * */ /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache * instead of head cache and allocate a cloned (child) skb. * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of at least size bytes. The object has a reference count * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; bool pfmemalloc; cache = (flags & SKB_ALLOC_FCLONE) ? skbuff_fclone_cache : skbuff_head_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); if (!skb) goto out; prefetchw(skb); /* We do our best to align skb_shared_info on a separate cache * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ size = SKB_WITH_OVERHEAD(ksize(data)); prefetchw(data + size); /* * Only clear those fields we need to clear, not those that we will * actually initialise below. Hence, don't put any more fields after * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); skb->pfmemalloc = pfmemalloc; refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); skb->fclone = SKB_FCLONE_ORIG; refcount_set(&fclones->fclone_ref, 1); fclones->skb2.fclone = SKB_FCLONE_CLONE; } skb_set_kcov_handle(skb, kcov_common_handle()); out: return skb; nodata: kmem_cache_free(cache, skb); skb = NULL; goto out; } EXPORT_SYMBOL(__alloc_skb); /* Caller must provide SKB that is memset cleared */ static struct sk_buff *__build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; unsigned int size = frag_size ? : ksize(data); size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /* Assumes caller memset cleared SKB */ skb->truesize = SKB_TRUESIZE(size); refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); skb_set_kcov_handle(skb, kcov_common_handle()); return skb; } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if * @frag_size is 0, otherwise data should come from the page allocator * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : * Before IO, driver allocates only data buffer where NIC put incoming frame * Driver should add room at head (NET_SKB_PAD) and * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) * After IO, driver calls build_skb(), to allocate sk_buff and populate it * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __build_skb_around(skb, data, frag_size); } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc * This means that if @frag_size is not zero, then @data must be backed * by a page fragment, not kmalloc() or vmalloc() */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __build_skb(data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb; } EXPORT_SYMBOL(build_skb); /** * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller * @frag_size: size of data, or 0 if head was kmalloced */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { if (unlikely(!skb)) return NULL; skb = __build_skb_around(skb, data, frag_size); if (skb && frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb; } EXPORT_SYMBOL(build_skb_around); #define NAPI_SKB_CACHE_SIZE 64 struct napi_alloc_cache { struct page_frag_cache page; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); return page_frag_alloc(&nc->page, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) { fragsz = SKB_DATA_ALIGN(fragsz); return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ void *netdev_alloc_frag(unsigned int fragsz) { struct page_frag_cache *nc; void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_irq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, fragsz, GFP_ATOMIC); } else { local_bh_disable(); data = __napi_alloc_frag(fragsz, GFP_ATOMIC); local_bh_enable(); } return data; } EXPORT_SYMBOL(netdev_alloc_frag); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has NET_SKB_PAD headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, gfp_t gfp_mask) { struct page_frag_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; len += NET_SKB_PAD; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_irq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; } else { local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; local_bh_enable(); } if (unlikely(!data)) return NULL; skb = __build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); /** * __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used * only for NAPI Rx allocation. By doing this we can save several * CPU cycles by avoiding having to disable and re-enable IRQs. * * %NULL is returned if there is no free memory. */ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask) { struct napi_alloc_cache *nc; struct sk_buff *skb; void *data; len += NET_SKB_PAD + NET_IP_ALIGN; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } nc = this_cpu_ptr(&napi_alloc_cache); len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; data = page_frag_alloc(&nc->page, len, gfp_mask); if (unlikely(!data)) return NULL; skb = __build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); skb->dev = napi->dev; skb_fail: return skb; } EXPORT_SYMBOL(__napi_alloc_skb); void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_fill_page_desc(skb, i, page, off, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_add_rx_frag); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; skb_frag_size_add(frag, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_coalesce_rx_frag); static void skb_drop_list(struct sk_buff **listp) { kfree_skb_list(*listp); *listp = NULL; } static inline void skb_drop_fraglist(struct sk_buff *skb) { skb_drop_list(&skb_shinfo(skb)->frag_list); } static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; skb_walk_frags(skb, list) skb_get(list); } static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; if (skb->head_frag) skb_free_frag(head); else kfree(head); } static void skb_release_data(struct sk_buff *skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; if (skb->cloned && atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, &shinfo->dataref)) return; for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i]); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); skb_zcopy_clear(skb, true); skb_free_head(skb); } /* * Free an skbuff by memory without cleaning the state. */ static void kfree_skbmem(struct sk_buff *skb) { struct sk_buff_fclones *fclones; switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: kmem_cache_free(skbuff_head_cache, skb); return; case SKB_FCLONE_ORIG: fclones = container_of(skb, struct sk_buff_fclones, skb1); /* We usually free the clone (TX completion) before original skb * This test would have no chance to be true for the clone, * while here, branch prediction will be good. */ if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break; default: /* SKB_FCLONE_CLONE */ fclones = container_of(skb, struct sk_buff_fclones, skb2); break; } if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: kmem_cache_free(skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { WARN_ON(in_irq()); skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb_nfct(skb)); #endif skb_ext_put(skb); } /* Free everything but the sk_buff shell. */ static void skb_release_all(struct sk_buff *skb) { skb_release_head_state(skb); if (likely(skb->head)) skb_release_data(skb); } /** * __kfree_skb - private function * @skb: buffer * * Free an sk_buff. Release anything attached to the buffer. * Clean the state. This is an internal helper function. Users should * always call kfree_skb */ void __kfree_skb(struct sk_buff *skb) { skb_release_all(skb); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); /** * kfree_skb - free an sk_buff * @skb: buffer to free * * Drop a reference to the buffer and free it if the usage count has * hit zero. */ void kfree_skb(struct sk_buff *skb) { if (!skb_unref(skb)) return; trace_kfree_skb(skb, __builtin_return_address(0)); __kfree_skb(skb); } EXPORT_SYMBOL(kfree_skb); void kfree_skb_list(struct sk_buff *segs) { while (segs) { struct sk_buff *next = segs->next; kfree_skb(segs); segs = next; } } EXPORT_SYMBOL(kfree_skb_list); /* Dump skb information and contents. * * Must only be called from net_ratelimit()-ed paths. * * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; struct sk_buff *list_skb; bool has_mac, has_trans; int headroom, tailroom; int i, len, seg_len; if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); headroom = skb_headroom(skb); tailroom = skb_tailroom(skb); has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n" "mac=(%d,%d) net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n", level, skb->len, headroom, skb_headlen(skb), tailroom, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->network_header, has_trans ? skb_network_header_len(skb) : -1, has_trans ? skb->transport_header : -1, sh->tx_flags, sh->nr_frags, sh->gso_size, sh->gso_type, sh->gso_segs, skb->csum, skb->ip_summed, skb->csum_complete_sw, skb->csum_valid, skb->csum_level, skb->hash, skb->sw_hash, skb->l4_hash, ntohs(skb->protocol), skb->pkt_type, skb->skb_iif); if (dev) printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", level, sk->sk_family, sk->sk_type, sk->sk_protocol); if (full_pkt && headroom) print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb->head, headroom, false); seg_len = min_t(int, skb_headlen(skb), len); if (seg_len) print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, seg_len, false); len -= seg_len; if (full_pkt && tailroom) print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb_tail_pointer(skb), tailroom, false); for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); vaddr = kmap_atomic(p); print_hex_dump(level, "skb frag: ", DUMP_PREFIX_OFFSET, 16, 1, vaddr + p_off, seg_len, false); kunmap_atomic(vaddr); len -= seg_len; if (!len) break; } } if (full_pkt && skb_has_frag_list(skb)) { printk("skb fraglist:\n"); skb_walk_frags(skb, list_skb) skb_dump(level, list_skb, true); } } EXPORT_SYMBOL(skb_dump); /** * skb_tx_error - report an sk_buff xmit error * @skb: buffer that triggered an error * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. */ void skb_tx_error(struct sk_buff *skb) { skb_zcopy_clear(skb, true); } EXPORT_SYMBOL(skb_tx_error); #ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free * * Drop a ref to the buffer and free it if the usage count has hit zero * Functions identically to kfree_skb, but kfree_skb assumes that the frame * is being dropped after a failure and notes that */ void consume_skb(struct sk_buff *skb) { if (!skb_unref(skb)) return; trace_consume_skb(skb); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); #endif /** * consume_stateless_skb - free an skbuff, assuming it is stateless * @skb: buffer to free * * Alike consume_skb(), but this variant assumes that this is the last * skb reference and all the head states have been already dropped */ void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb); skb_release_data(skb); kfree_skbmem(skb); } void __kfree_skb_flush(void) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); /* flush skb_cache if containing objects */ if (nc->skb_count) { kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, nc->skb_cache); nc->skb_count = 0; } } static inline void _kfree_skb_defer(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); /* drop skb->head and call any destructors for packet */ skb_release_all(skb); /* record skb to CPU local list */ nc->skb_cache[nc->skb_count++] = skb; #ifdef CONFIG_SLUB /* SLUB writes into objects when freeing */ prefetchw(skb); #endif /* flush skb_cache if it is filled */ if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE, nc->skb_cache); nc->skb_count = 0; } } void __kfree_skb_defer(struct sk_buff *skb) { _kfree_skb_defer(skb); } void napi_consume_skb(struct sk_buff *skb, int budget) { /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) { dev_consume_skb_any(skb); return; } if (!skb_unref(skb)) return; /* if reaching here SKB is ready to free */ trace_consume_skb(skb); /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } _kfree_skb_defer(skb); } EXPORT_SYMBOL(napi_consume_skb); /* Make sure a field is enclosed inside headers_start/headers_end section */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) < \ offsetof(struct sk_buff, headers_start)); \ BUILD_BUG_ON(offsetof(struct sk_buff, field) > \ offsetof(struct sk_buff, headers_end)); \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; /* We do not copy old->sk */ new->dev = old->dev; memcpy(new->cb, old->cb, sizeof(old->cb)); skb_dst_copy(new, old); __skb_ext_copy(new, old); __nf_copy(new, old, false); /* Note : this field could be in headers_start/headers_end section * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; memcpy(&new->headers_start, &old->headers_start, offsetof(struct sk_buff, headers_end) - offsetof(struct sk_buff, headers_start)); CHECK_SKB_FIELD(protocol); CHECK_SKB_FIELD(csum); CHECK_SKB_FIELD(hash); CHECK_SKB_FIELD(priority); CHECK_SKB_FIELD(skb_iif); CHECK_SKB_FIELD(vlan_proto); CHECK_SKB_FIELD(vlan_tci); CHECK_SKB_FIELD(transport_header); CHECK_SKB_FIELD(network_header); CHECK_SKB_FIELD(mac_header); CHECK_SKB_FIELD(inner_protocol); CHECK_SKB_FIELD(inner_transport_header); CHECK_SKB_FIELD(inner_network_header); CHECK_SKB_FIELD(inner_mac_header); CHECK_SKB_FIELD(mark); #ifdef CONFIG_NETWORK_SECMARK CHECK_SKB_FIELD(secmark); #endif #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif #ifdef CONFIG_XPS CHECK_SKB_FIELD(sender_cpu); #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #endif } /* * You should not add any new code to this function. Add it to * __copy_skb_header above instead. */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { #define C(x) n->x = skb->x n->next = n->prev = NULL; n->sk = NULL; __copy_skb_header(n, skb); C(len); C(data_len); C(mac_len); n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; n->peeked = 0; C(pfmemalloc); n->destructor = NULL; C(tail); C(end); C(head); C(head_frag); C(data); C(truesize); refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); skb->cloned = 1; return n; #undef C } /** * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg * @first: first sk_buff of the msg */ struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) { struct sk_buff *n; n = alloc_skb(0, GFP_ATOMIC); if (!n) return NULL; n->len = first->len; n->data_len = first->len; n->truesize = first->truesize; skb_shinfo(n)->frag_list = first; __copy_skb_header(n, first); n->destructor = NULL; return n; } EXPORT_SYMBOL_GPL(alloc_skb_for_msg); /** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents * * This is identical to skb_clone except that the target skb is * supplied by the user. * * The target skb is returned upon exit. */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { skb_release_all(dst); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg; struct user_struct *user; if (capable(CAP_IPC_LOCK) || !size) return 0; num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ max_pg = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; user = mmp->user ? : current_user(); do { old_pg = atomic_long_read(&user->locked_vm); new_pg = old_pg + num_pg; if (new_pg > max_pg) return -ENOBUFS; } while (atomic_long_cmpxchg(&user->locked_vm, old_pg, new_pg) != old_pg); if (!mmp->user) { mmp->user = get_uid(user); mmp->num_pg = num_pg; } else { mmp->num_pg += num_pg; } return 0; } EXPORT_SYMBOL_GPL(mm_account_pinned_pages); void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info *uarg; struct sk_buff *skb; WARN_ON_ONCE(!in_task()); skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); uarg = (void *)skb->cb; uarg->mmp.user = NULL; if (mm_account_pinned_pages(&uarg->mmp, size)) { kfree_skb(skb); return NULL; } uarg->callback = sock_zerocopy_callback; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; refcount_set(&uarg->refcnt, 1); sock_hold(sk); return uarg; } EXPORT_SYMBOL_GPL(sock_zerocopy_alloc); static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg) { if (uarg) { const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ if (!sock_owned_by_user(sk)) { WARN_ON_ONCE(1); return NULL; } bytelen = uarg->bytelen + size; if (uarg->len == USHRT_MAX - 1 || bytelen > byte_limit) { /* TCP can create new skb to attach new uarg */ if (sk->sk_type == SOCK_STREAM) goto new_alloc; return NULL; } next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg->id + uarg->len) == next) { if (mm_account_pinned_pages(&uarg->mmp, size)) return NULL; uarg->len++; uarg->bytelen = bytelen; atomic_set(&sk->sk_zckey, ++next); /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) sock_zerocopy_get(uarg); return uarg; } } new_alloc: return sock_zerocopy_alloc(sk, size); } EXPORT_SYMBOL_GPL(sock_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 old_lo, old_hi; u64 sum_len; old_lo = serr->ee.ee_info; old_hi = serr->ee.ee_data; sum_len = old_hi - old_lo + 1ULL + len; if (sum_len >= (1ULL << 32)) return false; if (lo != old_hi + 1) return false; serr->ee.ee_data += len; return true; } void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; u32 lo, hi; u16 len; mm_unaccount_pinned_pages(&uarg->mmp); /* if !len, there was only 1 call, and it was aborted * so do not queue a completion notification */ if (!uarg->len || sock_flag(sk, SOCK_DEAD)) goto release; len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = 0; serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; if (!success) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; spin_lock_irqsave(&q->lock, flags); tail = skb_peek_tail(q); if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY || !skb_zerocopy_notify_extend(tail, lo, len)) { __skb_queue_tail(q, skb); skb = NULL; } spin_unlock_irqrestore(&q->lock, flags); sk->sk_error_report(sk); release: consume_skb(skb); sock_put(sk); } EXPORT_SYMBOL_GPL(sock_zerocopy_callback); void sock_zerocopy_put(struct ubuf_info *uarg) { if (uarg && refcount_dec_and_test(&uarg->refcnt)) { if (uarg->callback) uarg->callback(uarg, uarg->zerocopy); else consume_skb(skb_from_uarg(uarg)); } } EXPORT_SYMBOL_GPL(sock_zerocopy_put); void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { struct sock *sk = skb_from_uarg(uarg)->sk; atomic_dec(&sk->sk_zckey); uarg->len--; if (have_uref) sock_zerocopy_put(uarg); } } EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) { struct ubuf_info *orig_uarg = skb_zcopy(skb); struct iov_iter orig_iter = msg->msg_iter; int err, orig_len = skb->len; /* An skb can only point to one uarg. This edge case happens when * TCP appends to an skb, but zerocopy_realloc triggered a new alloc. */ if (orig_uarg && uarg != orig_uarg) return -EEXIST; err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; /* Streams do not free skb on error. Reset to prev state. */ msg->msg_iter = orig_iter; skb->sk = sk; ___pskb_trim(skb, orig_len); skb->sk = save_sk; return err; } skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { if (skb_zcopy(orig)) { if (skb_zcopy(nskb)) { /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ if (!gfp_mask) { WARN_ON_ONCE(1); return -ENOMEM; } if (skb_uarg(nskb) == skb_uarg(orig)) return 0; if (skb_copy_ubufs(nskb, GFP_ATOMIC)) return -EIO; } skb_zcopy_set(nskb, skb_uarg(orig), NULL); } return 0; } /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * * This must be called on SKBTX_DEV_ZEROCOPY skb. * It will copy all frags into kernel and drop the reference * to userspace pages. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. * * Returns 0 on success or a negative error code on failure * to allocate kernel memory to copy to. */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, new_frags; u32 d_off; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; if (!num_frags) goto release; new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < new_frags; i++) { page = alloc_page(gfp_mask); if (!page) { while (head) { struct page *next = (struct page *)page_private(head); put_page(head); head = next; } return -ENOMEM; } set_page_private(page, (unsigned long)head); head = page; } page = head; d_off = 0; for (i = 0; i < num_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); while (done < p_len) { if (d_off == PAGE_SIZE) { d_off = 0; page = (struct page *)page_private(page); } copy = min_t(u32, PAGE_SIZE - d_off, p_len - done); memcpy(page_address(page) + d_off, vaddr + p_off + done, copy); done += copy; d_off += copy; } kunmap_atomic(vaddr); } } /* skb frags release userspace buffers */ for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { __skb_fill_page_desc(skb, i, head, 0, PAGE_SIZE); head = (struct page *)page_private(head); } __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; release: skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority * * Duplicate an &sk_buff. The new one is not owned by a socket. Both * copies share the same packet data but not structure. The new * buffer has a reference count of 1. If the allocation fails the * function returns %NULL otherwise the new buffer is returned. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. */ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff_fclones *fclones = container_of(skb, struct sk_buff_fclones, skb1); struct sk_buff *n; if (skb_orphan_frags(skb, gfp_mask)) return NULL; if (skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) == 1) { n = &fclones->skb2; refcount_set(&fclones->fclone_ref, 2); } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; n->fclone = SKB_FCLONE_UNAVAILABLE; } return __skb_clone(n, skb); } EXPORT_SYMBOL(skb_clone); void skb_headers_offset_update(struct sk_buff *skb, int off) { /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += off; /* {transport,network,mac}_header and tail are relative to skb->head */ skb->transport_header += off; skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; skb->inner_transport_header += off; skb->inner_network_header += off; skb->inner_mac_header += off; } EXPORT_SYMBOL(skb_headers_offset_update); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { if (skb_pfmemalloc(skb)) return SKB_ALLOC_RX; return 0; } /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data. This is used when the * caller wishes to modify the data and needs a private copy of the * data to alter. Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * As by-product this function converts non-linear &sk_buff to linear * one, so that &sk_buff becomes completely private and caller is allowed * to modify all the data of returned buffer. This means that this * function is not recommended for use in circumstances when only * header is going to be modified. Use pskb_copy() instead. */ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; unsigned int size; int headerlen; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; headerlen = skb_headroom(skb); size = skb_end_offset(skb) + skb->data_len; n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; /* Set the data pointer */ skb_reserve(n, headerlen); /* Set the tail pointer and length */ skb_put(n, skb->len); BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); /** * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy * @headroom: headroom of new skb * @gfp_mask: allocation priority * @fclone: if true allocate the copy of the skb from the fclone * cache instead of the head cache; it is recommended to set this * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when * the caller wishes to modify only header of &sk_buff and needs * private copy of the header to alter. Returns %NULL on failure * or the pointer to the buffer on success. * The returned buffer has a reference count of 1. */ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone) { unsigned int size = skb_headlen(skb) + headroom; int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ skb_copy_from_linear_data(skb, n->data, n->len); n->truesize += skb->data_len; n->data_len = skb->data_len; n->len = skb->len; if (skb_shinfo(skb)->nr_frags) { int i; if (skb_orphan_frags(skb, gfp_mask) || skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; skb_shinfo(n)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; } if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } skb_copy_header(n, skb); out: return n; } EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @nhead: room to add at head * @ntail: room to add at tail * @gfp_mask: allocation priority * * Expands (or creates identical copy, if @nhead and @ntail are zero) * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { int i, osize = skb_end_offset(skb); int size = osize + nhead + ntail; long off; u8 *data; BUG_ON(nhead < 0); BUG_ON(skb_shared(skb)); size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. */ memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); /* * if shinfo is shared we must drop the old head gracefully, but if it * is not we can just drop the old head and let the existing refcount * be since all we did is relocate the values */ if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; if (skb_zcopy(skb)) refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb); } else { skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; skb->head_frag = 0; skb->data += off; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; off = nhead; #else skb->end = skb->head + size; #endif skb->tail += off; skb_headers_offset_update(skb, nhead); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); skb_metadata_clear(skb); /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). */ if (!skb->sk || skb->destructor == sock_edemux) skb->truesize += size - osize; return 0; nofrags: kfree(data); nodata: return -ENOMEM; } EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) { struct sk_buff *skb2; int delta = headroom - skb_headroom(skb); if (delta <= 0) skb2 = pskb_copy(skb, GFP_ATOMIC); else { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { kfree_skb(skb2); skb2 = NULL; } } return skb2; } EXPORT_SYMBOL(skb_realloc_headroom); /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @headroom: needed headroom * * Unlike skb_realloc_headroom, this one does not allocate a new skb * if possible; copies skb->sk to new skb as needed * and frees original skb in case of failures. * * It expect increased headroom and generates warning otherwise. */ struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); int osize = skb_end_offset(skb); struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; delta = SKB_DATA_ALIGN(delta); /* pskb_expand_head() might crash, if skb is shared. */ if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) goto fail; if (sk) skb_set_owner_w(nskb, sk); consume_skb(skb); skb = nskb; } if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) goto fail; if (sk && is_skb_wmem(skb)) { delta = skb_end_offset(skb) - osize; refcount_add(delta, &sk->sk_wmem_alloc); skb->truesize += delta; } return skb; fail: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_expand_head); /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head * @newtailroom: new free bytes at tail * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data and while doing so * allocate additional space. * * This is used when the caller wishes to modify the data and needs a * private copy of the data to alter as well as more space for new fields. * Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask) { /* * Allocate the copy buffer */ int head_copy_len, head_copy_off; struct sk_buff *n; int oldheadroom; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; oldheadroom = skb_headroom(skb); n = __alloc_skb(newheadroom + skb->len + newtailroom, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; skb_reserve(n, newheadroom); /* Set the tail pointer and length */ skb_put(n, skb->len); head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; else head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); return n; } EXPORT_SYMBOL(skb_copy_expand); /** * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error * if @free_on_error is true. */ int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { int err; int ntail; /* If the skbuff is non linear tailroom is always zero.. */ if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); return 0; } ntail = skb->data_len + pad - (skb->end - skb->tail); if (likely(skb_cloned(skb) || ntail > 0)) { err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); if (unlikely(err)) goto free_skb; } /* FIXME: The use of this function with non-linear skb's really needs * to be audited. */ err = skb_linearize(skb); if (unlikely(err)) goto free_skb; memset(skb->data + skb->len, 0, pad); return 0; free_skb: if (free_on_error) kfree_skb(skb); return err; } EXPORT_SYMBOL(__skb_pad); /** * pskb_put - add data to the tail of a potentially fragmented buffer * @skb: start of the buffer to use * @tail: tail fragment of the buffer to use * @len: amount of data to add * * This function extends the used data area of the potentially * fragmented buffer. @tail must be the last fragment of @skb -- or * @skb itself. If this would exceed the total buffer size the kernel * will panic. A pointer to the first byte of the extra data is * returned. */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { if (tail != skb) { skb->data_len += len; skb->len += len; } return skb_put(tail, len); } EXPORT_SYMBOL_GPL(pskb_put); /** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer. If this would * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ void *skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; if (unlikely(skb->tail > skb->end)) skb_over_panic(skb, len, __builtin_return_address(0)); return tmp; } EXPORT_SYMBOL(skb_put); /** * skb_push - add data to the start of a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer at the buffer * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; if (unlikely(skb->data < skb->head)) skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data; } EXPORT_SYMBOL(skb_push); /** * skb_pull - remove data from the start of a buffer * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the next data in the buffer * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ void *skb_pull(struct sk_buff *skb, unsigned int len) { return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); /** * skb_trim - remove end from a buffer * @skb: buffer to alter * @len: new length * * Cut the length of a buffer down by removing data from the tail. If * the buffer is already under the length specified it is not modified. * The skb must be linear. */ void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) __skb_trim(skb, len); } EXPORT_SYMBOL(skb_trim); /* Trims skb to length len. It can change skb pointers. */ int ___pskb_trim(struct sk_buff *skb, unsigned int len) { struct sk_buff **fragp; struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; int err; if (skb_cloned(skb) && unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) return err; i = 0; if (offset >= len) goto drop_pages; for (; i < nfrags; i++) { int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); goto done; } for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); fragp = &frag->next) { int end = offset + frag->len; if (skb_shared(frag)) { struct sk_buff *nfrag; nfrag = skb_clone(frag, GFP_ATOMIC); if (unlikely(!nfrag)) return -ENOMEM; nfrag->next = frag->next; consume_skb(frag); frag = nfrag; *fragp = frag; } if (end < len) { offset = end; continue; } if (end > len && unlikely((err = pskb_trim(frag, len - offset)))) return err; if (frag->next) skb_drop_list(&frag->next); break; } done: if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { skb->len = len; skb->data_len = 0; skb_set_tail_pointer(skb, len); } if (!skb->sk || skb->destructor == sock_edemux) skb_condense(skb); return 0; } EXPORT_SYMBOL(___pskb_trim); /* Note : use pskb_trim_rcsum() instead of calling this directly */ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len; skb->csum = csum_block_sub(skb->csum, skb_checksum(skb, len, delta, 0), len); } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len; int offset = skb_checksum_start_offset(skb) + skb->csum_offset; if (offset + sizeof(__sum16) > hdlen) return -EINVAL; } return __pskb_trim(skb, len); } EXPORT_SYMBOL(pskb_trim_rcsum_slow); /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate * @delta: number of bytes to advance tail * * The function makes a sense only on a fragmented &sk_buff, * it expands header moving its tail forward and copying necessary * data from fragmented part. * * &sk_buff MUST have reference count of 1. * * Returns %NULL (and &sk_buff does not change) if pull failed * or value of new tail of skb in the case of success. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ /* Moves tail of skb head forward, copying data from fragmented part, * when it is necessary. * 1. It may fail due to malloc failure. * 2. It may change skb pointers. * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ void *__pskb_pull_tail(struct sk_buff *skb, int delta) { /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough * room at tail, reallocate without expansion only if skb is cloned. */ int i, k, eat = (skb->tail + delta) - skb->end; if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) return NULL; } BUG_ON(skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size >= eat) goto pull_pages; eat -= size; } /* If we need update frag list, we are in troubles. * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. * Pure masohism, indeed. 8)8) */ if (eat) { struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_is_gso(skb) && !list->head_frag && skb_headlen(list)) skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ clone = skb_clone(list, GFP_ATOMIC); if (!clone) return NULL; insp = list->next; list = clone; } else { /* This may be pulled without * problems. */ insp = list; } if (!pskb_pull(list, eat)) { kfree_skb(clone); return NULL; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; skb_shinfo(skb)->frag_list = clone; } } /* Success! Now we may commit changes to skb data. */ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; *frag = skb_shinfo(skb)->frags[i]; if (eat) { skb_frag_off_add(frag, eat); skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; } k++; } } skb_shinfo(skb)->nr_frags = k; end: skb->tail += delta; skb->data_len -= delta; if (!skb->data_len) skb_zcopy_clear(skb, false); return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); /** * skb_copy_bits - copy bits from skb to kernel buffer * @skb: source skb * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source skb to the * destination buffer. * * CAUTION ! : * If its prototype is ever changed, * check arch/{*}/net/{*}.S files, * since it is called from BPF assembly code. */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; /* Copy header. */ if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; to += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(f, skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_copy_bits(frag_iter, offset - start, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_copy_bits); /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { put_page(spd->pages[i]); } static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) return NULL; *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); memcpy(page_address(pfrag->page) + pfrag->offset, page_address(page) + *offset, *len); *offset = pfrag->offset; pfrag->offset += *len; return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, struct page *page, unsigned int offset) { return spd->nr_pages && spd->pages[spd->nr_pages - 1] == page && (spd->partial[spd->nr_pages - 1].offset + spd->partial[spd->nr_pages - 1].len == offset); } /* * Fill page/offset/length into spd, if it can hold more pages. */ static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { page = linear_to_page(page, len, &offset, sk); if (!page) return true; } if (spd_can_coalesce(spd, page, offset)) { spd->partial[spd->nr_pages - 1].len += *len; return false; } get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; return false; } static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) { if (!*len) return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; return false; } /* ignore any bits we already processed */ poff += *off; plen -= *off; *off = 0; do { unsigned int flen = min(*len, plen); if (spd_fill_page(spd, pipe, page, &flen, poff, linear, sk)) return true; poff += flen; plen -= flen; *len -= flen; } while (*len && plen); return false; } /* * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsigned int *offset, unsigned int *len, struct splice_pipe_desc *spd, struct sock *sk) { int seg; struct sk_buff *iter; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a * fragment, and if the head is not shared with any clones then * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; /* * then map the fragments */ for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) return true; } skb_walk_frags(skb, iter) { if (*offset >= iter->len) { *offset -= iter->len; continue; } /* __skb_splice_bits() only fails if the output has no room * left, so no point in going over the frag_list for the error * case. */ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) return true; } return false; } /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; int ret = 0; __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); if (spd.nr_pages) ret = splice_to_pipe(pipe, &spd); return ret; } EXPORT_SYMBOL_GPL(skb_splice_bits); /* Send skb data on a socket. Socket must be locked. */ int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len) { unsigned int orig_len = len; struct sk_buff *head = skb; unsigned short fragidx; int slen, ret; do_frag_list: /* Deal with head data */ while (offset < skb_headlen(skb) && len) { struct kvec kv; struct msghdr msg; slen = min_t(int, len, skb_headlen(skb) - offset); kv.iov_base = skb->data + offset; kv.iov_len = slen; memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT; ret = kernel_sendmsg_locked(sk, &msg, &kv, 1, slen); if (ret <= 0) goto error; offset += ret; len -= ret; } /* All the data was skb head? */ if (!len) goto out; /* Make offset relative to start of frags */ offset -= skb_headlen(skb); /* Find where we are in frag list */ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; if (offset < skb_frag_size(frag)) break; offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { ret = kernel_sendpage_locked(sk, skb_frag_page(frag), skb_frag_off(frag) + offset, slen, MSG_DONTWAIT); if (ret <= 0) goto error; len -= ret; offset += ret; slen -= ret; } offset = 0; } if (len) { /* Process any frag lists */ if (skb == head) { if (skb_has_frag_list(skb)) { skb = skb_shinfo(skb)->frag_list; goto do_frag_list; } } else if (skb->next) { skb = skb->next; goto do_frag_list; } } out: return orig_len - len; error: return orig_len == len ? ret : orig_len - len; } EXPORT_SYMBOL_GPL(skb_send_sock_locked); /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer * @offset: offset in destination * @from: source buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source buffer to the * destination skb. This function handles all the messy bits of * traversing fragment lists and such. */ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; from += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_store_bits(frag_iter, offset - start, from, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ if (copy > 0) { if (copy > len) copy = len; csum = INDIRECT_CALL_1(ops->update, csum_partial_ext, skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; pos = copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = INDIRECT_CALL_1(ops->update, csum_partial_ext, vaddr + p_off, p_len, 0); kunmap_atomic(vaddr); csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, csum, csum2, pos, p_len); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { __wsum csum2; if (copy > len) copy = len; csum2 = __skb_checksum(frag_iter, offset - start, copy, 0, ops); csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, csum, csum2, pos, copy); if ((len -= copy) == 0) return csum; offset += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(__skb_checksum); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { const struct skb_checksum_ops ops = { .update = csum_partial_ext, .combine = csum_block_add_ext, }; return __skb_checksum(skb, offset, len, csum, &ops); } EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; __wsum csum = 0; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial_copy_nocheck(skb->data + offset, to, copy); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos = copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, to + copied, p_len); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { __wsum csum2; int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; csum2 = skb_copy_and_csum_bits(frag_iter, offset - start, to, copy); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_copy_and_csum_bits); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { __sum16 sum; sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) skb->csum_valid = !sum; return sum; } EXPORT_SYMBOL(__skb_checksum_complete_head); /* This function assumes skb->csum already holds pseudo header's checksum, * which has been changed from the hardware checksum, for example, by * __skb_checksum_validate_complete(). And, the original skb->csum must * have been validated unsuccessfully for CHECKSUM_COMPLETE case. * * It returns non-zero if the recomputed checksum is still invalid, otherwise * zero. The new checksum is stored back into skb->csum unless the skb is * shared. */ __sum16 __skb_checksum_complete(struct sk_buff *skb) { __wsum csum; __sum16 sum; csum = skb_checksum(skb, 0, skb->len, 0); sum = csum_fold(csum_add(skb->csum, csum)); /* This check is inverted, because we already knew the hardware * checksum is invalid before calling this function. So, if the * re-computed checksum is valid instead, then we have a mismatch * between the original skb->csum and skb_checksum(). This means either * the original hardware checksum is incorrect or we screw up skb->csum * when moving skb->data around. */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) { /* Save full packet checksum */ skb->csum = csum; skb->ip_summed = CHECKSUM_COMPLETE; skb->csum_complete_sw = 1; skb->csum_valid = !sum; } return sum; } EXPORT_SYMBOL(__skb_checksum_complete); static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum) { net_warn_ratelimited( "%s: attempt to compute crc32c without libcrc32c.ko\n", __func__); return 0; } static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2, int offset, int len) { net_warn_ratelimited( "%s: attempt to compute crc32c without libcrc32c.ko\n", __func__); return 0; } static const struct skb_checksum_ops default_crc32c_ops = { .update = warn_crc32c_csum_update, .combine = warn_crc32c_csum_combine, }; const struct skb_checksum_ops *crc32c_csum_stub __read_mostly = &default_crc32c_ops; EXPORT_SYMBOL(crc32c_csum_stub); /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer * * Calculates the amount of linear headroom needed in the 'to' skb passed * into skb_zerocopy(). */ unsigned int skb_zerocopy_headlen(const struct sk_buff *from) { unsigned int hlen = 0; if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); if (!hlen) hlen = from->len; } if (skb_has_frag_list(from)) hlen = from->len; return hlen; } EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); /** * skb_zerocopy - Zero copy skb to skb * @to: destination buffer * @from: source buffer * @len: number of bytes to copy from source buffer * @hlen: size of linear headroom in destination buffer * * Copies up to `len` bytes from `from` to `to` by creating references * to the frags in the source buffer. * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. * * Return value: * 0: everything is OK * -ENOMEM: couldn't orphan frags of @from due to lack of memory * -EFAULT: skb_copy_bits() found some problem with skb geometry */ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); /* dont bother with small payloads */ if (len <= skb_tailroom(to)) return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); if (unlikely(ret)) return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); __skb_fill_page_desc(to, 0, page, offset, plen); get_page(page); j = 1; len -= plen; } } to->truesize += len + plen; to->len += len + plen; to->data_len += len + plen; if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { skb_tx_error(from); return -ENOMEM; } skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { int size; if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), len); skb_frag_size_set(&skb_shinfo(to)->frags[j], size); len -= size; skb_frag_ref(to, j); j++; } skb_shinfo(to)->nr_frags = j; return 0; } EXPORT_SYMBOL_GPL(skb_zerocopy); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart); if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum_offset; *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The head item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. The list lock is taken so the function * may be used safely with other locking list functions. The tail item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue_tail(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge - empty a list * @list: list to empty * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ void skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = skb_dequeue(list)) != NULL) kfree_skb(skb); } EXPORT_SYMBOL(skb_queue_purge); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); sum += skb->truesize; kfree_skb(skb); } return sum; } /** * skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the tail of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * @list: list to use * * Remove a packet from a list. The list locks are taken and this * function is atomic with respect to other list locked calls * * You must know what list the SKB is on. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * @list: list to use * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls. * A buffer cannot be placed on two lists at the same time. */ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_append); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { int i; skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, int pos) { int i, k = 0; const int nfrags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->len = skb1->data_len = skb->len - len; skb->len = len; skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < len) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; } else skb_shinfo(skb)->nr_frags++; pos += size; } skb_shinfo(skb1)->nr_frags = k; } /** * skb_split - Split fragmented skb to two parts at length len. * @skb: the buffer to split * @skb1: the buffer to receive the second part * @len: new length for skb */ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); skb_shinfo(skb1)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } EXPORT_SYMBOL(skb_split); /* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here! */ static int skb_prepare_for_shift(struct sk_buff *skb) { int ret = 0; if (skb_cloned(skb)) { /* Save and restore truesize: pskb_expand_head() may reallocate * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we * cannot change truesize at this point. */ unsigned int save_truesize = skb->truesize; ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); skb->truesize = save_truesize; } return ret; } /** * skb_shift - Shifts paged data partially from skb to another * @tgt: buffer into which tail data gets added * @skb: buffer from which the paged data comes from * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. * * Skb cannot include anything else but paged data while tgt is allowed * to have non-paged data as well. * * TODO: full sized shift could be optimized but that would need * specialized skb free'er to handle frags without up-to-date nr_frags. */ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); if (skb_headlen(skb)) return 0; if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0; todo = shiftlen; from = 0; to = skb_shinfo(tgt)->nr_frags; fragfrom = &skb_shinfo(skb)->frags[from]; /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ if (!to || !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; /* All previous frag pointers might be stale! */ fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } from++; } /* Skip full, not-fitting skb to avoid expensive operations */ if ((shiftlen == skb->len) && (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) return 0; if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { if (to == MAX_SKB_FRAGS) return 0; fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; todo -= skb_frag_size(fragfrom); from++; to++; } else { __skb_frag_ref(fragfrom); skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; to++; break; } } /* Ready to "commit" this state change to tgt */ skb_shinfo(tgt)->nr_frags = to; if (merge >= 0) { fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); __skb_frag_unref(fragfrom); } /* Reposition in the original skb */ to = 0; while (from < skb_shinfo(skb)->nr_frags) skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; skb_shinfo(skb)->nr_frags = to; BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); onlymerged: /* Most likely the tgt won't ever need its checksum anymore, skb on * the other hand might need it if it needs to be resent */ tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(tgt)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; /* Yak, is it really working this way? Some helper please? */ skb->len -= shiftlen; skb->data_len -= shiftlen; skb->truesize -= shiftlen; tgt->len += shiftlen; tgt->data_len += shiftlen; tgt->truesize += shiftlen; return shiftlen; } /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read * @from: lower offset of data to be read * @to: upper offset of data to be read * @st: state variable * * Initializes the specified state variable. Must be called before * invoking skb_seq_read() for the first time. */ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st) { st->lower_offset = from; st->upper_offset = to; st->root_skb = st->cur_skb = skb; st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; } EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data * @consumed: number of bytes consumed by the caller so far * @data: destination pointer for data to be returned * @st: state variable * * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st) { unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; if (unlikely(abs_offset >= st->upper_offset)) { if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } return 0; } next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; if (abs_offset < block_limit && !st->frag_data) { *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; block_limit = skb_frag_size(frag) + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag)); *data = (u8 *) st->frag_data + skb_frag_off(frag) + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->frag_idx++; st->stepped_offset += skb_frag_size(frag); } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; } else if (st->cur_skb->next) { st->cur_skb = st->cur_skb->next; st->frag_idx = 0; goto next_skb; } return 0; } EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data * @st: state variable * * Must be called if skb_seq_read() was not called until it * returned 0. */ void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, struct ts_config *conf, struct ts_state *state) { return skb_seq_read(offset, text, TS_SKB_CB(state)); } static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) { skb_abort_seq_read(TS_SKB_CB(state)); } /** * skb_find_text - Find a text pattern in skb data * @skb: the buffer to look in * @from: search offset * @to: search limit * @config: textsearch configuration * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve * subsequent occurrences of the pattern. Returns the offset * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { struct ts_state state; unsigned int ret; config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); return (ret <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size) { int i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < MAX_SKB_FRAGS) { get_page(page); skb_fill_page_desc(skb, i, page, offset, size); } else { return -EMSGSIZE; } return 0; } EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_pull on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_pull unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { unsigned char *data = skb->data; BUG_ON(len > skb->len); __skb_pull(skb, len); skb_postpull_rcsum(skb, data, len); return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) { skb_frag_t head_frag; struct page *page; page = virt_to_head_page(frag_skb->head); __skb_frag_set_page(&head_frag, page); skb_frag_off_set(&head_frag, frag_skb->data - (unsigned char *)page_address(page)); skb_frag_size_set(&head_frag, skb_headlen(frag_skb)); return head_frag; } struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset) { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_truesize = 0; unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int err; skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ err = skb_unclone(skb, GFP_ATOMIC); if (err) goto err_linearize; skb_shinfo(skb)->frag_list = NULL; while (list_skb) { nskb = list_skb; list_skb = list_skb->next; err = 0; delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { consume_skb(nskb); nskb = tmp; err = skb_unclone(nskb, GFP_ATOMIC); } else { err = -ENOMEM; } } if (!tail) skb->next = nskb; else tail->next = nskb; if (unlikely(err)) { nskb->next = list_skb; goto err_linearize; } tail = nskb; delta_len += nskb->len; skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; skb_gso_reset(skb); skb->prev = tail; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto err_linearize; skb_get(skb); return skb; err_linearize: kfree_skb_list(skb->next); skb->next = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(skb_segment_list); int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) { if (unlikely(p->len + skb->len >= 65536)) return -E2BIG; if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; skb_pull(skb, skb_gro_offset(skb)); NAPI_GRO_CB(p)->last = skb; NAPI_GRO_CB(p)->count++; p->data_len += skb->len; p->truesize += skb->truesize; p->len += skb->len; skb_shinfo(p)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; NAPI_GRO_CB(skb)->same_flow = 1; return 0; } /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ struct sk_buff *skb_segment(struct sk_buff *head_skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; struct sk_buff *frag_skb; skb_frag_t *frag; __be16 proto; bool csum, sg; int err = -ENOMEM; int i = 0; int nfrags, pos; if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { struct sk_buff *check_skb; for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { if (skb_headlen(check_skb) && !check_skb->head_frag) { /* gso_size is untrusted, and we have a frag_list with * a linear non head_frag item. * * If head_skb's headlen does not fit requested gso_size, * it means that the frag_list members do NOT terminate * on exact gso_size boundaries. Hence we cannot perform * skb_frag_t page sharing. Therefore we must fallback to * copying the frag_list skbs; we do so by disabling SG. */ features &= ~NETIF_F_SG; break; } } } __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL); sg = !!(features & NETIF_F_SG); csum = !!can_checksum_protocol(features, proto); if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; /* If we get here then all the required * GSO features except frag_list are supported. * Try to split the SKB to multiple GSO SKBs * with no frag_list. * Currently we can do that only when the buffers don't * have a linear part and all the buffers except * the last are of the same length. */ frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { if (frag_len != iter->len && iter->next) goto normal; if (skb_headlen(iter) && !iter->head_frag) goto normal; len -= iter->len; } if (len != frag_len) goto normal; } /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. * Cap len to not accidentally hit GSO_BY_FRAGS. */ partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else partial_segs = 0; } normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); if (skb_orphan_frags(head_skb, GFP_ATOMIC)) return ERR_PTR(-ENOMEM); nfrags = skb_shinfo(head_skb)->nr_frags; frag = skb_shinfo(head_skb)->frags; frag_skb = head_skb; do { struct sk_buff *nskb; skb_frag_t *nskb_frag; int hsize; int size; if (unlikely(mss == GSO_BY_FRAGS)) { len = list_skb->len; } else { len = head_skb->len - offset; if (len > mss) len = mss; } hsize = skb_headlen(head_skb) - offset; if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; if (!hsize && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); nskb = skb_clone(list_skb, GFP_ATOMIC); if (unlikely(!nskb)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; frag++; } list_skb = list_skb->next; if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; } hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) goto err; skb_reserve(nskb, headroom); __skb_put(nskb, doffset); } if (segs) tail->next = nskb; else segs = nskb; tail = nskb; __copy_skb_header(nskb, head_skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { if (!csum) { if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) goto err; } continue; } nskb_frag = skb_shinfo(nskb)->frags; skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); skb_shinfo(nskb)->tx_flags |= (skb_shinfo(head_skb)->tx_flags | skb_shinfo(frag_skb)->tx_flags) & SKBTX_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { if (skb_orphan_frags(list_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, list_skb, GFP_ATOMIC)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; skb_shinfo(nskb)->tx_flags |= skb_shinfo(frag_skb)->tx_flags & SKBTX_SHARED_FRAG; if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { BUG_ON(!list_skb->head_frag); /* to make room for head_frag. */ i--; frag--; } list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS)) { net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); err = -EINVAL; goto err; } *nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag; __skb_frag_ref(nskb_frag); size = skb_frag_size(nskb_frag); if (pos < offset) { skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; frag++; pos += size; } else { skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } nskb_frag++; } skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; perform_csum_check: if (!csum) { if (skb_has_shared_frag(nskb) && __skb_linearize(nskb)) goto err; if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); /* Some callers want to get the end of the list. * Put it in segs->prev to avoid walking the list. * (see validate_xmit_skb_list() for example) */ segs->prev = tail; if (partial_segs) { struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; unsigned short gso_size = skb_shinfo(head_skb)->gso_size; /* Update type to add partial and then remove dodgy if set */ type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL; type &= ~SKB_GSO_DODGY; /* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols. */ for (iter = segs; iter; iter = iter->next) { skb_shinfo(iter)->gso_size = gso_size; skb_shinfo(iter)->gso_segs = partial_segs; skb_shinfo(iter)->gso_type = type; SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset; } if (tail->len - doffset <= gso_size) skb_shinfo(tail)->gso_size = 0; else if (tail != segs) skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size); } /* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment. */ if (head_skb->destructor == sock_wfree) { swap(tail->truesize, head_skb->truesize); swap(tail->destructor, head_skb->destructor); swap(tail->sk, head_skb->sk); } return segs; err: kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) { struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; struct sk_buff *lp; if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) return -E2BIG; lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); if (headlen <= offset) { skb_frag_t *frag; skb_frag_t *frag2; int i = skbinfo->nr_frags; int nr_frags = pinfo->nr_frags + i; if (nr_frags > MAX_SKB_FRAGS) goto merge; offset -= headlen; pinfo->nr_frags = nr_frags; skbinfo->nr_frags = 0; frag = pinfo->frags + nr_frags; frag2 = skbinfo->frags + i; do { *--frag = *--frag2; } while (--i); skb_frag_off_add(frag, offset); skb_frag_size_sub(frag, offset); /* all fragments truesize : remove (head size + sk_buff) */ delta_truesize = skb->truesize - SKB_TRUESIZE(skb_end_offset(skb)); skb->truesize -= skb->data_len; skb->len -= skb->data_len; skb->data_len = 0; NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; goto done; } else if (skb->head_frag) { int nr_frags = pinfo->nr_frags; skb_frag_t *frag = pinfo->frags + nr_frags; struct page *page = virt_to_head_page(skb->head); unsigned int first_size = headlen - offset; unsigned int first_offset; if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) goto merge; first_offset = skb->data - (unsigned char *)page_address(page) + offset; pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; __skb_frag_set_page(frag, page); skb_frag_off_set(frag, first_offset); skb_frag_size_set(frag, first_size); memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); /* We dont need to clear skbinfo->nr_frags here */ delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } merge: delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; skb_frag_off_add(&skbinfo->frags[0], eat); skb_frag_size_sub(&skbinfo->frags[0], eat); skb->data_len -= eat; skb->len -= eat; offset = headlen; } __skb_pull(skb, offset); if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; NAPI_GRO_CB(p)->last = skb; __skb_header_release(skb); lp = p; done: NAPI_GRO_CB(p)->count++; p->data_len += len; p->truesize += delta_truesize; p->len += len; skb_shinfo(p)->tx_flags |= skbinfo->tx_flags & SKBTX_SHARED_FRAG; if (lp != p) { lp->data_len += len; lp->truesize += delta_truesize; lp->len += len; skb_shinfo(lp)->tx_flags |= skbinfo->tx_flags & SKBTX_SHARED_FRAG; } NAPI_GRO_CB(skb)->same_flow = 1; return 0; } #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info), #endif #ifdef CONFIG_XFRM [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path), #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif }; static __always_inline unsigned int skb_ext_total_length(void) { return SKB_EXT_CHUNKSIZEOF(struct skb_ext) + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) skb_ext_type_len[SKB_EXT_BRIDGE_NF] + #endif #ifdef CONFIG_XFRM skb_ext_type_len[SKB_EXT_SEC_PATH] + #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) skb_ext_type_len[TC_SKB_EXT] + #endif #if IS_ENABLED(CONFIG_MPTCP) skb_ext_type_len[SKB_EXT_MPTCP] + #endif 0; } static void skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM >= 8); BUILD_BUG_ON(skb_ext_total_length() > 255); skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } #else static void skb_extensions_init(void) {} #endif void __init skb_init(void) { skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); skb_extensions_init(); } static int __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsigned int recursion_level) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0; if (unlikely(recursion_level >= 24)) return -EMSGSIZE; if (copy > 0) { if (copy > len) copy = len; sg_set_buf(sg, skb->data + offset, copy); elt++; if ((len -= copy) == 0) return elt; offset += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end, ret; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start, copy, recursion_level + 1); if (unlikely(ret < 0)) return ret; elt += ret; if ((len -= copy) == 0) return elt; offset += copy; } start = end; } BUG_ON(len); return elt; } /** * skb_to_sgvec - Fill a scatter-gather list from a socket buffer * @skb: Socket buffer containing the buffers to be mapped * @sg: The scatter-gather list to map into * @offset: The offset into the buffer's contents to start mapping * @len: Length of buffer space to be mapped * * Fill the specified scatter-gather list with mappings/pointers into a * region of the buffer space attached to a socket buffer. Returns either * the number of scatterlist items used, or -EMSGSIZE if the contents * could not fit. */ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len, 0); if (nsg <= 0) return nsg; sg_mark_end(&sg[nsg - 1]); return nsg; } EXPORT_SYMBOL_GPL(skb_to_sgvec); /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after * the first call without calling sg_unmark_end to expend sg list. * * Scenario to use skb_to_sgvec_nomark: * 1. sg_init_table * 2. skb_to_sgvec_nomark(payload1) * 3. skb_to_sgvec_nomark(payload2) * * This is equivalent to: * 1. sg_init_table * 2. skb_to_sgvec(payload1) * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * * When mapping mutilple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { return __skb_to_sgvec(skb, sg, offset, len, 0); } EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); /** * skb_cow_data - Check that a socket buffer's data buffers are writable * @skb: The socket buffer to check. * @tailbits: Amount of trailing space to be added * @trailer: Returned pointer to the skb where the @tailbits space begins * * Make sure that the data buffers attached to a socket buffer are * writable. If they are not, private copies are made of the data buffers * and the socket buffer is set to use these instead. * * If @tailbits is given, make sure that there is space to write @tailbits * bytes of data beyond current end of socket buffer. @trailer will be * set to point to the skb in which this space begins. * * The number of scatterlist elements required to completely map the * COW'd and extended socket buffer will be returned. */ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) { int copyflag; int elt; struct sk_buff *skb1, **skb_p; /* If skb is cloned or its head is paged, reallocate * head pulling out all the pages (pages are considered not writable * at the moment even if they are anonymous). */ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && !__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM; /* Easy case. Most of packets will go this way. */ if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more * space, 128 bytes is fair. */ if (skb_tailroom(skb) < tailbits && pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) return -ENOMEM; /* Voila! */ *trailer = skb; return 1; } /* Misery. We are in troubles, going to mincer fragments... */ elt = 1; skb_p = &skb_shinfo(skb)->frag_list; copyflag = 0; while ((skb1 = *skb_p) != NULL) { int ntail = 0; /* The fragment is partially pulled by someone, * this can happen on input. Copy it and everything * after it. */ if (skb_shared(skb1)) copyflag = 1; /* If the skb is the last, worry about trailer. */ if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } if (copyflag || skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ if (ntail == 0) skb2 = skb_copy(skb1, GFP_ATOMIC); else skb2 = skb_copy_expand(skb1, skb_headroom(skb1), ntail, GFP_ATOMIC); if (unlikely(skb2 == NULL)) return -ENOMEM; if (skb1->sk) skb_set_owner_w(skb2, skb1->sk); /* Looking around. Are we still alive? * OK, link new skb, drop old one */ skb2->next = skb1->next; *skb_p = skb2; kfree_skb(skb1); skb1 = skb2; } elt++; *trailer = skb1; skb_p = &skb1->next; } return elt; } EXPORT_SYMBOL_GPL(skb_cow_data); static void sock_rmem_free(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); } static void skb_set_err_queue(struct sk_buff *skb) { /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING. * So, it is safe to (mis)use it to mark skbs on the error queue. */ skb->pkt_type = PACKET_OUTGOING; BUILD_BUG_ON(PACKET_OUTGOING == 0); } /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); skb_set_err_queue(skb); /* before exiting rcu section, make sure dst is refcounted */ skb_dst_force(skb); skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); static bool is_icmp_err_skb(const struct sk_buff *skb) { return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6); } struct sk_buff *sock_dequeue_err_skb(struct sock *sk) { struct sk_buff_head *q = &sk->sk_error_queue; struct sk_buff *skb, *skb_next = NULL; bool icmp_next = false; unsigned long flags; spin_lock_irqsave(&q->lock, flags); skb = __skb_dequeue(q); if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); if (is_icmp_err_skb(skb) && !icmp_next) sk->sk_err = 0; if (skb_next) sk->sk_error_report(sk); return skb; } EXPORT_SYMBOL(sock_dequeue_err_skb); /** * skb_clone_sk - create clone of skb, and take reference to socket * @skb: the skb to clone * * This function creates a clone of a buffer that holds a reference on * sk_refcnt. Buffers created via this function are meant to be * returned using sock_queue_err_skb, or free via kfree_skb. * * When passing buffers allocated with this function to sock_queue_err_skb * it is necessary to wrap the call with sock_hold/sock_put in order to * prevent the socket from being released prior to being enqueued on * the sk_error_queue. */ struct sk_buff *skb_clone_sk(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sk_buff *clone; if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) { sock_put(sk); return NULL; } clone->sk = sk; clone->destructor = sock_efree; return clone; } EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, int tstype, bool opt_stats) { struct sock_exterr_skb *serr; int err; BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) serr->ee.ee_data -= sk->sk_tskey; } err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); } static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); ret = sk->sk_socket && sk->sk_socket->file && file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW); read_unlock_bh(&sk->sk_callback_lock); return ret; } void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); return; } err: kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); void __skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { struct sk_buff *skb; bool tsonly, opt_stats = false; if (!sk) return; if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb); opt_stats = true; } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { kfree_skb(skb); return; } } if (!skb) return; if (tsonly) { skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags & SKBTX_ANY_TSTAMP; skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; } if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; else skb->tstamp = ktime_get_real(); __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { return __skb_tstamp_tx(orig_skb, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } if (err) kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set * @start: the number of bytes after skb->data to start checksumming. * @off: the offset from start to place the checksum. * * For untrusted partially-checksummed packets, we need to make sure the values * for skb->csum_start and skb->csum_offset are valid so we don't oops. * * This function checks and sets those values and skb->ip_summed: if this * returns false you should drop the packet. */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); u32 csum_start = skb_headroom(skb) + (u32)start; if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) { net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = csum_start; skb->csum_offset = off; skb_set_transport_header(skb, start); return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, unsigned int max) { if (skb_headlen(skb) >= len) return 0; /* If we need to pullup then pullup to the max, so we * won't need to do it again. */ if (max > skb->len) max = skb->len; if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) return -ENOMEM; if (skb_headlen(skb) < len) return -EPROTO; return 0; } #define MAX_TCP_HDR_LEN (15 * 4) static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { int err; switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; case IPPROTO_UDP: err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), off + sizeof(struct udphdr)); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct udphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &udp_hdr(skb)->check; } return ERR_PTR(-EPROTO); } /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; __sum16 *csum; int err; fragment = false; err = skb_maybe_pull_tail(skb, sizeof(struct iphdr), MAX_IP_HDR_LEN); if (err < 0) goto out; if (ip_is_fragment(ip_hdr(skb))) fragment = true; off = ip_hdrlen(skb); err = -EPROTO; if (fragment) goto out; csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - off, ip_hdr(skb)->protocol, 0); err = 0; out: return err; } /* This value should be large enough to cover a tagged ethernet header plus * an IPv6 header, all options, and a maximal TCP or UDP header. */ #define MAX_IPV6_HDR_LEN 256 #define OPT_HDR(type, skb, off) \ (type *)(skb_network_header(skb) + (off)) static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) { int err; u8 nexthdr; unsigned int off; unsigned int len; bool fragment; bool done; __sum16 *csum; fragment = false; done = false; off = sizeof(struct ipv6hdr); err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); if (err < 0) goto out; nexthdr = ipv6_hdr(skb)->nexthdr; len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { struct ipv6_opt_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ipv6_opt_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { struct ip_auth_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ip_auth_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ip_auth_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_authlen(hp); break; } case IPPROTO_FRAGMENT: { struct frag_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct frag_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct frag_hdr, skb, off); if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) fragment = true; nexthdr = hp->nexthdr; off += sizeof(struct frag_hdr); break; } default: done = true; break; } } err = -EPROTO; if (!done || fragment) goto out; csum = skb_checksum_setup_ip(skb, nexthdr, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - off, nexthdr, 0); err = 0; out: return err; } /** * skb_checksum_setup - set up partial checksum offset * @skb: the skb to set up * @recalculate: if true the pseudo-header checksum will be recalculated */ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) { int err; switch (skb->protocol) { case htons(ETH_P_IP): err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): err = skb_checksum_setup_ipv6(skb, recalculate); break; default: err = -EPROTO; break; } return err; } EXPORT_SYMBOL(skb_checksum_setup); /** * skb_checksum_maybe_trim - maybe trims the given skb * @skb: the skb to check * @transport_len: the data length beyond the network header * * Checks whether the given skb has data beyond the given transport length. * If so, returns a cloned skb trimmed to this transport length. * Otherwise returns the provided skb. Returns NULL in error cases * (e.g. transport_len exceeds skb length or out-of-memory). * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsigned int transport_len) { struct sk_buff *skb_chk; unsigned int len = skb_transport_offset(skb) + transport_len; int ret; if (skb->len < len) return NULL; else if (skb->len == len) return skb; skb_chk = skb_clone(skb, GFP_ATOMIC); if (!skb_chk) return NULL; ret = pskb_trim_rcsum(skb_chk, len); if (ret) { kfree_skb(skb_chk); return NULL; } return skb_chk; } /** * skb_checksum_trimmed - validate checksum of an skb * @skb: the skb to check * @transport_len: the data length beyond the network header * @skb_chkf: checksum function to use * * Applies the given checksum function skb_chkf to the provided skb. * Returns a checked and maybe trimmed skb. Returns NULL on error. * * If the skb has data beyond the given transport length, then a * trimmed & cloned skb is checked and returned. * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)) { struct sk_buff *skb_chk; unsigned int offset = skb_transport_offset(skb); __sum16 ret; skb_chk = skb_checksum_maybe_trim(skb, transport_len); if (!skb_chk) goto err; if (!pskb_may_pull(skb_chk, offset)) goto err; skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); skb_push_rcsum(skb_chk, offset); if (ret) goto err; return skb_chk; err: if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return NULL; } EXPORT_SYMBOL(skb_checksum_trimmed); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); kmem_cache_free(skbuff_head_cache, skb); } else { __kfree_skb(skb); } } EXPORT_SYMBOL(kfree_skb_partial); /** * skb_try_coalesce - try to merge skb to prior one * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; if (skb_cloned(to)) return false; if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; return true; } to_shinfo = skb_shinfo(to); from_shinfo = skb_shinfo(from); if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; if (skb_headlen(from) != 0) { struct page *page; unsigned int offset; if (to_shinfo->nr_frags + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) return false; delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { if (to_shinfo->nr_frags + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); } WARN_ON_ONCE(delta < len); memcpy(to_shinfo->frags + to_shinfo->nr_frags, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; if (from_shinfo->nr_frags) to_shinfo->tx_flags |= from_shinfo->tx_flags & SKBTX_SHARED_FRAG; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ for (i = 0; i < from_shinfo->nr_frags; i++) __skb_frag_ref(&from_shinfo->frags[i]); to->truesize += delta; to->len += len; to->data_len += len; *delta_truesize = delta; return true; } EXPORT_SYMBOL(skb_try_coalesce); /** * skb_scrub_packet - scrub an skb * * @skb: buffer to clean * @xnet: packet is crossing netns * * skb_scrub_packet can be used after encapsulating or decapsulting a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in * another namespace (@xnet == true). We have to clear all information in the * skb that could impact namespace isolation. */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif ipvs_reset(skb); if (!xnet) return; skb->mark = 0; skb->tstamp = 0; } EXPORT_SYMBOL_GPL(skb_scrub_packet); /** * skb_gso_transport_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_transport_seglen is used to determine the real size of the * individual segments, including Layer4 headers (TCP/UDP). * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; if (skb->encapsulation) { thlen = skb_inner_transport_header(skb) - skb_transport_header(skb); if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { thlen = sizeof(struct udphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already * accounted for. */ return thlen + shinfo->gso_size; } /** * skb_gso_network_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_network_seglen is used to determine the real size of the * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). * * The MAC/L2 header is not accounted for. */ static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_mac_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_mac_seglen is used to determine the real size of the * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 * headers (TCP/UDP). */ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS * * There are a couple of instances where we have a GSO skb, and we * want to determine what size it would be after it is segmented. * * We might want to check: * - L3+L4+payload size (e.g. IP forwarding) * - L2+L3+L4+payload size (e.g. sanity check before passing to driver) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * * @skb: GSO skb * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * * @max_len: The maximum permissible length. * * Returns true if the segmented length <= max length. */ static inline bool skb_gso_size_check(const struct sk_buff *skb, unsigned int seg_len, unsigned int max_len) { const struct skb_shared_info *shinfo = skb_shinfo(skb); const struct sk_buff *iter; if (shinfo->gso_size != GSO_BY_FRAGS) return seg_len <= max_len; /* Undo this so we can re-use header sizes */ seg_len -= GSO_BY_FRAGS; skb_walk_frags(skb, iter) { if (seg_len + skb_headlen(iter) > max_len) return false; } return true; } /** * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * * skb_gso_validate_network_len validates if a given skb will fit a * wanted MTU once split. It considers L3 headers, L4 headers, and the * payload. */ bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? * * @skb: GSO skb * @len: length to validate against * * skb_gso_validate_mac_len validates if a given skb will fit a wanted * length once split, including L2, L3 and L4 headers and the payload. */ bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len) { return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len); } EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { int mac_len, meta_len; void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } mac_len = skb->data - skb_mac_header(skb); if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) { memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } meta_len = skb_metadata_len(skb); if (meta_len) { meta = skb_metadata_end(skb) - meta_len; memmove(meta + VLAN_HLEN, meta, meta_len); } skb->mac_header += VLAN_HLEN; return skb; } struct sk_buff *skb_vlan_untag(struct sk_buff *skb) { struct vlan_hdr *vhdr; u16 vlan_tci; if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; vlan_tci = ntohs(vhdr->h_vlan_TCI); __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb = skb_reorder_vlan_header(skb); if (unlikely(!skb)) goto err_free; skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_reset_mac_len(skb); return skb; err_free: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_vlan_untag); int skb_ensure_writable(struct sk_buff *skb, int write_len) { if (!pskb_may_pull(skb, write_len)) return -ENOMEM; if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; return pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable); /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr; int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = skb_ensure_writable(skb, VLAN_ETH_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); __skb_pull(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb->mac_header += VLAN_HLEN; if (skb_network_offset(skb) < ETH_HLEN) skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return err; } EXPORT_SYMBOL(__skb_vlan_pop); /* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header. */ int skb_vlan_pop(struct sk_buff *skb) { u16 vlan_tci; __be16 vlan_proto; int err; if (likely(skb_vlan_tag_present(skb))) { __vlan_hwaccel_clear_tag(skb); } else { if (unlikely(!eth_type_vlan(skb->protocol))) return 0; err = __skb_vlan_pop(skb, &vlan_tci); if (err) return err; } /* move next vlan tag to hw accel tag */ if (likely(!eth_type_vlan(skb->protocol))) return 0; vlan_proto = skb->protocol; err = __skb_vlan_pop(skb, &vlan_tci); if (unlikely(err)) return err; __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_pop); /* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present). * Expects skb->data at mac header. */ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { if (skb_vlan_tag_present(skb)) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "skb_vlan_push got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; skb->mac_len += VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_push); /** * skb_eth_pop() - Drop the Ethernet header at the head of a packet * * @skb: Socket buffer to modify * * Drop the Ethernet header of @skb. * * Expects that skb->data points to the mac header and that no VLAN tags are * present. * * Returns 0 on success, -errno otherwise. */ int skb_eth_pop(struct sk_buff *skb) { if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || skb_network_offset(skb) < ETH_HLEN) return -EPROTO; skb_pull_rcsum(skb, ETH_HLEN); skb_reset_mac_header(skb); skb_reset_mac_len(skb); return 0; } EXPORT_SYMBOL(skb_eth_pop); /** * skb_eth_push() - Add a new Ethernet header at the head of a packet * * @skb: Socket buffer to modify * @dst: Destination MAC address of the new header * @src: Source MAC address of the new header * * Prepend @skb with a new Ethernet header. * * Expects that skb->data points to the mac header, which must be empty. * * Returns 0 on success, -errno otherwise. */ int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src) { struct ethhdr *eth; int err; if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) return -EPROTO; err = skb_cow_head(skb, sizeof(*eth)); if (err < 0) return err; skb_push(skb, sizeof(*eth)); skb_reset_mac_header(skb); skb_reset_mac_len(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_dest, dst); ether_addr_copy(eth->h_source, src); eth->h_proto = skb->protocol; skb_postpush_rcsum(skb, eth, sizeof(*eth)); return 0; } EXPORT_SYMBOL(skb_eth_push); /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { if (skb->ip_summed == CHECKSUM_COMPLETE) { __be16 diff[] = { ~hdr->h_proto, ethertype }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } hdr->h_proto = ethertype; } /** * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is * ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; if (unlikely(!eth_p_mpls(mpls_proto))) return -EINVAL; /* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) return -EINVAL; err = skb_cow_head(skb, MPLS_HLEN); if (unlikely(err)) return err; if (!skb->inner_protocol) { skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_push); /** * skb_mpls_pop() - pop the outermost MPLS header * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return 0; err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN); skb_mod_eth_type(skb, hdr, next_proto); } skb->protocol = next_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); /** * skb_mpls_update_lse() - modify outermost MPLS header and update csum * * @skb: buffer * @mpls_lse: new MPLS label stack entry to update to * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } mpls_hdr(skb)->label_stack_entry = mpls_lse; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_update_lse); /** * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header * * @skb: buffer * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_dec_ttl(struct sk_buff *skb) { u32 lse; u8 ttl; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) return -ENOMEM; lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) return -EINVAL; lse &= ~MPLS_LS_TTL_MASK; lse |= ttl << MPLS_LS_TTL_SHIFT; return skb_mpls_update_lse(skb, cpu_to_be32(lse)); } EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl); /** * alloc_skb_with_frags - allocate skb with page frags * * @header_len: size of linear part * @data_len: needed length in frags * @max_page_order: max page order desired. * @errcode: pointer to error code if any * @gfp_mask: allocation mask * * This can be used to allocate a paged skb, given a maximal order for frags. */ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask) { int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; unsigned long chunk; struct sk_buff *skb; struct page *page; int i; *errcode = -EMSGSIZE; /* Note this test could be relaxed, if we succeed to allocate * high order pages... */ if (npages > MAX_SKB_FRAGS) return NULL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; skb->truesize += npages << PAGE_SHIFT; for (i = 0; npages > 0; i++) { int order = max_page_order; while (order) { if (npages >= 1 << order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN, order); if (page) goto fill_page; /* Do not retry other high order allocations */ order = 1; max_page_order = 0; } order--; } page = alloc_page(gfp_mask); if (!page) goto failure; fill_page: chunk = min_t(unsigned long, data_len, PAGE_SIZE << order); skb_fill_page_desc(skb, i, page, 0, chunk); data_len -= chunk; npages -= 1 << order; } return skb; failure: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(alloc_skb_with_frags); /* carve out the first off bytes from skb when off < headlen */ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { int i; int size = skb_end_offset(skb); int new_hlen = headlen - off; u8 *data; size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy real data, and all frags */ skb_copy_from_linear_data_offset(skb, off, data, new_hlen); skb->len -= off; memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb); } else { /* we can reuse existing recount- all we did was * relocate values */ skb_free_head(skb); } skb->head = data; skb->data = data; skb->head_frag = 0; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; #else skb->end = skb->head + size; #endif skb_set_tail_pointer(skb, skb_headlen(skb)); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp); /* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve() */ static int pskb_carve_frag_list(struct sk_buff *skb, struct skb_shared_info *shinfo, int eat, gfp_t gfp_mask) { struct sk_buff *list = shinfo->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (!list) { pr_err("Not enough bytes to eat. Want %d\n", eat); return -EFAULT; } if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_shared(list)) { clone = skb_clone(list, gfp_mask); if (!clone) return -ENOMEM; insp = list->next; list = clone; } else { /* This may be pulled without problems. */ insp = list; } if (pskb_carve(list, eat, gfp_mask) < 0) { kfree_skb(clone); return -ENOMEM; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; shinfo->frag_list = clone; } return 0; } /* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb */ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { int i, k = 0; int size = skb_end_offset(skb); u8 *data; const int nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo; size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(ksize(data)); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); for (i = 0; i < nfrags; i++) { int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + fsize > off) { shinfo->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < off) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); k++; } pos += fsize; } shinfo->nr_frags = k; if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); /* split line is in frag list */ if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); kfree(data); return -ENOMEM; } skb_release_data(skb); skb->head = data; skb->head_frag = 0; skb->data = data; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; #else skb->end = skb->head + size; #endif skb_reset_tail_pointer(skb); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; skb->len -= off; skb->data_len = skb->len; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } /* remove len bytes from the beginning of the skb */ static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp) { int headlen = skb_headlen(skb); if (len < headlen) return pskb_carve_inside_header(skb, len, headlen, gfp); else return pskb_carve_inside_nonlinear(skb, len, headlen, gfp); } /* Extract to_copy bytes starting at off from skb, and return this in * a new skb */ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp) { struct sk_buff *clone = skb_clone(skb, gfp); if (!clone) return NULL; if (pskb_carve(clone, off, gfp) < 0 || pskb_trim(clone, to_copy)) { kfree_skb(clone); return NULL; } return clone; } EXPORT_SYMBOL(pskb_extract); /** * skb_condense - try to get rid of fragments/frag_list if possible * @skb: buffer * * Can be used to save memory before skb is added to a busy queue. * If packet has bytes in frags and enough tail room in skb->head, * pull all of them, so that we can free the frags right now and adjust * truesize. * Notes: * We do not reallocate skb->head thus can not fail. * Caller must re-evaluate skb->truesize if needed. */ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || skb_cloned(skb)) return; /* Nice, we can free page frag(s) right now */ __pskb_pull_tail(skb, skb->data_len); } /* At this point, skb->truesize might be over estimated, * because skb had a fragment, and fragments do not tell * their truesize. * When we pulled its content into skb->head, fragment * was freed, but __pskb_pull_tail() could not possibly * adjust skb->truesize, not knowing the frag truesize. */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) { return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } /** * __skb_ext_alloc - allocate a new skb extensions storage * * @flags: See kmalloc(). * * Returns the newly allocated pointer. The pointer can later attached to a * skb via __skb_ext_set(). * Note: caller must handle the skb_ext as an opaque data. */ struct skb_ext *__skb_ext_alloc(gfp_t flags) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags); if (new) { memset(new->offset, 0, sizeof(new->offset)); refcount_set(&new->refcnt, 1); } return new; } static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, unsigned int old_active) { struct skb_ext *new; if (refcount_read(&old->refcnt) == 1) return old; new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); if (!new) return NULL; memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE); refcount_set(&new->refcnt, 1); #ifdef CONFIG_XFRM if (old_active & (1 << SKB_EXT_SEC_PATH)) { struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH); unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } #endif __skb_ext_put(old); return new; } /** * __skb_ext_set - attach the specified extension storage to this skb * @skb: buffer * @id: extension id * @ext: extension storage previously allocated via __skb_ext_alloc() * * Existing extensions, if any, are cleared. * * Returns the pointer to the extension. */ void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext) { unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); skb_ext_put(skb); newlen = newoff + skb_ext_type_len[id]; ext->chunks = newlen; ext->offset[id] = newoff; skb->extensions = ext; skb->active_extensions = 1 << id; return skb_ext_get_ptr(ext, id); } /** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for * * Allocates enough space for the given extension. * If the extension is already present, a pointer to that extension * is returned. * * If the skb was cloned, COW applies and the returned memory can be * modified without changing the extension space of clones buffers. * * Returns pointer to the extension or NULL on allocation failure. */ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *new, *old = NULL; unsigned int newlen, newoff; if (skb->active_extensions) { old = skb->extensions; new = skb_ext_maybe_cow(old, skb->active_extensions); if (!new) return NULL; if (__skb_ext_exist(new, id)) goto set_active; newoff = new->chunks; } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); new = __skb_ext_alloc(GFP_ATOMIC); if (!new) return NULL; } newlen = newoff + skb_ext_type_len[id]; new->chunks = newlen; new->offset[id] = newoff; set_active: skb->extensions = new; skb->active_extensions |= 1 << id; return skb_ext_get_ptr(new, id); } EXPORT_SYMBOL(skb_ext_add); #ifdef CONFIG_XFRM static void skb_ext_put_sp(struct sec_path *sp) { unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_put(sp->xvec[i]); } #endif void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *ext = skb->extensions; skb->active_extensions &= ~(1 << id); if (skb->active_extensions == 0) { skb->extensions = NULL; __skb_ext_put(ext); #ifdef CONFIG_XFRM } else if (id == SKB_EXT_SEC_PATH && refcount_read(&ext->refcnt) == 1) { struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH); skb_ext_put_sp(sp); sp->len = 0; #endif } } EXPORT_SYMBOL(__skb_ext_del); void __skb_ext_put(struct skb_ext *ext) { /* If this is last clone, nothing can increment * it after check passes. Avoids one atomic op. */ if (refcount_read(&ext->refcnt) == 1) goto free_now; if (!refcount_dec_and_test(&ext->refcnt)) return; free_now: #ifdef CONFIG_XFRM if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH)) skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif kmem_cache_free(skbuff_ext_cache, ext); } EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLY__ #include <asm/nospec-branch.h> /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __section(".cpuidle.text") /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern __always_inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : "=rm" (flags) : /* no input */ : "memory"); return flags; } extern inline void native_restore_fl(unsigned long flags); extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ :"g" (flags) :"memory", "cc"); } static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static __always_inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static inline __cpuidle void native_safe_halt(void) { x86_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { x86_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } #endif #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline unsigned long arch_local_save_flags(void) { return native_save_fl(); } static __always_inline void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); } static __always_inline void arch_local_irq_enable(void) { native_irq_enable(); } /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static inline __cpuidle void halt(void) { native_halt(); } /* * For spinlocks, etc: */ static __always_inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(x) pushfq; popq %rax #endif #define INTERRUPT_RETURN jmp native_iret #else #define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static __always_inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } #else #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV #else #define SWAPGS swapgs #endif #endif #endif /* !__ASSEMBLY__ */ #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /** * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses * this_cpu_add which is irq-safe by definition. Hence there is no need muck * with irq state before calling this one */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; preempt_disable(); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock_irqrestore(&fbc->lock, flags); } else { this_cpu_add(*fbc->counters, amount); } preempt_enable(); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { unsigned long flags __maybe_unused; raw_spin_lock_init(&fbc->lock); lockdep_set_class(&fbc->lock, key); fbc->count = amount; fbc->counters = alloc_percpu_gfp(s32, gfp); if (!fbc->counters) return -ENOMEM; debug_percpu_counter_activate(fbc); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc->list); spin_lock_irqsave(&percpu_counters_lock, flags); list_add(&fbc->list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init); void percpu_counter_destroy(struct percpu_counter *fbc) { unsigned long flags __maybe_unused; if (!fbc->counters) return; debug_percpu_counter_deactivate(fbc); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); list_del(&fbc->list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc->counters); fbc->counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/block_dev.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE */ #include <linux/init.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/major.h> #include <linux/device_cgroup.h> #include <linux/highmem.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/module.h> #include <linux/blkpg.h> #include <linux/magic.h> #include <linux/buffer_head.h> #include <linux/swap.h> #include <linux/pagevec.h> #include <linux/writeback.h> #include <linux/mpage.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> #include <linux/task_io_accounting_ops.h> #include <linux/falloc.h> #include <linux/uaccess.h> #include <linux/suspend.h> #include "internal.h" struct bdev_inode { struct block_device bdev; struct inode vfs_inode; }; static const struct address_space_operations def_blk_aops; static inline struct bdev_inode *BDEV_I(struct inode *inode) { return container_of(inode, struct bdev_inode, vfs_inode); } struct block_device *I_BDEV(struct inode *inode) { return &BDEV_I(inode)->bdev; } EXPORT_SYMBOL(I_BDEV); static void bdev_write_inode(struct block_device *bdev) { struct inode *inode = bdev->bd_inode; int ret; spin_lock(&inode->i_lock); while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); ret = write_inode_now(inode, true); if (ret) { char name[BDEVNAME_SIZE]; pr_warn_ratelimited("VFS: Dirty inode writeback failed " "for block device %s (err=%d).\n", bdevname(bdev, name), ret); } spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); } /* Kill _all_ buffers and pagecache , dirty or not.. */ static void kill_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) return; invalidate_bh_lrus(); truncate_inode_pages(mapping, 0); } /* Invalidate clean unused buffers and pagecache. */ void invalidate_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; if (mapping->nrpages) { invalidate_bh_lrus(); lru_add_drain_all(); /* make sure all lru add caches are flushed */ invalidate_mapping_pages(mapping, 0, -1); } /* 99% of the time, we don't need to flush the cleancache on the bdev. * But, for the strange corners, lets be cautious */ cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(invalidate_bdev); /* * Drop all buffers & page cache for given bdev range. This function bails * with error if bdev has other exclusive owner (such as filesystem). */ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend) { struct block_device *claimed_bdev = NULL; int err; /* * If we don't hold exclusive handle for the device, upgrade to it * while we discard the buffer cache to avoid discarding buffers * under live filesystem. */ if (!(mode & FMODE_EXCL)) { claimed_bdev = bdev->bd_contains; err = bd_prepare_to_claim(bdev, claimed_bdev, truncate_bdev_range); if (err) goto invalidate; } truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); if (claimed_bdev) bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range); return 0; invalidate: /* * Someone else has handle exclusively open. Try invalidating instead. * The 'end' argument is inclusive so the rounding is safe. */ return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, lstart >> PAGE_SHIFT, lend >> PAGE_SHIFT); } EXPORT_SYMBOL(truncate_bdev_range); static void set_init_blocksize(struct block_device *bdev) { unsigned int bsize = bdev_logical_block_size(bdev); loff_t size = i_size_read(bdev->bd_inode); while (bsize < PAGE_SIZE) { if (size & bsize) break; bsize <<= 1; } bdev->bd_inode->i_blkbits = blksize_bits(bsize); } int set_blocksize(struct block_device *bdev, int size) { /* Size must be a power of two, and between 512 and PAGE_SIZE */ if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ if (size < bdev_logical_block_size(bdev)) return -EINVAL; /* Don't change the size if it is same as current */ if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { sync_blockdev(bdev); bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } return 0; } EXPORT_SYMBOL(set_blocksize); int sb_set_blocksize(struct super_block *sb, int size) { if (set_blocksize(sb->s_bdev, size)) return 0; /* If we get here, we know size is power of two * and it's value is between 512 and PAGE_SIZE */ sb->s_blocksize = size; sb->s_blocksize_bits = blksize_bits(size); return sb->s_blocksize; } EXPORT_SYMBOL(sb_set_blocksize); int sb_min_blocksize(struct super_block *sb, int size) { int minsize = bdev_logical_block_size(sb->s_bdev); if (size < minsize) size = minsize; return sb_set_blocksize(sb, size); } EXPORT_SYMBOL(sb_min_blocksize); static int blkdev_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { bh->b_bdev = I_BDEV(inode); bh->b_blocknr = iblock; set_buffer_mapped(bh); return 0; } static struct inode *bdev_file_inode(struct file *file) { return file->f_mapping->host; } static unsigned int dio_bio_write_op(struct kiocb *iocb) { unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; /* avoid the need for a I/O completion work item */ if (iocb->ki_flags & IOCB_DSYNC) op |= REQ_FUA; return op; } #define DIO_INLINE_BIO_VECS 4 static void blkdev_bio_end_io_simple(struct bio *bio) { struct task_struct *waiter = bio->bi_private; WRITE_ONCE(bio->bi_private, NULL); blk_wake_io_task(waiter); } static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) { struct file *file = iocb->ki_filp; struct block_device *bdev = I_BDEV(bdev_file_inode(file)); struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs; loff_t pos = iocb->ki_pos; bool should_dirty = false; struct bio bio; ssize_t ret; blk_qc_t qc; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; if (nr_pages <= DIO_INLINE_BIO_VECS) vecs = inline_vecs; else { vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec), GFP_KERNEL); if (!vecs) return -ENOMEM; } bio_init(&bio, vecs, nr_pages); bio_set_dev(&bio, bdev); bio.bi_iter.bi_sector = pos >> 9; bio.bi_write_hint = iocb->ki_hint; bio.bi_private = current; bio.bi_end_io = blkdev_bio_end_io_simple; bio.bi_ioprio = iocb->ki_ioprio; ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) goto out; ret = bio.bi_iter.bi_size; if (iov_iter_rw(iter) == READ) { bio.bi_opf = REQ_OP_READ; if (iter_is_iovec(iter)) should_dirty = true; } else { bio.bi_opf = dio_bio_write_op(iocb); task_io_account_write(ret); } if (iocb->ki_flags & IOCB_NOWAIT) bio.bi_opf |= REQ_NOWAIT; if (iocb->ki_flags & IOCB_HIPRI) bio_set_polled(&bio, iocb); qc = submit_bio(&bio); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(bio.bi_private)) break; if (!(iocb->ki_flags & IOCB_HIPRI) || !blk_poll(bdev_get_queue(bdev), qc, true)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); bio_release_pages(&bio, should_dirty); if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); out: if (vecs != inline_vecs) kfree(vecs); bio_uninit(&bio); return ret; } struct blkdev_dio { union { struct kiocb *iocb; struct task_struct *waiter; }; size_t size; atomic_t ref; bool multi_bio : 1; bool should_dirty : 1; bool is_sync : 1; struct bio bio; }; static struct bio_set blkdev_dio_pool; static int blkdev_iopoll(struct kiocb *kiocb, bool wait) { struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host); struct request_queue *q = bdev_get_queue(bdev); return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait); } static void blkdev_bio_end_io(struct bio *bio) { struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->should_dirty; if (bio->bi_status && !dio->bio.bi_status) dio->bio.bi_status = bio->bi_status; if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret; if (likely(!dio->bio.bi_status)) { ret = dio->size; iocb->ki_pos += ret; } else { ret = blk_status_to_errno(dio->bio.bi_status); } dio->iocb->ki_complete(iocb, ret, 0); if (dio->multi_bio) bio_put(&dio->bio); } else { struct task_struct *waiter = dio->waiter; WRITE_ONCE(dio->waiter, NULL); blk_wake_io_task(waiter); } } if (should_dirty) { bio_check_pages_dirty(bio); } else { bio_release_pages(bio, false); bio_put(bio); } } static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) { struct file *file = iocb->ki_filp; struct inode *inode = bdev_file_inode(file); struct block_device *bdev = I_BDEV(inode); struct blk_plug plug; struct blkdev_dio *dio; struct bio *bio; bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; bool is_read = (iov_iter_rw(iter) == READ), is_sync; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; int ret = 0; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool); dio = container_of(bio, struct blkdev_dio, bio); dio->is_sync = is_sync = is_sync_kiocb(iocb); if (dio->is_sync) { dio->waiter = current; bio_get(bio); } else { dio->iocb = iocb; } dio->size = 0; dio->multi_bio = false; dio->should_dirty = is_read && iter_is_iovec(iter); /* * Don't plug for HIPRI/polled IO, as those should go straight * to issue */ if (!is_poll) blk_start_plug(&plug); for (;;) { bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; bio->bi_write_hint = iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; ret = bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; } if (is_read) { bio->bi_opf = REQ_OP_READ; if (dio->should_dirty) bio_set_pages_dirty(bio); } else { bio->bi_opf = dio_bio_write_op(iocb); task_io_account_write(bio->bi_iter.bi_size); } if (iocb->ki_flags & IOCB_NOWAIT) bio->bi_opf |= REQ_NOWAIT; dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES); if (!nr_pages) { bool polled = false; if (iocb->ki_flags & IOCB_HIPRI) { bio_set_polled(bio, iocb); polled = true; } qc = submit_bio(bio); if (polled) WRITE_ONCE(iocb->ki_cookie, qc); break; } if (!dio->multi_bio) { /* * AIO needs an extra reference to ensure the dio * structure which is embedded into the first bio * stays around. */ if (!is_sync) bio_get(bio); dio->multi_bio = true; atomic_set(&dio->ref, 2); } else { atomic_inc(&dio->ref); } submit_bio(bio); bio = bio_alloc(GFP_KERNEL, nr_pages); } if (!is_poll) blk_finish_plug(&plug); if (!is_sync) return -EIOCBQUEUED; for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(dio->waiter)) break; if (!(iocb->ki_flags & IOCB_HIPRI) || !blk_poll(bdev_get_queue(bdev), qc, true)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); if (!ret) ret = blk_status_to_errno(dio->bio.bi_status); if (likely(!ret)) ret = dio->size; bio_put(&dio->bio); return ret; } static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { int nr_pages; nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1); if (!nr_pages) return 0; if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES) return __blkdev_direct_IO_simple(iocb, iter, nr_pages); return __blkdev_direct_IO(iocb, iter, min(nr_pages, BIO_MAX_PAGES)); } static __init int blkdev_init(void) { return bioset_init(&blkdev_dio_pool, 4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS); } module_init(blkdev_init); int __sync_blockdev(struct block_device *bdev, int wait) { if (!bdev) return 0; if (!wait) return filemap_flush(bdev->bd_inode->i_mapping); return filemap_write_and_wait(bdev->bd_inode->i_mapping); } /* * Write out and wait upon all the dirty data associated with a block * device via its mapping. Does not take the superblock lock. */ int sync_blockdev(struct block_device *bdev) { return __sync_blockdev(bdev, 1); } EXPORT_SYMBOL(sync_blockdev); /* * Write out and wait upon all dirty data associated with this * device. Filesystem data as well as the underlying block * device. Takes the superblock lock. */ int fsync_bdev(struct block_device *bdev) { struct super_block *sb = get_super(bdev); if (sb) { int res = sync_filesystem(sb); drop_super(sb); return res; } return sync_blockdev(bdev); } EXPORT_SYMBOL(fsync_bdev); /** * freeze_bdev -- lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. * The reference counter (bd_fsfreeze_count) guarantees that only the last * unfreeze process can unfreeze the frozen filesystem actually when multiple * freeze requests arrive simultaneously. It counts up in freeze_bdev() and * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze * actually. */ struct super_block *freeze_bdev(struct block_device *bdev) { struct super_block *sb; int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); if (++bdev->bd_fsfreeze_count > 1) { /* * We don't even need to grab a reference - the first call * to freeze_bdev grab an active reference and only the last * thaw_bdev drops it. */ sb = get_super(bdev); if (sb) drop_super(sb); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } sb = get_active_super(bdev); if (!sb) goto out; if (sb->s_op->freeze_super) error = sb->s_op->freeze_super(sb); else error = freeze_super(sb); if (error) { deactivate_super(sb); bdev->bd_fsfreeze_count--; mutex_unlock(&bdev->bd_fsfreeze_mutex); return ERR_PTR(error); } deactivate_super(sb); out: sync_blockdev(bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; /* thaw_bdev releases s->s_umount */ } EXPORT_SYMBOL(freeze_bdev); /** * thaw_bdev -- unlock filesystem * @bdev: blockdevice to unlock * @sb: associated superblock * * Unlocks the filesystem and marks it writeable again after freeze_bdev(). */ int thaw_bdev(struct block_device *bdev, struct super_block *sb) { int error = -EINVAL; mutex_lock(&bdev->bd_fsfreeze_mutex); if (!bdev->bd_fsfreeze_count) goto out; error = 0; if (--bdev->bd_fsfreeze_count > 0) goto out; if (!sb) goto out; if (sb->s_op->thaw_super) error = sb->s_op->thaw_super(sb); else error = thaw_super(sb); if (error) bdev->bd_fsfreeze_count++; out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } EXPORT_SYMBOL(thaw_bdev); static int blkdev_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, blkdev_get_block, wbc); } static int blkdev_readpage(struct file * file, struct page * page) { return block_read_full_page(page, blkdev_get_block); } static void blkdev_readahead(struct readahead_control *rac) { mpage_readahead(rac, blkdev_get_block); } static int blkdev_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { return block_write_begin(mapping, pos, len, flags, pagep, blkdev_get_block); } static int blkdev_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { int ret; ret = block_write_end(file, mapping, pos, len, copied, page, fsdata); unlock_page(page); put_page(page); return ret; } /* * private llseek: * for a block special file file_inode(file)->i_size is zero * so we compute the size by hand (just as in block_read/write above) */ static loff_t block_llseek(struct file *file, loff_t offset, int whence) { struct inode *bd_inode = bdev_file_inode(file); loff_t retval; inode_lock(bd_inode); retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode)); inode_unlock(bd_inode); return retval; } int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *bd_inode = bdev_file_inode(filp); struct block_device *bdev = I_BDEV(bd_inode); int error; error = file_write_and_wait_range(filp, start, end); if (error) return error; /* * There is no need to serialise calls to blkdev_issue_flush with * i_mutex and doing so causes performance issues with concurrent * O_SYNC writers to a block device. */ error = blkdev_issue_flush(bdev, GFP_KERNEL); if (error == -EOPNOTSUPP) error = 0; return error; } EXPORT_SYMBOL(blkdev_fsync); /** * bdev_read_page() - Start reading a page from a block device * @bdev: The device to read the page from * @sector: The offset on the device to read the page to (need not be aligned) * @page: The page to read * * On entry, the page should be locked. It will be unlocked when the page * has been read. If the block driver implements rw_page synchronously, * that will be true on exit from this function, but it need not be. * * Errors returned by this function are usually "soft", eg out of memory, or * queue full; callers should try a different route to read this page rather * than propagate an error back up the stack. * * Return: negative errno if an error occurs, 0 if submission was successful. */ int bdev_read_page(struct block_device *bdev, sector_t sector, struct page *page) { const struct block_device_operations *ops = bdev->bd_disk->fops; int result = -EOPNOTSUPP; if (!ops->rw_page || bdev_get_integrity(bdev)) return result; result = blk_queue_enter(bdev->bd_disk->queue, 0); if (result) return result; result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, REQ_OP_READ); blk_queue_exit(bdev->bd_disk->queue); return result; } /** * bdev_write_page() - Start writing a page to a block device * @bdev: The device to write the page to * @sector: The offset on the device to write the page to (need not be aligned) * @page: The page to write * @wbc: The writeback_control for the write * * On entry, the page should be locked and not currently under writeback. * On exit, if the write started successfully, the page will be unlocked and * under writeback. If the write failed already (eg the driver failed to * queue the page to the device), the page will still be locked. If the * caller is a ->writepage implementation, it will need to unlock the page. * * Errors returned by this function are usually "soft", eg out of memory, or * queue full; callers should try a different route to write this page rather * than propagate an error back up the stack. * * Return: negative errno if an error occurs, 0 if submission was successful. */ int bdev_write_page(struct block_device *bdev, sector_t sector, struct page *page, struct writeback_control *wbc) { int result; const struct block_device_operations *ops = bdev->bd_disk->fops; if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; result = blk_queue_enter(bdev->bd_disk->queue, 0); if (result) return result; set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, REQ_OP_WRITE); if (result) { end_page_writeback(page); } else { clean_page_buffers(page); unlock_page(page); } blk_queue_exit(bdev->bd_disk->queue); return result; } /* * pseudo-fs */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock); static struct kmem_cache * bdev_cachep __read_mostly; static struct inode *bdev_alloc_inode(struct super_block *sb) { struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void bdev_free_inode(struct inode *inode) { kmem_cache_free(bdev_cachep, BDEV_I(inode)); } static void init_once(void *foo) { struct bdev_inode *ei = (struct bdev_inode *) foo; struct block_device *bdev = &ei->bdev; memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); #ifdef CONFIG_SYSFS INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif bdev->bd_bdi = &noop_backing_dev_info; inode_init_once(&ei->vfs_inode); /* Initialize mutex for freeze. */ mutex_init(&bdev->bd_fsfreeze_mutex); } static void bdev_evict_inode(struct inode *inode) { struct block_device *bdev = &BDEV_I(inode)->bdev; truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); /* Detach inode from wb early as bdi_put() may free bdi->wb */ inode_detach_wb(inode); if (bdev->bd_bdi != &noop_backing_dev_info) { bdi_put(bdev->bd_bdi); bdev->bd_bdi = &noop_backing_dev_info; } } static const struct super_operations bdev_sops = { .statfs = simple_statfs, .alloc_inode = bdev_alloc_inode, .free_inode = bdev_free_inode, .drop_inode = generic_delete_inode, .evict_inode = bdev_evict_inode, }; static int bd_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, BDEVFS_MAGIC); if (!ctx) return -ENOMEM; fc->s_iflags |= SB_I_CGROUPWB; ctx->ops = &bdev_sops; return 0; } static struct file_system_type bd_type = { .name = "bdev", .init_fs_context = bd_init_fs_context, .kill_sb = kill_anon_super, }; struct super_block *blockdev_superblock __read_mostly; EXPORT_SYMBOL_GPL(blockdev_superblock); void __init bdev_cache_init(void) { int err; static struct vfsmount *bd_mnt; bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), init_once); err = register_filesystem(&bd_type); if (err) panic("Cannot register bdev pseudo-fs"); bd_mnt = kern_mount(&bd_type); if (IS_ERR(bd_mnt)) panic("Cannot create bdev pseudo-fs"); blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ } /* * Most likely _very_ bad one - but then it's hardly critical for small * /dev and can be fixed when somebody will need really large one. * Keep in mind that it will be fed through icache hash function too. */ static inline unsigned long hash(dev_t dev) { return MAJOR(dev)+MINOR(dev); } static int bdev_test(struct inode *inode, void *data) { return BDEV_I(inode)->bdev.bd_dev == *(dev_t *)data; } static int bdev_set(struct inode *inode, void *data) { BDEV_I(inode)->bdev.bd_dev = *(dev_t *)data; return 0; } static struct block_device *bdget(dev_t dev) { struct block_device *bdev; struct inode *inode; inode = iget5_locked(blockdev_superblock, hash(dev), bdev_test, bdev_set, &dev); if (!inode) return NULL; bdev = &BDEV_I(inode)->bdev; if (inode->i_state & I_NEW) { spin_lock_init(&bdev->bd_size_lock); bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; bdev->bd_part_count = 0; inode->i_mode = S_IFBLK; inode->i_rdev = dev; inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); unlock_new_inode(inode); } return bdev; } /** * bdgrab -- Grab a reference to an already referenced block device * @bdev: Block device to grab a reference to. */ struct block_device *bdgrab(struct block_device *bdev) { ihold(bdev->bd_inode); return bdev; } EXPORT_SYMBOL(bdgrab); struct block_device *bdget_part(struct hd_struct *part) { return bdget(part_devt(part)); } long nr_blockdev_pages(void) { struct inode *inode; long ret = 0; spin_lock(&blockdev_superblock->s_inode_list_lock); list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) ret += inode->i_mapping->nrpages; spin_unlock(&blockdev_superblock->s_inode_list_lock); return ret; } void bdput(struct block_device *bdev) { iput(bdev->bd_inode); } EXPORT_SYMBOL(bdput); static struct block_device *bd_acquire(struct inode *inode) { struct block_device *bdev; spin_lock(&bdev_lock); bdev = inode->i_bdev; if (bdev && !inode_unhashed(bdev->bd_inode)) { bdgrab(bdev); spin_unlock(&bdev_lock); return bdev; } spin_unlock(&bdev_lock); /* * i_bdev references block device inode that was already shut down * (corresponding device got removed). Remove the reference and look * up block device inode again just in case new device got * reestablished under the same device number. */ if (bdev) bd_forget(inode); bdev = bdget(inode->i_rdev); if (bdev) { spin_lock(&bdev_lock); if (!inode->i_bdev) { /* * We take an additional reference to bd_inode, * and it's released in clear_inode() of inode. * So, we can access it via ->i_mapping always * without igrab(). */ bdgrab(bdev); inode->i_bdev = bdev; inode->i_mapping = bdev->bd_inode->i_mapping; } spin_unlock(&bdev_lock); } return bdev; } /* Call when you free inode */ void bd_forget(struct inode *inode) { struct block_device *bdev = NULL; spin_lock(&bdev_lock); if (!sb_is_blkdev_sb(inode->i_sb)) bdev = inode->i_bdev; inode->i_bdev = NULL; inode->i_mapping = &inode->i_data; spin_unlock(&bdev_lock); if (bdev) bdput(bdev); } /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest * @whole: whole block device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * * Test whether @bdev can be claimed by @holder. * * CONTEXT: * spin_lock(&bdev_lock). * * RETURNS: * %true if @bdev can be claimed, %false otherwise. */ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, void *holder) { if (bdev->bd_holder == holder) return true; /* already a holder */ else if (bdev->bd_holder != NULL) return false; /* held by someone else */ else if (whole == bdev) return true; /* is a whole device which isn't held */ else if (whole->bd_holder == bd_may_claim) return true; /* is a partition of a device that is being partitioned */ else if (whole->bd_holder != NULL) return false; /* is a partition of a held device */ else return true; /* is a partition of an un-held device */ } /** * bd_prepare_to_claim - claim a block device * @bdev: block device of interest * @whole: the whole device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * * Claim @bdev. This function fails if @bdev is already claimed by another * holder and waits if another claiming is in progress. return, the caller * has ownership of bd_claiming and bd_holder[s]. * * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, void *holder) { retry: spin_lock(&bdev_lock); /* if someone else claimed, fail */ if (!bd_may_claim(bdev, whole, holder)) { spin_unlock(&bdev_lock); return -EBUSY; } /* if claiming is already in progress, wait for it to finish */ if (whole->bd_claiming) { wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); DEFINE_WAIT(wait); prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); goto retry; } /* yay, all mine */ whole->bd_claiming = holder; spin_unlock(&bdev_lock); return 0; } EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) { struct gendisk *disk = get_gendisk(bdev->bd_dev, partno); if (!disk) return NULL; /* * Now that we hold gendisk reference we make sure bdev we looked up is * not stale. If it is, it means device got removed and created before * we looked up gendisk and we fail open in such case. Associating * unhashed bdev with newly created gendisk could lead to two bdevs * (and thus two independent caches) being associated with one device * which is bad. */ if (inode_unhashed(bdev->bd_inode)) { put_disk_and_module(disk); return NULL; } return disk; } static void bd_clear_claiming(struct block_device *whole, void *holder) { lockdep_assert_held(&bdev_lock); /* tell others that we're done */ BUG_ON(whole->bd_claiming != holder); whole->bd_claiming = NULL; wake_up_bit(&whole->bd_claiming, 0); } /** * bd_finish_claiming - finish claiming of a block device * @bdev: block device of interest * @whole: whole block device * @holder: holder that has claimed @bdev * * Finish exclusive open of a block device. Mark the device as exlusively * open by the holder and wake up all waiters for exclusive open to finish. */ static void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, void *holder) { spin_lock(&bdev_lock); BUG_ON(!bd_may_claim(bdev, whole, holder)); /* * Note that for a whole device bd_holders will be incremented twice, * and bd_holder will be set to bd_may_claim before being set to holder */ whole->bd_holders++; whole->bd_holder = bd_may_claim; bdev->bd_holders++; bdev->bd_holder = holder; bd_clear_claiming(whole, holder); spin_unlock(&bdev_lock); } /** * bd_abort_claiming - abort claiming of a block device * @bdev: block device of interest * @whole: whole block device * @holder: holder that has claimed @bdev * * Abort claiming of a block device when the exclusive open failed. This can be * also used when exclusive open is not actually desired and we just needed * to block other exclusive openers for a while. */ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder) { spin_lock(&bdev_lock); bd_clear_claiming(whole, holder); spin_unlock(&bdev_lock); } EXPORT_SYMBOL(bd_abort_claiming); #ifdef CONFIG_SYSFS struct bd_holder_disk { struct list_head list; struct gendisk *disk; int refcnt; }; static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; list_for_each_entry(holder, &bdev->bd_holder_disks, list) if (holder->disk == disk) return holder; return NULL; } static int add_symlink(struct kobject *from, struct kobject *to) { return sysfs_create_link(from, to, kobject_name(to)); } static void del_symlink(struct kobject *from, struct kobject *to) { sysfs_remove_link(from, kobject_name(to)); } /** * bd_link_disk_holder - create symlinks between holding disk and slave bdev * @bdev: the claimed slave bdev * @disk: the holding disk * * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. * * This functions creates the following sysfs symlinks. * * - from "slaves" directory of the holder @disk to the claimed @bdev * - from "holders" directory of the @bdev to the holder @disk * * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is * passed to bd_link_disk_holder(), then: * * /sys/block/dm-0/slaves/sda --> /sys/block/sda * /sys/block/sda/holders/dm-0 --> /sys/block/dm-0 * * The caller must have claimed @bdev before calling this function and * ensure that both @bdev and @disk are valid during the creation and * lifetime of these symlinks. * * CONTEXT: * Might sleep. * * RETURNS: * 0 on success, -errno on failure. */ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; int ret = 0; mutex_lock(&bdev->bd_mutex); WARN_ON_ONCE(!bdev->bd_holder); /* FIXME: remove the following once add_disk() handles errors */ if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir)) goto out_unlock; holder = bd_find_holder_disk(bdev, disk); if (holder) { holder->refcnt++; goto out_unlock; } holder = kzalloc(sizeof(*holder), GFP_KERNEL); if (!holder) { ret = -ENOMEM; goto out_unlock; } INIT_LIST_HEAD(&holder->list); holder->disk = disk; holder->refcnt = 1; ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); if (ret) goto out_free; ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); if (ret) goto out_del; /* * bdev could be deleted beneath us which would implicitly destroy * the holder directory. Hold on to it. */ kobject_get(bdev->bd_part->holder_dir); list_add(&holder->list, &bdev->bd_holder_disks); goto out_unlock; out_del: del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); out_free: kfree(holder); out_unlock: mutex_unlock(&bdev->bd_mutex); return ret; } EXPORT_SYMBOL_GPL(bd_link_disk_holder); /** * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() * @bdev: the calimed slave bdev * @disk: the holding disk * * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. * * CONTEXT: * Might sleep. */ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; mutex_lock(&bdev->bd_mutex); holder = bd_find_holder_disk(bdev, disk); if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); kobject_put(bdev->bd_part->holder_dir); list_del_init(&holder->list); kfree(holder); } mutex_unlock(&bdev->bd_mutex); } EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif /** * check_disk_size_change - checks for disk size change and adjusts bdev size. * @disk: struct gendisk to check * @bdev: struct bdev to adjust. * @verbose: if %true log a message about a size change if there is any * * This routine checks to see if the bdev size does not match the disk size * and adjusts it if it differs. When shrinking the bdev size, its all caches * are freed. */ static void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, bool verbose) { loff_t disk_size, bdev_size; spin_lock(&bdev->bd_size_lock); disk_size = (loff_t)get_capacity(disk) << 9; bdev_size = i_size_read(bdev->bd_inode); if (disk_size != bdev_size) { if (verbose) { printk(KERN_INFO "%s: detected capacity change from %lld to %lld\n", disk->disk_name, bdev_size, disk_size); } i_size_write(bdev->bd_inode, disk_size); } spin_unlock(&bdev->bd_size_lock); if (bdev_size > disk_size) { if (__invalidate_device(bdev, false)) pr_warn("VFS: busy inodes on resized disk %s\n", disk->disk_name); } } /** * revalidate_disk_size - checks for disk size change and adjusts bdev size. * @disk: struct gendisk to check * @verbose: if %true log a message about a size change if there is any * * This routine checks to see if the bdev size does not match the disk size * and adjusts it if it differs. When shrinking the bdev size, its all caches * are freed. */ void revalidate_disk_size(struct gendisk *disk, bool verbose) { struct block_device *bdev; /* * Hidden disks don't have associated bdev so there's no point in * revalidating them. */ if (disk->flags & GENHD_FL_HIDDEN) return; bdev = bdget_disk(disk, 0); if (bdev) { check_disk_size_change(disk, bdev, verbose); bdput(bdev); } } EXPORT_SYMBOL(revalidate_disk_size); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors) { spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); spin_unlock(&bdev->bd_size_lock); } EXPORT_SYMBOL(bd_set_nr_sectors); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); int bdev_disk_changed(struct block_device *bdev, bool invalidate) { struct gendisk *disk = bdev->bd_disk; int ret; lockdep_assert_held(&bdev->bd_mutex); if (!(disk->flags & GENHD_FL_UP)) return -ENXIO; rescan: ret = blk_drop_partitions(bdev); if (ret) return ret; clear_bit(GD_NEED_PART_SCAN, &disk->state); /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). * Doing that is rather inconsistent, but changing it broke legacy * udisks polling for legacy ide-cdrom devices. Use the crude check * below to get the sane behavior for most device while not breaking * userspace for this particular setup. */ if (invalidate) { if (disk_part_scan_enabled(disk) || !(disk->flags & GENHD_FL_REMOVABLE)) set_capacity(disk, 0); } else { if (disk->fops->revalidate_disk) disk->fops->revalidate_disk(disk); } check_disk_size_change(disk, bdev, !invalidate); if (get_capacity(disk)) { ret = blk_add_partitions(disk, bdev); if (ret == -EAGAIN) goto rescan; } else if (invalidate) { /* * Tell userspace that the media / partition table may have * changed. */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); } return ret; } /* * Only exported for for loop and dasd for historic reasons. Don't use in new * code! */ EXPORT_SYMBOL_GPL(bdev_disk_changed); /* * bd_mutex locking: * * mutex_lock(part->bd_mutex) * mutex_lock_nested(whole->bd_mutex, 1) */ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, int for_part) { struct block_device *whole = NULL, *claiming = NULL; struct gendisk *disk; int ret; int partno; bool first_open = false, unblock_events = true, need_restart; restart: need_restart = false; ret = -ENXIO; disk = bdev_get_gendisk(bdev, &partno); if (!disk) goto out; if (partno) { whole = bdget_disk(disk, 0); if (!whole) { ret = -ENOMEM; goto out_put_disk; } } if (!for_part && (mode & FMODE_EXCL)) { WARN_ON_ONCE(!holder); if (whole) claiming = whole; else claiming = bdev; ret = bd_prepare_to_claim(bdev, claiming, holder); if (ret) goto out_put_whole; } disk_block_events(disk); mutex_lock_nested(&bdev->bd_mutex, for_part); if (!bdev->bd_openers) { first_open = true; bdev->bd_disk = disk; bdev->bd_contains = bdev; bdev->bd_partno = partno; if (!partno) { ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); if (!bdev->bd_part) goto out_clear; ret = 0; if (disk->fops->open) { ret = disk->fops->open(bdev, mode); /* * If we lost a race with 'disk' being deleted, * try again. See md.c */ if (ret == -ERESTARTSYS) need_restart = true; } if (!ret) { bd_set_nr_sectors(bdev, get_capacity(disk)); set_init_blocksize(bdev); } /* * If the device is invalidated, rescan partition * if open succeeded or failed with -ENOMEDIUM. * The latter is necessary to prevent ghost * partitions on a removed medium. */ if (test_bit(GD_NEED_PART_SCAN, &disk->state) && (!ret || ret == -ENOMEDIUM)) bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_clear; } else { BUG_ON(for_part); ret = __blkdev_get(whole, mode, NULL, 1); if (ret) goto out_clear; bdev->bd_contains = bdgrab(whole); bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || !bdev->bd_part || !bdev->bd_part->nr_sects) { ret = -ENXIO; goto out_clear; } bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects); set_init_blocksize(bdev); } if (bdev->bd_bdi == &noop_backing_dev_info) bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); } else { if (bdev->bd_contains == bdev) { ret = 0; if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ if (test_bit(GD_NEED_PART_SCAN, &disk->state) && (!ret || ret == -ENOMEDIUM)) bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_unlock_bdev; } } bdev->bd_openers++; if (for_part) bdev->bd_part_count++; if (claiming) bd_finish_claiming(bdev, claiming, holder); /* * Block event polling for write claims if requested. Any write holder * makes the write_holder state stick until all are released. This is * good enough and tracking individual writeable reference is too * fragile given the way @mode is used in blkdev_get/put(). */ if (claiming && (mode & FMODE_WRITE) && !bdev->bd_write_holder && (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { bdev->bd_write_holder = true; unblock_events = false; } mutex_unlock(&bdev->bd_mutex); if (unblock_events) disk_unblock_events(disk); /* only one opener holds refs to the module and disk */ if (!first_open) put_disk_and_module(disk); if (whole) bdput(whole); return 0; out_clear: disk_put_part(bdev->bd_part); bdev->bd_disk = NULL; bdev->bd_part = NULL; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; out_unlock_bdev: if (claiming) bd_abort_claiming(bdev, claiming, holder); mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); out_put_whole: if (whole) bdput(whole); out_put_disk: put_disk_and_module(disk); if (need_restart) goto restart; out: return ret; } /** * blkdev_get - open a block device * @bdev: block_device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * * Open @bdev with @mode. If @mode includes %FMODE_EXCL, @bdev is * open with exclusive access. Specifying %FMODE_EXCL with %NULL * @holder is invalid. Exclusive opens may nest for the same @holder. * * On success, the reference count of @bdev is unchanged. On failure, * @bdev is put. * * CONTEXT: * Might sleep. * * RETURNS: * 0 on success, -errno on failure. */ static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) { int ret, perm = 0; if (mode & FMODE_READ) perm |= MAY_READ; if (mode & FMODE_WRITE) perm |= MAY_WRITE; ret = devcgroup_inode_permission(bdev->bd_inode, perm); if (ret) goto bdput; ret =__blkdev_get(bdev, mode, holder, 0); if (ret) goto bdput; return 0; bdput: bdput(bdev); return ret; } /** * blkdev_get_by_path - open a block device by name * @path: path to the block device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * * Open the blockdevice described by the device file at @path. @mode * and @holder are identical to blkdev_get(). * * On success, the returned block_device has reference count of one. * * CONTEXT: * Might sleep. * * RETURNS: * Pointer to block_device on success, ERR_PTR(-errno) on failure. */ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder) { struct block_device *bdev; int err; bdev = lookup_bdev(path); if (IS_ERR(bdev)) return bdev; err = blkdev_get(bdev, mode, holder); if (err) return ERR_PTR(err); if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) { blkdev_put(bdev, mode); return ERR_PTR(-EACCES); } return bdev; } EXPORT_SYMBOL(blkdev_get_by_path); /** * blkdev_get_by_dev - open a block device by device number * @dev: device number of block device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * * Open the blockdevice described by device number @dev. @mode and * @holder are identical to blkdev_get(). * * Use it ONLY if you really do not have anything better - i.e. when * you are behind a truly sucky interface and all you are given is a * device number. _Never_ to be used for internal purposes. If you * ever need it - reconsider your API. * * On success, the returned block_device has reference count of one. * * CONTEXT: * Might sleep. * * RETURNS: * Pointer to block_device on success, ERR_PTR(-errno) on failure. */ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) { struct block_device *bdev; int err; bdev = bdget(dev); if (!bdev) return ERR_PTR(-ENOMEM); err = blkdev_get(bdev, mode, holder); if (err) return ERR_PTR(err); return bdev; } EXPORT_SYMBOL(blkdev_get_by_dev); static int blkdev_open(struct inode * inode, struct file * filp) { struct block_device *bdev; /* * Preserve backwards compatibility and allow large file access * even if userspace doesn't ask for it explicitly. Some mkfs * binary needs it. We might want to drop this workaround * during an unstable branch. */ filp->f_flags |= O_LARGEFILE; filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; if (filp->f_flags & O_NDELAY) filp->f_mode |= FMODE_NDELAY; if (filp->f_flags & O_EXCL) filp->f_mode |= FMODE_EXCL; if ((filp->f_flags & O_ACCMODE) == 3) filp->f_mode |= FMODE_WRITE_IOCTL; bdev = bd_acquire(inode); if (bdev == NULL) return -ENOMEM; filp->f_mapping = bdev->bd_inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); return blkdev_get(bdev, filp->f_mode, filp); } static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) { struct gendisk *disk = bdev->bd_disk; struct block_device *victim = NULL; /* * Sync early if it looks like we're the last one. If someone else * opens the block device between now and the decrement of bd_openers * then we did a sync that we didn't need to, but that's not the end * of the world and we want to avoid long (could be several minute) * syncs while holding the mutex. */ if (bdev->bd_openers == 1) sync_blockdev(bdev); mutex_lock_nested(&bdev->bd_mutex, for_part); if (for_part) bdev->bd_part_count--; if (!--bdev->bd_openers) { WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); kill_bdev(bdev); bdev_write_inode(bdev); } if (bdev->bd_contains == bdev) { if (disk->fops->release) disk->fops->release(disk, mode); } if (!bdev->bd_openers) { disk_put_part(bdev->bd_part); bdev->bd_part = NULL; bdev->bd_disk = NULL; if (bdev != bdev->bd_contains) victim = bdev->bd_contains; bdev->bd_contains = NULL; put_disk_and_module(disk); } mutex_unlock(&bdev->bd_mutex); bdput(bdev); if (victim) __blkdev_put(victim, mode, 1); } void blkdev_put(struct block_device *bdev, fmode_t mode) { mutex_lock(&bdev->bd_mutex); if (mode & FMODE_EXCL) { bool bdev_free; /* * Release a claim on the device. The holder fields * are protected with bdev_lock. bd_mutex is to * synchronize disk_holder unlinking. */ spin_lock(&bdev_lock); WARN_ON_ONCE(--bdev->bd_holders < 0); WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0); /* bd_contains might point to self, check in a separate step */ if ((bdev_free = !bdev->bd_holders)) bdev->bd_holder = NULL; if (!bdev->bd_contains->bd_holders) bdev->bd_contains->bd_holder = NULL; spin_unlock(&bdev_lock); /* * If this was the last claim, remove holder link and * unblock evpoll if it was a write holder. */ if (bdev_free && bdev->bd_write_holder) { disk_unblock_events(bdev->bd_disk); bdev->bd_write_holder = false; } } /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE * event. This is to ensure detection of media removal commanded * from userland - e.g. eject(1). */ disk_flush_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE); mutex_unlock(&bdev->bd_mutex); __blkdev_put(bdev, mode, 0); } EXPORT_SYMBOL(blkdev_put); static int blkdev_close(struct inode * inode, struct file * filp) { struct block_device *bdev = I_BDEV(bdev_file_inode(filp)); blkdev_put(bdev, filp->f_mode); return 0; } static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct block_device *bdev = I_BDEV(bdev_file_inode(file)); fmode_t mode = file->f_mode; /* * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have * to updated it before every ioctl. */ if (file->f_flags & O_NDELAY) mode |= FMODE_NDELAY; else mode &= ~FMODE_NDELAY; return blkdev_ioctl(bdev, mode, cmd, arg); } /* * Write data to the block device. Only intended for the block device itself * and the raw driver which basically is a fake block device. * * Does not take i_mutex for the write and thus is not for general purpose * use. */ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *bd_inode = bdev_file_inode(file); loff_t size = i_size_read(bd_inode); struct blk_plug plug; size_t shorted = 0; ssize_t ret; if (bdev_read_only(I_BDEV(bd_inode))) return -EPERM; if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev)) return -ETXTBSY; if (!iov_iter_count(from)) return 0; if (iocb->ki_pos >= size) return -ENOSPC; if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT) return -EOPNOTSUPP; size -= iocb->ki_pos; if (iov_iter_count(from) > size) { shorted = iov_iter_count(from) - size; iov_iter_truncate(from, size); } blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); if (ret > 0) ret = generic_write_sync(iocb, ret); iov_iter_reexpand(from, iov_iter_count(from) + shorted); blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL_GPL(blkdev_write_iter); ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *bd_inode = bdev_file_inode(file); loff_t size = i_size_read(bd_inode); loff_t pos = iocb->ki_pos; size_t shorted = 0; ssize_t ret; if (pos >= size) return 0; size -= pos; if (iov_iter_count(to) > size) { shorted = iov_iter_count(to) - size; iov_iter_truncate(to, size); } ret = generic_file_read_iter(iocb, to); iov_iter_reexpand(to, iov_iter_count(to) + shorted); return ret; } EXPORT_SYMBOL_GPL(blkdev_read_iter); /* * Try to release a page associated with block device when the system * is under memory pressure. */ static int blkdev_releasepage(struct page *page, gfp_t wait) { struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super; if (super && super->s_op->bdev_try_to_free_page) return super->s_op->bdev_try_to_free_page(super, page, wait); return try_to_free_buffers(page); } static int blkdev_writepages(struct address_space *mapping, struct writeback_control *wbc) { return generic_writepages(mapping, wbc); } static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .readahead = blkdev_readahead, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, .writepages = blkdev_writepages, .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .migratepage = buffer_migrate_page_norefs, .is_dirty_writeback = buffer_check_dirty_writeback, }; #define BLKDEV_FALLOC_FL_SUPPORTED \ (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE) static long blkdev_fallocate(struct file *file, int mode, loff_t start, loff_t len) { struct block_device *bdev = I_BDEV(bdev_file_inode(file)); loff_t end = start + len - 1; loff_t isize; int error; /* Fail if we don't recognize the flags. */ if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED) return -EOPNOTSUPP; /* Don't go off the end of the device. */ isize = i_size_read(bdev->bd_inode); if (start >= isize) return -EINVAL; if (end >= isize) { if (mode & FALLOC_FL_KEEP_SIZE) { len = isize - start; end = start + len - 1; } else return -EINVAL; } /* * Don't allow IO that isn't aligned to logical block size. */ if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; /* * Invalidate the page cache, including dirty pages, for valid * de-allocate mode calls to fallocate(). */ switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: error = truncate_bdev_range(bdev, file->f_mode, start, end); if (error) break; error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: error = truncate_bdev_range(bdev, file->f_mode, start, end); if (error) break; error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: error = truncate_bdev_range(bdev, file->f_mode, start, end); if (error) break; error = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); break; default: return -EOPNOTSUPP; } if (error) return error; /* * Invalidate again; if someone wandered in and dirtied a page, * the caller will be given -EBUSY. The third argument is * inclusive, so the rounding here is safe. */ return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, start >> PAGE_SHIFT, end >> PAGE_SHIFT); } const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .iopoll = blkdev_iopoll, .mmap = generic_file_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = blkdev_fallocate, }; /** * lookup_bdev - lookup a struct block_device by name * @pathname: special file representing the block device * * Get a reference to the blockdevice at @pathname in the current * namespace if possible and return it. Return ERR_PTR(error) * otherwise. */ struct block_device *lookup_bdev(const char *pathname) { struct block_device *bdev; struct inode *inode; struct path path; int error; if (!pathname || !*pathname) return ERR_PTR(-EINVAL); error = kern_path(pathname, LOOKUP_FOLLOW, &path); if (error) return ERR_PTR(error); inode = d_backing_inode(path.dentry); error = -ENOTBLK; if (!S_ISBLK(inode->i_mode)) goto fail; error = -EACCES; if (!may_open_dev(&path)) goto fail; error = -ENOMEM; bdev = bd_acquire(inode); if (!bdev) goto fail; out: path_put(&path); return bdev; fail: bdev = ERR_PTR(error); goto out; } EXPORT_SYMBOL(lookup_bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty) { struct super_block *sb = get_super(bdev); int res = 0; if (sb) { /* * no need to lock the super, get_super holds the * read mutex so the filesystem cannot go away * under us (->put_super runs with the write lock * hold). */ shrink_dcache_sb(sb); res = invalidate_inodes(sb, kill_dirty); drop_super(sb); } invalidate_bdev(bdev); return res; } EXPORT_SYMBOL(__invalidate_device); void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) { struct inode *inode, *old_inode = NULL; spin_lock(&blockdev_superblock->s_inode_list_lock); list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { struct address_space *mapping = inode->i_mapping; struct block_device *bdev; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || mapping->nrpages == 0) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&blockdev_superblock->s_inode_list_lock); /* * We hold a reference to 'inode' so it couldn't have been * removed from s_inodes list while we dropped the * s_inode_list_lock We cannot iput the inode now as we can * be holding the last reference and we cannot iput it under * s_inode_list_lock. So we keep the reference and iput it * later. */ iput(old_inode); old_inode = inode; bdev = I_BDEV(inode); mutex_lock(&bdev->bd_mutex); if (bdev->bd_openers) func(bdev, arg); mutex_unlock(&bdev->bd_mutex); spin_lock(&blockdev_superblock->s_inode_list_lock); } spin_unlock(&blockdev_superblock->s_inode_list_lock); iput(old_inode); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 3 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id()), 32) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, &seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned long lpos) { unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, data_ring, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, &rb->text_data_ring, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* Specify a data-less block. */ blk_lpos->begin = NO_LPOS; blk_lpos->next = NO_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); if (!data_push_tail(rb, data_ring, next_lpos - DATA_SIZE(data_ring))) { /* Failed to allocate, specify a data-less block. */ blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* If the data block does not increase, there is nothing to do. */ if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } if (!data_push_tail(rb, data_ring, next_lpos - DATA_SIZE(data_ring))) return NULL; /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { if (blk_lpos->begin == NO_LPOS && blk_lpos->next == NO_LPOS) { *data_size = 0; return ""; } return NULL; } /* Regular data block: @begin less than @next and in same wrap. */ if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && blk_lpos->begin < blk_lpos->next) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == DATA_WRAPS(data_ring, blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* A valid data block will always have at least an ID. */ if (WARN_ON_ONCE(*data_size < sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB If desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, &rb->text_data_ring, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, &rb->text_data_ring, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); atomic_long_cmpxchg_relaxed(&d->state_var, prev_state_val, DESC_SV(id, desc_finalized)); /* LMM(desc_make_final:A) */ } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(desc_ring, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, &rb->text_data_ring, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB _prb_commit:B to prb_commit:A * matching * MB desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(desc_ring, e->id); } /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { _prb_commit(e, desc_finalized); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ static u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /* * Non-blocking read of a record. Updates @seq to the last finalized record * (which may have no data available). * * See the description of prb_read_valid() and prb_read_valid_info() * for details. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but no data available. Skip. */ (*seq)++; } else { /* Non-existent/non-finalized record. Must stop. */ return false; } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a not yet written record. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a not yet written record. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { u64 seq = 0; /* Search forward from the oldest descriptor. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static void flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); #define CSD_LOCK_TIMEOUT (5ULL * NSEC_PER_SEC) static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void csd_lock_record(struct __call_single_data *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline int csd_lock_wait_getcpu(struct __call_single_data *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static __always_inline bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->flags); if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); return true; } ts2 = sched_clock(); ts_delta = ts2 - *ts1; if (likely(ts_delta <= CSD_LOCK_TIMEOUT)) return false; firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0, cpu, csd->func, csd->info); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (!trigger_single_cpu_backtrace(cpu)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static __always_inline void csd_lock_wait(struct __call_single_data *csd) { int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = sched_clock(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } #else static void csd_lock_record(struct __call_single_data *csd) { } static __always_inline void csd_lock_wait(struct __call_single_data *csd) { smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(struct __call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(struct __call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * The list addition should be visible before sending the IPI * handler locks the list to pull the entry off it because of * normal cache coherency rules implied by spinlocks. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, struct __call_single_data *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); func(info); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { flush_smp_call_function_queue(true); } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; lockdep_assert_irqs_disabled(); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->llist; } else { entry = &csd_next->llist; } csd_lock_record(csd); func(info); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->llist; } else { entry = &csd_next->llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); func(info); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) sched_ttwu_pending(entry); } void flush_smp_call_function_from_idle(void) { unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq(); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->src = smp_processor_id(); csd->dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async(): Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { int err = 0; preempt_disable(); if (csd->flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait, smp_cond_func_t cond_func) { struct call_function_data *cfd; int cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress && !early_boot_irqs_disabled); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); /* No online cpus? We're done. */ if (cpu >= nr_cpu_ids) return; /* Do we have another CPU which isn't us? */ next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (next_cpu == this_cpu) next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); /* Fastpath: do that cpu by itself. */ if (next_cpu >= nr_cpu_ids) { if (!cond_func || cond_func(cpu, info)) smp_call_function_single(cpu, func, info, wait); return; } cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ if (unlikely(!cpumask_weight(cfd->cpumask))) return; cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) continue; csd_lock(csd); if (wait) csd->flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->src = smp_processor_id(); csd->dst = cpu; #endif if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) __cpumask_set_cpu(cpu, cfd->cpumask_ipi); } /* Send a message to all CPUs in the map */ arch_send_call_function_ipi_mask(cfd->cpumask_ipi); if (wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of other CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) nr_cpu_ids = nr_cpus; return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * Call a function on all processors. May be used during early boot while * early_boot_irqs_disabled is set. Use local_irq_save/restore() instead * of local_irq_disable/enable(). */ void on_each_cpu(smp_call_func_t func, void *info, int wait) { unsigned long flags; preempt_disable(); smp_call_function(func, info, wait); local_irq_save(flags); func(info); local_irq_restore(flags); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu); /** * on_each_cpu_mask(): Run a function on processors specified by * cpumask, which may include the local processor. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. The * exception is that it may be used during early boot while * early_boot_irqs_disabled is set. */ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { int cpu = get_cpu(); smp_call_function_many(mask, func, info, wait); if (cpumask_test_cpu(cpu, mask)) { unsigned long flags; local_irq_save(flags); func(info); local_irq_restore(flags); } put_cpu(); } EXPORT_SYMBOL(on_each_cpu_mask); /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { int cpu = get_cpu(); smp_call_function_many_cond(mask, func, info, wait, cond_func); if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) { unsigned long flags; local_irq_save(flags); func(info); local_irq_restore(flags); } put_cpu(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait) { on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } EXPORT_SYMBOL(on_each_cpu_cond); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; preempt_disable(); for_each_online_cpu(cpu) { if (cpu == smp_processor_id()) continue; wake_up_if_idle(cpu); } preempt_enable(); } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * smp_call_on_cpu - Call a function on a specific cpu * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); destroy_work_on_stack(&sscs.work); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_USER_NAMESPACE_H #define _LINUX_USER_NAMESPACE_H #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> #define UID_GID_MAP_MAX_BASE_EXTENTS 5 #define UID_GID_MAP_MAX_EXTENTS 340 struct uid_gid_extent { u32 first; u32 lower_first; u32 count; }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ u32 nr_extents; union { struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; }; }; }; #define USERNS_SETGROUPS_ALLOWED 1UL #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED struct ucounts; enum ucount_type { UCOUNT_USER_NAMESPACES, UCOUNT_PID_NAMESPACES, UCOUNT_UTS_NAMESPACES, UCOUNT_IPC_NAMESPACES, UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif #ifdef CONFIG_FANOTIFY UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif UCOUNT_COUNTS, }; struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; atomic_t count; struct user_namespace *parent; int level; kuid_t owner; kgid_t group; struct ns_common ns; unsigned long flags; /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP * in its effective capability set at the child ns creation time. */ bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of * these pointers is controlled by keyring_sem. Once * user_keyring_register is set, it won't be changed, so it can be * accessed directly with READ_ONCE(). */ struct list_head keyring_name_list; struct key *user_keyring_register; struct rw_semaphore keyring_sem; #endif /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; #endif struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; } __randomize_layout; struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; int count; atomic_t ucount[UCOUNT_COUNTS]; }; extern struct user_namespace init_user_ns; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) atomic_inc(&ns->count); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { if (ns && atomic_dec_and_test(&ns->count)) __put_user_ns(ns); } struct seq_operations; extern const struct seq_operations proc_uid_seq_operations; extern const struct seq_operations proc_gid_seq_operations; extern const struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { return &init_user_ns; } static inline int create_user_ns(struct cred *new) { return -EINVAL; } static inline int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { if (unshare_flags & CLONE_NEWUSER) return -EINVAL; return 0; } static inline void put_user_ns(struct user_namespace *ns) { } static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } static inline bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { return true; } static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } static inline struct ns_common *ns_get_owner(struct ns_common *ns) { return ERR_PTR(-EPERM); } #endif #endif /* _LINUX_USER_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_GENHD_H #define _LINUX_GENHD_H /* * genhd.h Copyright (C) 1992 Drew Eckhardt * Generic hard disk header file by * Drew Eckhardt * * <drew@colorado.edu> */ #include <linux/types.h> #include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/uuid.h> #include <linux/blk_types.h> #include <asm/local.h> #define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) #define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; #define DISK_MAX_PARTS 256 #define DISK_NAME_LEN 32 #include <linux/major.h> #include <linux/device.h> #include <linux/smp.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/workqueue.h> #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. * EFI UUID is 36 characters. MSDOS UUID is 11 characters. */ #define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) struct partition_meta_info { char uuid[PARTITION_META_INFO_UUIDLTH]; u8 volname[PARTITION_META_INFO_VOLNAMELTH]; }; struct hd_struct { sector_t start_sect; /* * nr_sects is protected by sequence counter. One might extend a * partition while IO is happening to it and update of nr_sects * can be non-atomic on 32bit machines with 64bit sector_t. */ sector_t nr_sects; #if BITS_PER_LONG==32 && defined(CONFIG_SMP) seqcount_t nr_sects_seq; #endif unsigned long stamp; struct disk_stats __percpu *dkstats; struct percpu_ref ref; struct device __dev; struct kobject *holder_dir; int policy, partno; struct partition_meta_info *info; #ifdef CONFIG_FAIL_MAKE_REQUEST int make_it_fail; #endif struct rcu_work rcu_work; }; /** * DOC: genhd capability flags * * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device * gives access to removable media. * When set, the device remains present even when media is not * inserted. * Must not be set for devices which are removed entirely when the * media is removed. * * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style * device. * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. * * ``GENHD_FL_UP`` (0x0010): indicates that the block device is "up", * with a similar meaning to network interfaces. * * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include * partition information in ``/proc/partitions`` or in the output of * printk_all_partitions(). * Used for the null block device and some MMC devices. * * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended * dynamic ``dev_t``, i.e. it wants extended device numbers * (``BLOCK_EXT_MAJOR``). * This affects the maximum number of partitions. * * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the * partition table, the device's capacity has been extended to its * native capacity; i.e. the device has hidden capacity used by one * of the partitions (this is a flag used so that native capacity is * only ever unlocked once). * * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is * blocked whenever a writer holds an exclusive lock. * * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled. * Used for loop devices in their default settings and some MMC * devices. * * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it * doesn't produce events, doesn't appear in sysfs, and doesn't have * an associated ``bdev``. * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and * ``GENHD_FL_NO_PART_SCAN``. * Used for multipath devices. */ #define GENHD_FL_REMOVABLE 0x0001 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ #define GENHD_FL_CD 0x0008 #define GENHD_FL_UP 0x0010 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NATIVE_CAPACITY 0x0080 #define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100 #define GENHD_FL_NO_PART_SCAN 0x0200 #define GENHD_FL_HIDDEN 0x0400 enum { DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ }; enum { /* Poll even if events_poll_msecs is unset */ DISK_EVENT_FLAG_POLL = 1 << 0, /* Forward events to udev */ DISK_EVENT_FLAG_UEVENT = 1 << 1, }; struct disk_part_tbl { struct rcu_head rcu_head; int len; struct hd_struct __rcu *last_lookup; struct hd_struct __rcu *part[]; }; struct disk_events; struct badblocks; struct blk_integrity { const struct blk_integrity_profile *profile; unsigned char flags; unsigned char tuple_size; unsigned char interval_exp; unsigned char tag_size; }; struct gendisk { /* major, first_minor and minors are input parameters only, * don't use directly. Use disk_devt() and disk_max_parts(). */ int major; /* major number of driver */ int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ char disk_name[DISK_NAME_LEN]; /* name of major driver */ unsigned short events; /* supported events */ unsigned short event_flags; /* flags related to event processing */ /* Array of pointers to partitions indexed by partno. * Protected with matching bdev lock but stat and other * non-critical accesses use RCU. Always access through * helpers. */ struct disk_part_tbl __rcu *part_tbl; struct hd_struct part0; const struct block_device_operations *fops; struct request_queue *queue; void *private_data; int flags; unsigned long state; #define GD_NEED_PART_SCAN 0 struct rw_semaphore lookup_sem; struct kobject *slave_dir; struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; #ifdef CONFIG_BLK_DEV_INTEGRITY struct kobject integrity_kobj; #endif /* CONFIG_BLK_DEV_INTEGRITY */ #if IS_ENABLED(CONFIG_CDROM) struct cdrom_device_info *cdi; #endif int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; }; #if IS_REACHABLE(CONFIG_CDROM) #define disk_to_cdi(disk) ((disk)->cdi) #else #define disk_to_cdi(disk) NULL #endif static inline struct gendisk *part_to_disk(struct hd_struct *part) { if (likely(part)) { if (part->partno) return dev_to_disk(part_to_dev(part)->parent); else return dev_to_disk(part_to_dev(part)); } return NULL; } static inline int disk_max_parts(struct gendisk *disk) { if (disk->flags & GENHD_FL_EXT_DEVT) return DISK_MAX_PARTS; return disk->minors; } static inline bool disk_part_scan_enabled(struct gendisk *disk) { return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART_SCAN); } static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); } static inline dev_t part_devt(struct hd_struct *part) { return part_to_dev(part)->devt; } extern struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno); static inline void disk_put_part(struct hd_struct *part) { if (likely(part)) put_device(part_to_dev(part)); } static inline void hd_sects_seq_init(struct hd_struct *p) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) seqcount_init(&p->nr_sects_seq); #endif } /* * Smarter partition iterator without context limits. */ #define DISK_PITER_REVERSE (1 << 0) /* iterate in the reverse direction */ #define DISK_PITER_INCL_EMPTY (1 << 1) /* include 0-sized parts */ #define DISK_PITER_INCL_PART0 (1 << 2) /* include partition 0 */ #define DISK_PITER_INCL_EMPTY_PART0 (1 << 3) /* include empty partition 0 */ struct disk_part_iter { struct gendisk *disk; struct hd_struct *part; int idx; unsigned int flags; }; extern void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk, unsigned int flags); extern struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter); extern void disk_part_iter_exit(struct disk_part_iter *piter); extern bool disk_has_partitions(struct gendisk *disk); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups); static inline void add_disk(struct gendisk *disk) { device_add_disk(NULL, disk, NULL); } extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk); static inline void add_disk_no_queue_reg(struct gendisk *disk) { device_add_disk_no_queue_reg(NULL, disk); } extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); static inline int get_disk_ro(struct gendisk *disk) { return disk->part0.policy; } extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); bool set_capacity_and_notify(struct gendisk *disk, sector_t size); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; extern void rand_initialize_disk(struct gendisk *disk); static inline sector_t get_start_sect(struct block_device *bdev) { return bdev->bd_part->start_sect; } static inline sector_t get_capacity(struct gendisk *disk) { return disk->part0.nr_sects; } static inline void set_capacity(struct gendisk *disk, sector_t size) { disk->part0.nr_sects = size; } int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); int blk_drop_partitions(struct block_device *bdev); extern struct gendisk *__alloc_disk_node(int minors, int node_id); extern struct kobject *get_disk_and_module(struct gendisk *disk); extern void put_disk(struct gendisk *disk); extern void put_disk_and_module(struct gendisk *disk); extern void blk_register_region(dev_t devt, unsigned long range, struct module *module, struct kobject *(*probe)(dev_t, int *, void *), int (*lock)(dev_t, void *), void *data); extern void blk_unregister_region(dev_t devt, unsigned long range); #define alloc_disk_node(minors, node_id) \ ({ \ static struct lock_class_key __key; \ const char *__name; \ struct gendisk *__disk; \ \ __name = "(gendisk_completion)"#minors"("#node_id")"; \ \ __disk = __alloc_disk_node(minors, node_id); \ \ if (__disk) \ lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \ \ __disk; \ }) #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); void revalidate_disk_size(struct gendisk *disk, bool verbose); bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); /* for drivers/char/raw.c: */ int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); #ifdef CONFIG_SYSFS int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { return 0; } static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_BLOCK void printk_all_partitions(void); dev_t blk_lookup_devt(const char *name, int partno); #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } static inline dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); return devt; } #endif /* CONFIG_BLOCK */ #endif /* _LINUX_GENHD_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Interfaces handler. * * Version: @(#)dev.h 1.0.10 08/12/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Donald J. Becker, <becker@cesdis.gsfc.nasa.gov> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Bjorn Ekwall. <bj0rn@blox.se> * Pekka Riikonen <priikone@poseidon.pspt.fi> * * Moved to /usr/include/linux for NET3 */ #ifndef _LINUX_NETDEVICE_H #define _LINUX_NETDEVICE_H #include <linux/timer.h> #include <linux/bug.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> #include <linux/percpu.h> #include <linux/rculist.h> #include <linux/workqueue.h> #include <linux/dynamic_queue_limits.h> #include <linux/ethtool.h> #include <net/net_namespace.h> #ifdef CONFIG_DCB #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> #include <net/xdp.h> #include <linux/netdev_features.h> #include <linux/neighbour.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> #include <linux/hashtable.h> struct netpoll_info; struct device; struct phy_device; struct dsa_port; struct ip_tunnel_parm; struct macsec_context; struct macsec_ops; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct udp_tunnel_nic_info; struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ #define MAX_NEST_DEV 8 /* * Transmit return codes: transmit return codes originate from three different * namespaces: * * - qdisc return codes * - driver transmit return codes * - errno values * * Drivers are allowed to return any one of those in their hard_start_xmit() * function. Real network devices commonly used with qdiscs should only return * the driver transmit return codes though - when qdiscs are used, the actual * transmission happens asynchronously, so the value is not propagated to * higher layers. Virtual network devices transmit synchronously; in this case * the driver transmit return codes are consumed by dev_queue_xmit(), and all * others are propagated to higher layers. */ /* qdisc ->enqueue() return codes. */ #define NET_XMIT_SUCCESS 0x00 #define NET_XMIT_DROP 0x01 /* skb dropped */ #define NET_XMIT_CN 0x02 /* congestion notification */ #define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */ /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It * indicates that the device will soon be dropping packets, or already drops * some packets of the same priority; prompting us to send less aggressively. */ #define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e)) #define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0) /* Driver transmit return codes */ #define NETDEV_TX_MASK 0xf0 enum netdev_tx { __NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */ NETDEV_TX_OK = 0x00, /* driver took care of packet */ NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/ }; typedef enum netdev_tx netdev_tx_t; /* * Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant; * hard_start_xmit() return < NET_XMIT_MASK means skb was consumed. */ static inline bool dev_xmit_complete(int rc) { /* * Positive cases with an skb consumed by a driver: * - successful transmission (rc == NETDEV_TX_OK) * - error while transmitting (rc < 0) * - error while queueing to a different device (rc & NET_XMIT_MASK) */ if (likely(rc < NET_XMIT_MASK)) return true; return false; } /* * Compute the worst-case header length according to the protocols * used. */ #if defined(CONFIG_HYPERV_NET) # define LL_MAX_HEADER 128 #elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else # define LL_MAX_HEADER 96 # endif #else # define LL_MAX_HEADER 32 #endif #if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \ !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL) #define MAX_HEADER LL_MAX_HEADER #else #define MAX_HEADER (LL_MAX_HEADER + 48) #endif /* * Old network device statistics. Fields are native words * (unsigned long) so they can be read and written atomically. */ #define NET_DEV_STAT(FIELD) \ union { \ unsigned long FIELD; \ atomic_long_t __##FIELD; \ } struct net_device_stats { NET_DEV_STAT(rx_packets); NET_DEV_STAT(tx_packets); NET_DEV_STAT(rx_bytes); NET_DEV_STAT(tx_bytes); NET_DEV_STAT(rx_errors); NET_DEV_STAT(tx_errors); NET_DEV_STAT(rx_dropped); NET_DEV_STAT(tx_dropped); NET_DEV_STAT(multicast); NET_DEV_STAT(collisions); NET_DEV_STAT(rx_length_errors); NET_DEV_STAT(rx_over_errors); NET_DEV_STAT(rx_crc_errors); NET_DEV_STAT(rx_frame_errors); NET_DEV_STAT(rx_fifo_errors); NET_DEV_STAT(rx_missed_errors); NET_DEV_STAT(tx_aborted_errors); NET_DEV_STAT(tx_carrier_errors); NET_DEV_STAT(tx_fifo_errors); NET_DEV_STAT(tx_heartbeat_errors); NET_DEV_STAT(tx_window_errors); NET_DEV_STAT(rx_compressed); NET_DEV_STAT(tx_compressed); }; #undef NET_DEV_STAT #include <linux/cache.h> #include <linux/skbuff.h> #ifdef CONFIG_RPS #include <linux/static_key.h> extern struct static_key_false rps_needed; extern struct static_key_false rfs_needed; #endif struct neighbour; struct neigh_parms; struct sk_buff; struct netdev_hw_addr { struct list_head list; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 #define NETDEV_HW_ADDR_T_SAN 2 #define NETDEV_HW_ADDR_T_UNICAST 3 #define NETDEV_HW_ADDR_T_MULTICAST 4 bool global_use; int sync_cnt; int refcount; int synced; struct rcu_head rcu_head; }; struct netdev_hw_addr_list { struct list_head list; int count; }; #define netdev_hw_addr_list_count(l) ((l)->count) #define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0) #define netdev_hw_addr_list_for_each(ha, l) \ list_for_each_entry(ha, &(l)->list, list) #define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc) #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { unsigned int hh_len; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ #define HH_DATA_MOD 16 #define HH_DATA_OFF(__len) \ (HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1)) #define HH_DATA_ALIGN(__len) \ (((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1)) unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; }; /* Reserve HH_DATA_MOD byte-aligned hard_header_len, but at least that much. * Alternative is: * dev->hard_header_len ? (dev->hard_header_len + * (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0 * * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len); int (*parse)(const struct sk_buff *skb, unsigned char *haddr); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); bool (*validate)(const char *ll_header, unsigned int len); __be16 (*parse_protocol)(const struct sk_buff *skb); }; /* These flag bits are private to the generic network queueing * layer; they may not be explicitly referenced by any other * code. */ enum netdev_state_t { __LINK_STATE_START, __LINK_STATE_PRESENT, __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, __LINK_STATE_TESTING, }; /* * This structure holds boot-time configured netdevice settings. They * are then used in the device probing. */ struct netdev_boot_setup { char name[IFNAMSIZ]; struct ifmap map; }; #define NETDEV_BOOT_SETUP_MAX 8 int __init netdev_boot_setup(char *str); struct gro_list { struct list_head list; int count; }; /* * size of gro hash buckets, must less than bit number of * napi_struct::gro_bitmask */ #define GRO_HASH_BUCKETS 8 /* * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct * to the per-CPU poll_list, and whoever clears that bit * can remove from the list right before clearing the bit. */ struct list_head poll_list; unsigned long state; int weight; int defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL int poll_owner; #endif struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ struct hrtimer timer; struct list_head dev_list; struct hlist_node napi_hash_node; unsigned int napi_id; }; enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ }; enum { NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { GRO_MERGED, GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, GRO_DROP, GRO_CONSUMED, }; typedef enum gro_result gro_result_t; /* * enum rx_handler_result - Possible return values for rx_handlers. * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it * further. * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in * case skb->dev was changed by rx_handler. * @RX_HANDLER_EXACT: Force exact delivery, no wildcard. * @RX_HANDLER_PASS: Do nothing, pass the skb as if no rx_handler was called. * * rx_handlers are functions called from inside __netif_receive_skb(), to do * special processing of the skb, prior to delivery to protocol handlers. * * Currently, a net_device can only have a single rx_handler registered. Trying * to register a second rx_handler will return -EBUSY. * * To register a rx_handler on a net_device, use netdev_rx_handler_register(). * To unregister a rx_handler on a net_device, use * netdev_rx_handler_unregister(). * * Upon return, rx_handler is expected to tell __netif_receive_skb() what to * do with the skb. * * If the rx_handler consumed the skb in some way, it should return * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for * the skb to be delivered in some other way. * * If the rx_handler changed skb->dev, to divert the skb to another * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the * new device will be called if it exists. * * If the rx_handler decides the skb should be ignored, it should return * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that * are registered on exact device (ptype->dev == skb->dev). * * If the rx_handler didn't change skb->dev, but wants the skb to be normally * delivered, it should return RX_HANDLER_PASS. * * A device without a registered rx_handler will behave as if rx_handler * returned RX_HANDLER_PASS. */ enum rx_handler_result { RX_HANDLER_CONSUMED, RX_HANDLER_ANOTHER, RX_HANDLER_EXACT, RX_HANDLER_PASS, }; typedef enum rx_handler_result rx_handler_result_t; typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); void __napi_schedule(struct napi_struct *n); void __napi_schedule_irqoff(struct napi_struct *n); static inline bool napi_disable_pending(struct napi_struct *n) { return test_bit(NAPI_STATE_DISABLE, &n->state); } bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll * @n: NAPI context * * Schedule NAPI poll routine to be called if it is not already * running. */ static inline void napi_schedule(struct napi_struct *n) { if (napi_schedule_prep(n)) __napi_schedule(n); } /** * napi_schedule_irqoff - schedule NAPI poll * @n: NAPI context * * Variant of napi_schedule(), assuming hard irqs are masked. */ static inline void napi_schedule_irqoff(struct napi_struct *n) { if (napi_schedule_prep(n)) __napi_schedule_irqoff(n); } /* Try to reschedule poll. Called by dev->poll() after napi_complete(). */ static inline bool napi_reschedule(struct napi_struct *napi) { if (napi_schedule_prep(napi)) { __napi_schedule(napi); return true; } return false; } bool napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete * @n: NAPI context * * Mark NAPI processing as complete. * Consider using napi_complete_done() instead. * Return false if device should avoid rearming interrupts. */ static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); } /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context * * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. */ void napi_disable(struct napi_struct *n); /** * napi_enable - enable NAPI scheduling * @n: NAPI context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. */ static inline void napi_enable(struct napi_struct *n) { BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); clear_bit(NAPI_STATE_NPSVC, &n->state); } /** * napi_synchronize - wait until NAPI is not running * @n: NAPI context * * Wait until NAPI is done being scheduled on this context. * Waits till any outstanding processing completes but * does not disable future activations. */ static inline void napi_synchronize(const struct napi_struct *n) { if (IS_ENABLED(CONFIG_SMP)) while (test_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); else barrier(); } /** * napi_if_scheduled_mark_missed - if napi is running, set the * NAPIF_STATE_MISSED * @n: NAPI context * * If napi is running, set the NAPIF_STATE_MISSED, and return true if * NAPI is scheduled. **/ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) { unsigned long val, new; do { val = READ_ONCE(n->state); if (val & NAPIF_STATE_DISABLE) return true; if (!(val & NAPIF_STATE_SCHED)) return false; new = val | NAPIF_STATE_MISSED; } while (cmpxchg(&n->state, val, new) != val); return true; } enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, __QUEUE_STATE_FROZEN, }; #define QUEUE_STATE_DRV_XOFF (1 << __QUEUE_STATE_DRV_XOFF) #define QUEUE_STATE_STACK_XOFF (1 << __QUEUE_STATE_STACK_XOFF) #define QUEUE_STATE_FROZEN (1 << __QUEUE_STATE_FROZEN) #define QUEUE_STATE_ANY_XOFF (QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF) #define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \ QUEUE_STATE_FROZEN) #define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \ QUEUE_STATE_FROZEN) /* * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The * netif_tx_* functions below are used to manipulate this flag. The * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit * queue independently. The netif_xmit_*stopped functions below are called * to check if the queue has been stopped by the driver or stack (either * of the XOFF bits are set in the state). Drivers should not need to call * netif_xmit*stopped functions, they should only be using netif_tx_*. */ struct netdev_queue { /* * read-mostly part */ struct net_device *dev; struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) int numa_node; #endif unsigned long tx_maxrate; /* * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ unsigned long trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif /* * write-mostly part */ spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* * Time (in jiffies) of last Tx */ unsigned long trans_start; unsigned long state; #ifdef CONFIG_BQL struct dql dql; #endif } ____cacheline_aligned_in_smp; extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; /* * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns * == 1 : For initns only * == 2 : For none. */ static inline bool net_has_fallback_tunnels(const struct net *net) { #if IS_ENABLED(CONFIG_SYSCTL) int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net); return !fb_tunnels_only_for_init_net || (net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1); #else return true; #endif } static inline int net_inherit_devconf(void) { #if IS_ENABLED(CONFIG_SYSCTL) return READ_ONCE(sysctl_devconf_inherit_init_net); #else return 0; #endif } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) return q->numa_node; #else return NUMA_NO_NODE; #endif } static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) q->numa_node = node; #endif } #ifdef CONFIG_RPS /* * This structure holds an RPS map which can be of variable length. The * map is an array of CPUs. */ struct rps_map { unsigned int len; struct rcu_head rcu; u16 cpus[]; }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) /* * The rps_dev_flow structure contains the mapping of a flow to a CPU, the * tail pointer for that CPU's input queue at the time of last enqueue, and * a hardware filter index. */ struct rps_dev_flow { u16 cpu; u16 filter; unsigned int last_qtail; }; #define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. */ struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; struct rps_dev_flow flows[]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ ((_num) * sizeof(struct rps_dev_flow))) /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). * Each entry is a 32bit value. Upper part is the high-order bits * of flow hash, lower part is CPU number. * rps_cpu_mask is used to partition the space, depending on number of * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { u32 mask; u32 ents[] ____cacheline_aligned_in_smp; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) #define RPS_NO_CPU 0xffff extern u32 rps_cpu_mask; extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, u32 hash) { if (table && hash) { unsigned int index = hash & table->mask; u32 val = hash & ~rps_cpu_mask; /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in get_rps_cpu(). */ if (READ_ONCE(table->ents[index]) != val) WRITE_ONCE(table->ents[index], val); } } #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif #endif /* CONFIG_RPS */ /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { #ifdef CONFIG_RPS struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; #endif struct kobject kobj; struct net_device *dev; struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif } ____cacheline_aligned_in_smp; /* * RX queue sysfs structures and functions. */ struct rx_queue_attribute { struct attribute attr; ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); ssize_t (*store)(struct netdev_rx_queue *queue, const char *buf, size_t len); }; #ifdef CONFIG_XPS /* * This structure holds an XPS map which can be of variable length. The * map is an array of queues. */ struct xps_map { unsigned int len; unsigned int alloc_len; struct rcu_head rcu; u16 queues[]; }; #define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16))) #define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \ - sizeof(struct xps_map)) / sizeof(u16)) /* * This structure holds all XPS maps for device. Maps are indexed by CPU. */ struct xps_dev_maps { struct rcu_head rcu; struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */ }; #define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) #define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ (_rxqs * (_tcs) * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 #define TC_BITMASK 15 /* HW offloaded queuing disciplines txq count and offset maps */ struct netdev_tc_txq { u16 count; u16 offset; }; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* * This structure is to hold information about the device * configured to run FCoE protocol stack. */ struct netdev_fcoe_hbainfo { char manufacturer[64]; char serial_number[64]; char hardware_version[64]; char driver_version[64]; char optionrom_version[64]; char firmware_version[64]; char model[256]; char model_description[256]; }; #endif #define MAX_PHYS_ITEM_ID_LEN 32 /* This structure holds a unique identifier to identify some * physical item (port for example) used by a netdevice. */ struct netdev_phys_item_id { unsigned char id[MAX_PHYS_ITEM_ID_LEN]; unsigned char id_len; }; static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, struct netdev_phys_item_id *b) { return a->id_len == b->id_len && memcmp(a->id, b->id, a->id_len) == 0; } typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); enum tc_setup_type { TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, TC_SETUP_BLOCK, TC_SETUP_QDISC_CBS, TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, TC_SETUP_QDISC_ETF, TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, TC_SETUP_FT, TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, }; /* These structures hold the attributes of bpf state that are being passed * to the netdevice through the bpf op. */ enum bpf_netdev_command { /* Set or clear a bpf program used in the earliest stages of packet * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee * is responsible for calling bpf_prog_put on any old progs that are * stored. In case of error, the callee need not release the new prog * reference, but on success it takes ownership and must bpf_prog_put * when it is no longer used. */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; struct bpf_xdp_link; enum bpf_xdp_mode { XDP_MODE_SKB = 0, XDP_MODE_DRV = 1, XDP_MODE_HW = 2, __MAX_XDP_MODE }; struct bpf_xdp_entity { struct bpf_prog *prog; struct bpf_xdp_link *link; }; struct netdev_bpf { enum bpf_netdev_command command; union { /* XDP_SETUP_PROG */ struct { u32 flags; struct bpf_prog *prog; struct netlink_ext_ack *extack; }; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; }; /* XDP_SETUP_XSK_POOL */ struct { struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; }; /* Flags for ndo_xsk_wakeup. */ #define XDP_WAKEUP_RX (1 << 0) #define XDP_WAKEUP_TX (1 << 1) #ifdef CONFIG_XFRM_OFFLOAD struct xfrmdev_ops { int (*xdo_dev_state_add) (struct xfrm_state *x); void (*xdo_dev_state_delete) (struct xfrm_state *x); void (*xdo_dev_state_free) (struct xfrm_state *x); bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); }; #endif struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; }; struct devlink; struct tlsdev_ops; struct netdev_name_node { struct hlist_node hlist; struct list_head list; struct net_device *dev; const char *name; }; int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); struct netdev_net_notifier { struct list_head list; struct notifier_block *nb; }; /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*ndo_init)(struct net_device *dev); * This function is called once when a network device is registered. * The network device can use this for any late stage initialization * or semantic validation. It can fail with an error code which will * be propagated back to register_netdev. * * void (*ndo_uninit)(struct net_device *dev); * This function is called when device is unregistered or when registration * fails. It is not called if init fails. * * int (*ndo_open)(struct net_device *dev); * This function is called when a network device transitions to the up * state. * * int (*ndo_stop)(struct net_device *dev); * This function is called when a network device transitions to the down * state. * * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, * struct net_device *dev); * Called when a packet needs to be transmitted. * Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop * the queue before that can happen; it's for obsolete devices and weird * corner cases, but the stack really does a non-trivial amount * of useless work if you return NETDEV_TX_BUSY. * Required; cannot be NULL. * * netdev_features_t (*ndo_features_check)(struct sk_buff *skb, * struct net_device *dev * netdev_features_t features); * Called by core transmit path to determine if device is capable of * performing offload operations on a given packet. This is to give * the device an opportunity to implement any restrictions that cannot * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * struct net_device *sb_dev); * Called to decide which queue to use when device supports multiple * transmit queues. * * void (*ndo_change_rx_flags)(struct net_device *dev, int flags); * This function is called to allow device receiver to make * changes to configuration when multicast or promiscuous is enabled. * * void (*ndo_set_rx_mode)(struct net_device *dev); * This function is called device changes address list filtering. * If driver handles unicast address filtering, it should set * IFF_UNICAST_FLT in its priv_flags. * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address * needs to be changed. If this interface is not defined, the * MAC address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Called when a user requests an ioctl which can't be handled by * the generic interface code. If not defined ioctls return * not supported error code. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface * is retained for legacy reasons; new devices should use the bus * interface (PCI) for low level management. * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); * Called when a user wants to change the Maximum Transfer Unit * of a device. * * void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue); * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * * void (*ndo_get_stats64)(struct net_device *dev, * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: * 1. Define @ndo_get_stats64 to fill in a zero-initialised * rtnl_link_stats64 structure passed by the caller. * 2. Define @ndo_get_stats to update a net_device_stats structure * (which should normally be dev->stats) and return a pointer to * it. The structure may be changed asynchronously only if each * field is written atomically. * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * * bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id) * Return true if this device supports offload stats of this attr_id. * * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, * void *attr_data) * Get statistics for offload operations by attr_id. Write it into the * attr_data pointer. * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); * * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, * u8 qos, __be16 proto); * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * * Enable or disable the VF ability to query its RSS Redirection Table and * Hash Key. This is needed since on some devices VF share this information * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, * void *type_data); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue * management safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); * Called when the FCoE protocol stack wants to start using LLD for FCoE * so the underlying device can perform whatever needed configuration or * initialization to support acceleration of FCoE traffic. * * int (*ndo_fcoe_disable)(struct net_device *dev); * Called when the FCoE protocol stack wants to stop using LLD for FCoE * so the underlying device can perform whatever needed clean-ups to * stop supporting acceleration of FCoE traffic. * * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Initiator wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); * Called when the FCoE Initiator/Target is done with the DDPed I/O as * indicated by the FC exchange id 'xid', so the underlying device can * clean up and reuse resources for later DDP requests. * * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Target wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, * struct netdev_fcoe_hbainfo *hbainfo); * Called when the FCoE Protocol stack wants information on the underlying * device. This information is utilized by the FCoE protocol stack to * register attributes with Fiber Channel management service as per the * FC-GS Fabric Device Management Information(FDMI) specification. * * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); * Called when the underlying device wants to override default World Wide * Name (WWN) generation mechanism in FCoE protocol stack to pass its own * World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE * protocol stack to use. * * RFS acceleration. * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, * u16 rxq_index, u32 flow_id); * Set hardware filter for RFS. rxq_index is the target queue index; * flow_id is a flow ID to be passed to rps_may_expire_flow() later. * Return the filter ID on success, or a negative error code. * * Slave management functions (for bridge, bonding, etc). * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to make another netdev an underling. * * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev, * struct sk_buff *skb, * bool all_slaves); * Get the xmit slave of master device. If all_slaves is true, function * assume all the slaves can transmit. * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); * Adjusts the requested feature flags according to device-specific * constraints, and returns the resulting flags. Must not modify * the device state. * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). * Must return >0 or -errno if it changed dev->features itself. * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid, u16 flags, * struct netlink_ext_ack *extack); * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * u16 vid, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags, struct netlink_ext_ack *extack) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, * struct net_device *dev, u32 filter_mask, * int nlflags) * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags); * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) * which do not represent real hardware may define this to allow their * userspace components to manage their virtual carrier state. Devices * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. * * int (*ndo_get_phys_port_id)(struct net_device *dev, * struct netdev_phys_item_id *ppid); * Called to get ID of physical port of this device. If driver does * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * * int (*ndo_get_port_parent_id)(struct net_device *dev, * struct netdev_phys_item_id *ppid) * Called to get the parent ID of the physical port of this device. * * void (*ndo_udp_tunnel_add)(struct net_device *dev, * struct udp_tunnel_info *ti); * Called by UDP tunnel to notify a driver about the UDP port and socket * address family that a UDP tunnel is listnening to. It is called only * when a new port starts listening. The operation is protected by the * RTNL. * * void (*ndo_udp_tunnel_del)(struct net_device *dev, * struct udp_tunnel_info *ti); * Called by UDP tunnel to notify the driver about a UDP port and socket * address family that the UDP tunnel is not listening to anymore. The * operation is protected by the RTNL. * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) * Called by upper layer devices to accelerate switching or other * station functionality into hardware. 'pdev is the lowerdev * to use for the offload and 'dev' is the net device that will * back the offload. Returns a pointer to the private structure * the upper layer will maintain. * void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv) * Called by upper layer device to delete the station created * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing * the station and priv is the structure returned by the add * operation. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. * void (*ndo_change_proto_down)(struct net_device *dev, * bool proto_down); * This function is used to pass protocol port error state information * to the switch driver. The switch driver can react to the proto_down * by doing a phys down on the associated switch port. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while * sampling packet. * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); * This function is used to specify the headroom that the skb must * consider when allocation skb during packet reception. Setting * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, * u32 flags); * This function is used to submit @n XDP packets for transmit on a * netdevice. Returns number of frames successfully transmitted, frames * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); * This function is used to wake up the softirq, ksoftirqd or kthread * responsible for sending and/or receiving packets on a specific * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev); * Get devlink port instance associated with a given netdev. * Called with a reference on the netdevice and devlink locks only, * rtnl_lock is not held. * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); * If a device is paired with a peer device, return the peer instance. * The caller must be under RCU read context. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); void (*ndo_uninit)(struct net_device *dev); int (*ndo_open)(struct net_device *dev); int (*ndo_stop)(struct net_device *dev); netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, struct net_device *dev); netdev_features_t (*ndo_features_check)(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); int (*ndo_set_mac_address)(struct net_device *dev, void *addr); int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev, unsigned int txqueue); void (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, void *attr_data); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, int queue, u16 vlan, u8 qos, __be16 proto); int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); int (*ndo_get_vf_stats)(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats); int (*ndo_set_vf_port)(struct net_device *dev, int vf, struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); int (*ndo_get_vf_guid)(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*ndo_set_vf_guid)(struct net_device *dev, int vf, u64 guid, int guid_type); int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, struct netdev_fcoe_hbainfo *hbainfo); #endif #if IS_ENABLED(CONFIG_LIBFCOE) #define NETDEV_FCOE_WWNN 0 #define NETDEV_FCOE_WWPN 1 int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif #ifdef CONFIG_RFS_ACCEL int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, u16 rxq_index, u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, struct sk_buff *skb, bool all_slaves); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); int (*ndo_neigh_construct)(struct net_device *dev, struct neighbour *n); void (*ndo_neigh_destroy)(struct net_device *dev, struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, struct netlink_ext_ack *extack); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, u16 vid, struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx); int (*ndo_fdb_get)(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); int (*ndo_get_port_parent_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); void (*ndo_udp_tunnel_add)(struct net_device *dev, struct udp_tunnel_info *ti); void (*ndo_udp_tunnel_del)(struct net_device *dev, struct udp_tunnel_info *ti); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); int (*ndo_change_proto_down)(struct net_device *dev, bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); }; /** * enum net_device_priv_flags - &struct net_device priv_flags * * These are the &struct net_device, they are only set internally * by drivers and used in the kernel. These flags are invisible to * userspace; this means that the order of these flags can change * during any kernel release. * * You should have a pretty good reason to be extending these flags. * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device * @IFF_BONDING: bonding master or slave * @IFF_ISATAP: ISATAP interface (RFC4214) * @IFF_WAN_HDLC: WAN HDLC device * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to * release skb->dst * @IFF_DONT_BRIDGE: disallow bridging this ether dev * @IFF_DISABLE_NETPOLL: disable netpoll at run-time * @IFF_MACVLAN_PORT: device used as macvlan port * @IFF_BRIDGE_PORT: device used as bridge port * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit * @IFF_UNICAST_FLT: Supports unicast filtering * @IFF_TEAM_PORT: device used as team port * @IFF_SUPP_NOFCS: device supports sending custom FCS * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device * @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account * underlying stacked devices * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, IFF_EBRIDGE = 1<<1, IFF_BONDING = 1<<2, IFF_ISATAP = 1<<3, IFF_WAN_HDLC = 1<<4, IFF_XMIT_DST_RELEASE = 1<<5, IFF_DONT_BRIDGE = 1<<6, IFF_DISABLE_NETPOLL = 1<<7, IFF_MACVLAN_PORT = 1<<8, IFF_BRIDGE_PORT = 1<<9, IFF_OVS_DATAPATH = 1<<10, IFF_TX_SKB_SHARING = 1<<11, IFF_UNICAST_FLT = 1<<12, IFF_TEAM_PORT = 1<<13, IFF_SUPP_NOFCS = 1<<14, IFF_LIVE_ADDR_CHANGE = 1<<15, IFF_MACVLAN = 1<<16, IFF_XMIT_DST_RELEASE_PERM = 1<<17, IFF_L3MDEV_MASTER = 1<<18, IFF_NO_QUEUE = 1<<19, IFF_OPENVSWITCH = 1<<20, IFF_L3MDEV_SLAVE = 1<<21, IFF_TEAM = 1<<22, IFF_RXFH_CONFIGURED = 1<<23, IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN #define IFF_EBRIDGE IFF_EBRIDGE #define IFF_BONDING IFF_BONDING #define IFF_ISATAP IFF_ISATAP #define IFF_WAN_HDLC IFF_WAN_HDLC #define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE #define IFF_DONT_BRIDGE IFF_DONT_BRIDGE #define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL #define IFF_MACVLAN_PORT IFF_MACVLAN_PORT #define IFF_BRIDGE_PORT IFF_BRIDGE_PORT #define IFF_OVS_DATAPATH IFF_OVS_DATAPATH #define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING #define IFF_UNICAST_FLT IFF_UNICAST_FLT #define IFF_TEAM_PORT IFF_TEAM_PORT #define IFF_SUPP_NOFCS IFF_SUPP_NOFCS #define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE #define IFF_MACVLAN IFF_MACVLAN #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED #define IFF_MACSEC IFF_MACSEC #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER #define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, ML_PRIV_CAN, }; /** * struct net_device - The DEVICE structure. * * Actually, this whole structure is a big mistake. It mixes I/O * data with strictly "high-level" data, and it has to know about * almost every data structure used in the INET module. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start * @base_addr: Device I/O address * @irq: Device IRQ number * * @state: Generic network queuing layer state, see netdev_state_t * @dev_list: The global list of network devices * @napi_list: List entry used for polling NAPI devices * @unreg_list: List entry when we are unregistering the * device; see the function unregister_netdev * @close_list: List entry used when we are closing the device * @ptype_all: Device-specific packet handlers for all protocols * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding * @features: Currently active device features * @hw_features: User-changeable features * * @wanted_features: User-requested features * @vlan_features: Mask of features inheritable by VLAN devices * * @hw_enc_features: Mask of features inherited by encapsulating devices * This field indicates what encapsulation * offloads the hardware is capable of doing, * and drivers will need to set them appropriately. * * @mpls_features: Mask of features inheritable by MPLS * @gso_partial_features: value(s) from NETIF_F_GSO\* * * @ifindex: interface index * @group: The group the device belongs to * * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * * @rx_dropped: Dropped packets by core network, * do not use this in drivers * @tx_dropped: Dropped packets by core network, * do not use this in drivers * @rx_nohandler: nohandler dropped packets by core network on * inactive devices, do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, * see <net/iw_handler.h> for details. * @wireless_data: Instance data managed by the core of wireless extensions * * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour * discovery handling. Necessary for e.g. 6LoWPAN. * @xfrmdev_ops: Transformation offload operations * @tlsdev_ops: Transport Layer Security offload operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * * @flags: Interface flags (a la BSD) * @priv_flags: Like 'flags' but invisible to userspace, * see if.h for the definitions * @gflags: Global flags ( kept as legacy ) * @padded: How much padding added by alloc_netdev() * @operstate: RFC2863 operstate * @link_mode: Mapping policy to operstate * @if_port: Selectable AUI, TP, ... * @dma: DMA channel * @mtu: Interface MTU value * @min_mtu: Interface Minimum MTU value * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed * @needed_tailroom: Extra tailroom the hardware may need, but not in all * cases can this be guaranteed. Some cases also use * LL_MAX_HEADER instead to allocate the skb * * interface address info: * * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length * @upper_level: Maximum depth level of upper devices. * @lower_level: Maximum depth level of lower devices. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one * @name_assign_type: network interface name assignment type * @uc_promisc: Counter that indicates promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that * does not implement ndo_set_rx_mode() * @uc: unicast mac addresses * @mc: multicast mac addresses * @dev_addrs: list of device hw addresses * @queues_kset: Group of all Kobjects in the Tx and RX queues * @promiscuity: Number of times the NIC is told to work in * promiscuous mode; if it becomes 0 the NIC will * exit promiscuous mode * @allmulti: Counter, enables or disables allmulticast mode * * @vlan_info: VLAN info * @dsa_ptr: dsa specific data * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network * device struct * @mpls_ptr: mpls_dev struct pointer * * @dev_addr: Hw address (before bcast, * because most packets are unicast) * * @_rx: Array of RX queues * @num_rx_queues: Number of RX queues * allocated at register_netdev() time * @real_num_rx_queues: Number of RX queues currently active in device * @xdp_prog: XDP sockets filter program pointer * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one * @miniq_ingress: ingress/clsact qdisc specific data for * ingress processing * @ingress_queue: XXX: need comments on this one * @nf_hooks_ingress: netfilter hooks executed for ingress packets * @broadcast: hw bcast address * * @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts, * indexed by RX queue number. Assigned by driver. * This must only be set if the ndo_rx_flow_steer * operation is defined * @index_hlist: Device index hash chain * * @_tx: Array of TX queues * @num_tx_queues: Number of TX queues allocated at alloc_netdev_mq() time * @real_num_tx_queues: Number of TX queues currently active in device * @qdisc: Root qdisc from userspace point of view * @tx_queue_len: Max frames per queue allowed * @tx_global_lock: XXX: need comments on this one * @xdp_bulkq: XDP device bulk queue * @xps_cpus_map: all CPUs map for XPS device * @xps_rxqs_map: all RXQs map for XPS device * * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * * @reg_state: Register/unregister state machine * @dismantle: Device is going to be freed * @rtnl_link_state: This enum represents the phases of creating * a new link * * @needs_free_netdev: Should unregister perform free_netdev? * @priv_destructor: Called from unregister * @npinfo: XXX: need comments on this one * @nd_net: Network namespace this network device is inside * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type * @lstats: Loopback statistics * @tstats: Tunnel statistics * @dstats: Dummy statistics * @vstats: Virtual ethernet statistics * * @garp_port: GARP * @mrp_port: MRP * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * * @gso_max_size: Maximum size of generic segmentation offload * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device * @tc_to_txq: XXX: need comments on this one * @prio_tc_map: XXX: need comments on this one * * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the * switch port. * * @wol_enabled: Wake-on-LAN is enabled * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. * * @macsec_ops: MACsec offloading ops * * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * * @nested_level: Used as as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ struct net_device { char name[IFNAMSIZ]; struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one */ unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; int irq; /* * Some hardware also needs these fields (state,dev_list, * napi_list,unreg_list,close_list) but they are not * part of the usual set specified in Space.c. */ unsigned long state; struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; struct list_head ptype_all; struct list_head ptype_specific; struct { struct list_head upper; struct list_head lower; } adj_list; netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; netdev_features_t vlan_features; netdev_features_t hw_enc_features; netdev_features_t mpls_features; netdev_features_t gso_partial_features; int ifindex; int group; struct net_device_stats stats; atomic_long_t rx_dropped; atomic_long_t tx_dropped; atomic_long_t rx_nohandler; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; atomic_t carrier_down_count; #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def *wireless_handlers; struct iw_public_data *wireless_data; #endif const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; #endif #if IS_ENABLED(CONFIG_IPV6) const struct ndisc_ops *ndisc_ops; #endif #ifdef CONFIG_XFRM_OFFLOAD const struct xfrmdev_ops *xfrmdev_ops; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) const struct tlsdev_ops *tlsdev_ops; #endif const struct header_ops *header_ops; unsigned int flags; unsigned int priv_flags; unsigned short gflags; unsigned short padded; unsigned char operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; /* Note : dev->mtu is often read without holding a lock. * Writers usually hold RTNL. * It is recommended to use READ_ONCE() to annotate the reads, * and to use WRITE_ONCE() to annotate the writes. */ unsigned int mtu; unsigned int min_mtu; unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; unsigned char min_header_len; unsigned char name_assign_type; unsigned short needed_headroom; unsigned short needed_tailroom; /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif #ifdef CONFIG_LOCKDEP struct list_head unlink_list; #endif unsigned int promiscuity; unsigned int allmulti; bool uc_promisc; #ifdef CONFIG_LOCKDEP unsigned char nested_level; #endif /* Protocol-specific pointers */ #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) struct dsa_port *dsa_ptr; #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif #if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif struct in_device __rcu *ip_ptr; struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; #endif struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif /* * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; struct netdev_rx_queue *_rx; unsigned int num_rx_queues; unsigned int real_num_rx_queues; struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_ingress; #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS struct nf_hook_entries __rcu *nf_hooks_ingress; #endif unsigned char broadcast[MAX_ADDR_LEN]; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rx_cpu_rmap; #endif struct hlist_node index_hlist; /* * Cache lines mostly used on transmit path */ struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; unsigned int real_num_tx_queues; struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; struct xdp_dev_bulk_queue __percpu *xdp_bulkq; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_cpus_map; struct xps_dev_maps __rcu *xps_rxqs_map; #endif #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; #endif #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; int watchdog_timeo; u32 proto_down_reason; struct list_head todo_list; int __percpu *pcpu_refcnt; struct list_head link_watch_list; enum { NETREG_UNINITIALIZED=0, NETREG_REGISTERED, /* completed register_netdevice */ NETREG_UNREGISTERING, /* called unregister_netdevice */ NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ NETREG_DUMMY, /* dummy device for NAPI poll */ } reg_state:8; bool dismantle; enum { RTNL_LINK_INITIALIZED, RTNL_LINK_INITIALIZING, } rtnl_link_state:16; bool needs_free_netdev; void (*priv_destructor)(struct net_device *dev); #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; #endif possible_net_t nd_net; /* mid-layer private */ void *ml_priv; enum netdev_ml_priv_type ml_priv_type; union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; #endif #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif struct device dev; const struct attribute_group *sysfs_groups[4]; const struct attribute_group *sysfs_rx_queue_group; const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif s16 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) unsigned int fcoe_ddp_xid; #endif #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; struct list_head net_notifier_list; #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; }; #define to_net_dev(d) container_of(d, struct net_device, dev) static inline bool netif_elide_gro(const struct net_device *dev) { if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) return true; return false; } #define NETDEV_ALIGN 32 static inline int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) { return dev->prio_tc_map[prio & TC_BITMASK]; } static inline int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) { if (tc >= dev->num_tc) return -EINVAL; dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; return 0; } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq); void netdev_reset_tc(struct net_device *dev); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); int netdev_set_num_tc(struct net_device *dev, u8 num_tc); static inline int netdev_get_num_tc(struct net_device *dev) { return dev->num_tc; } static inline void net_prefetch(void *p) { prefetch(p); #if L1_CACHE_BYTES < 128 prefetch((u8 *)p + L1_CACHE_BYTES); #endif } static inline void net_prefetchw(void *p) { prefetchw(p); #if L1_CACHE_BYTES < 128 prefetchw((u8 *)p + L1_CACHE_BYTES); #endif } void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset); int netdev_set_sb_channel(struct net_device *dev, u16 channel); static inline int netdev_get_sb_channel(struct net_device *dev) { return max_t(int, -dev->num_tc, 0); } static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { return &dev->_tx[index]; } static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev, const struct sk_buff *skb) { return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); } static inline void netdev_for_each_tx_queue(struct net_device *dev, void (*f)(struct net_device *, struct netdev_queue *, void *), void *arg) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) f(dev, &dev->_tx[i], arg); } #define netdev_lockdep_set_classes(dev) \ { \ static struct lock_class_key qdisc_tx_busylock_key; \ static struct lock_class_key qdisc_running_key; \ static struct lock_class_key qdisc_xmit_lock_key; \ static struct lock_class_key dev_addr_list_lock_key; \ unsigned int i; \ \ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ (dev)->qdisc_running_key = &qdisc_running_key; \ lockdep_set_class(&(dev)->addr_list_lock, \ &dev_addr_list_lock_key); \ for (i = 0; i < (dev)->num_tx_queues; i++) \ lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ &qdisc_xmit_lock_key); \ } u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev */ static inline unsigned netdev_get_fwd_headroom(struct net_device *dev) { return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom; } static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr) { if (dev->netdev_ops->ndo_set_rx_headroom) dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr); } /* set the device rx headroom to the dev's default */ static inline void netdev_reset_rx_headroom(struct net_device *dev) { netdev_set_rx_headroom(dev, -1); } static inline void *netdev_get_ml_priv(struct net_device *dev, enum netdev_ml_priv_type type) { if (dev->ml_priv_type != type) return NULL; return dev->ml_priv; } static inline void netdev_set_ml_priv(struct net_device *dev, void *ml_priv, enum netdev_ml_priv_type type) { WARN(dev->ml_priv_type && dev->ml_priv_type != type, "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", dev->ml_priv_type, type); WARN(!dev->ml_priv_type && dev->ml_priv, "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); dev->ml_priv = ml_priv; dev->ml_priv_type = type; } /* * Net namespace inlines */ static inline struct net *dev_net(const struct net_device *dev) { return read_pnet(&dev->nd_net); } static inline struct net *dev_net_rcu(const struct net_device *dev) { return read_pnet_rcu(&dev->nd_net); } static inline void dev_net_set(struct net_device *dev, struct net *net) { write_pnet(&dev->nd_net, net); } /** * netdev_priv - access network device private data * @dev: network device * * Get network device private data */ static inline void *netdev_priv(const struct net_device *dev) { return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN); } /* Set the sysfs physical device reference for the network logical device * if set prior to registration will cause a symlink during initialization. */ #define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev)) /* Set the sysfs device type for the network logical device to allow * fine-grained identification of different network device types. For * example Ethernet, Wireless LAN, Bluetooth, WiMAX etc. */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 /** * netif_napi_add - initialize a NAPI context * @dev: network device * @napi: NAPI context * @poll: polling function * @weight: default weight * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); /** * netif_tx_napi_add - initialize a NAPI context * @dev: network device * @napi: NAPI context * @poll: polling function * @weight: default weight * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ static inline void netif_tx_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); netif_napi_add(dev, napi, poll, weight); } /** * __netif_napi_del - remove a NAPI context * @napi: NAPI context * * Warning: caller must observe RCU grace period before freeing memory * containing @napi. Drivers might want to call this helper to combine * all the needed RCU grace periods into a single one. */ void __netif_napi_del(struct napi_struct *napi); /** * netif_napi_del - remove a NAPI context * @napi: NAPI context * * netif_napi_del() removes a NAPI context from the network device NAPI list */ static inline void netif_napi_del(struct napi_struct *napi) { __netif_napi_del(napi); synchronize_net(); } struct napi_gro_cb { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ void *frag0; /* Length of frag0. */ unsigned int frag0_len; /* This indicates where we are processing relative to skb->data. */ int data_offset; /* This is non-zero if the packet cannot be merged with the new skb. */ u16 flush; /* Save the IP ID here and check when we get to the transport layer */ u16 flush_id; /* Number of segments aggregated. */ u16 count; /* Start offset for remote checksum offload */ u16 gro_remcsum_start; /* jiffies when first packet was created/queued */ unsigned long age; /* Used in ipv6_gro_receive() and foo-over-udp */ u16 proto; /* This is non-zero if the packet may be of the same flow. */ u8 same_flow:1; /* Used in tunnel GRO receive */ u8 encap_mark:1; /* GRO checksum is valid */ u8 csum_valid:1; /* Number of checksums via CHECKSUM_UNNECESSARY */ u8 csum_cnt:3; /* Free the skb? */ u8 free:2; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 /* Used in foo-over-udp, set in udp[46]_gro_receive */ u8 is_ipv6:1; /* Used in GRE, set in fou/gue_gro_receive */ u8 is_fou:1; /* Used to determine if flush_id can be ignored */ u8 is_atomic:1; /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; /* GRO is done by frag_list pointer chaining. */ u8 is_flist:1; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; /* used in skb_gro_receive() slow path */ struct sk_buff *last; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) #define GRO_RECURSION_LIMIT 15 static inline int gro_recursion_inc_test(struct sk_buff *skb) { return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; } typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); static inline struct sk_buff *call_gro_receive(gro_receive_t cb, struct list_head *head, struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; return NULL; } return cb(head, skb); } typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, struct sk_buff *); static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, struct sock *sk, struct list_head *head, struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; return NULL; } return cb(sk, head, skb); } struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void (*list_func) (struct list_head *, struct packet_type *, struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); struct sk_buff *(*gro_receive)(struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; struct packet_offload { __be16 type; /* This is really htons(ether_type). */ u16 priority; struct offload_callbacks callbacks; struct list_head list; }; /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { u64 rx_packets; u64 rx_bytes; u64 tx_packets; u64 tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_bytes += len; tstats->rx_packets++; u64_stats_update_end(&tstats->syncp); } static inline void dev_lstats_add(struct net_device *dev, unsigned int len) { struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&lstats->syncp); u64_stats_add(&lstats->bytes, len); u64_stats_inc(&lstats->packets); u64_stats_update_end(&lstats->syncp); } #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ if (pcpu_stats) { \ int __cpu; \ for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ pcpu_stats; \ }) #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL) enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_UNKNOWN, NETDEV_LAG_TX_TYPE_RANDOM, NETDEV_LAG_TX_TYPE_BROADCAST, NETDEV_LAG_TX_TYPE_ROUNDROBIN, NETDEV_LAG_TX_TYPE_ACTIVEBACKUP, NETDEV_LAG_TX_TYPE_HASH, }; enum netdev_lag_hash { NETDEV_LAG_HASH_NONE, NETDEV_LAG_HASH_L2, NETDEV_LAG_HASH_L34, NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, NETDEV_LAG_HASH_UNKNOWN, }; struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; enum netdev_lag_hash hash_type; }; struct netdev_lag_lower_state_info { u8 link_up : 1, tx_enabled : 1; }; #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update netdev_cmd_to_name() * and the rtnetlink notification exclusion list in rtnetlink_event() when * adding new types. */ enum netdev_cmd { NETDEV_UP = 1, /* For now you can't veto a device up/down */ NETDEV_DOWN, NETDEV_REBOOT, /* Tell a protocol stack a network interface detected a hardware crash and restarted - we can use this eg to kick tcp sessions once done */ NETDEV_CHANGE, /* Notify device state change */ NETDEV_REGISTER, NETDEV_UNREGISTER, NETDEV_CHANGEMTU, /* notify after mtu change happened */ NETDEV_CHANGEADDR, /* notify after the address change */ NETDEV_PRE_CHANGEADDR, /* notify before the address change */ NETDEV_GOING_DOWN, NETDEV_CHANGENAME, NETDEV_FEAT_CHANGE, NETDEV_BONDING_FAILOVER, NETDEV_PRE_UP, NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, NETDEV_CHANGEUPPER, NETDEV_RESEND_IGMP, NETDEV_PRECHANGEMTU, /* notify before mtu change happened */ NETDEV_CHANGEINFODATA, NETDEV_BONDING_INFO, NETDEV_PRECHANGEUPPER, NETDEV_CHANGELOWERSTATE, NETDEV_UDP_TUNNEL_PUSH_INFO, NETDEV_UDP_TUNNEL_DROP_INFO, NETDEV_CHANGE_TX_QUEUE_LEN, NETDEV_CVLAN_FILTER_PUSH_INFO, NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); struct netdev_notifier_info { struct net_device *dev; struct netlink_ext_ack *extack; }; struct netdev_notifier_info_ext { struct netdev_notifier_info info; /* must be first */ union { u32 mtu; } ext; }; struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; }; struct netdev_notifier_changeupper_info { struct netdev_notifier_info info; /* must be first */ struct net_device *upper_dev; /* new upper dev */ bool master; /* is upper dev master */ bool linking; /* is the notification for link or unlink */ void *upper_info; /* upper dev info */ }; struct netdev_notifier_changelowerstate_info { struct netdev_notifier_info info; /* must be first */ void *lower_state_info; /* is lower dev state */ }; struct netdev_notifier_pre_changeaddr_info { struct netdev_notifier_info info; /* must be first */ const unsigned char *dev_addr; }; static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; info->extack = NULL; } static inline struct net_device * netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) { return info->dev; } static inline struct netlink_ext_ack * netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) { return info->extack; } int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_rcu(net, d) \ list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_safe(net, d, n) \ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue_reverse(net, d) \ list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ for_each_netdev_rcu(&init_net, slave) \ if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) static inline struct net_device *next_net_device(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = dev->dev_list.next; return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *next_net_device_rcu(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *first_net_device(struct net *net) { return list_empty(&net->dev_base_head) ? NULL : net_device_entry(net->dev_base_head.next); } static inline struct net_device *first_net_device_rcu(struct net *net) { struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } int netdev_boot_setup_check(struct net_device *dev); unsigned long netdev_boot_base(const char *prefix, int unit); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); void dev_add_pack(struct packet_type *pt); void dev_remove_pack(struct packet_type *pt); void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { int ret; ret = __dev_direct_xmit(skb, queue_id); if (!dev_xmit_complete(ret)) kfree_skb(skb); return ret; } int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); static inline void unregister_netdevice(struct net_device *dev) { unregister_netdevice_queue(dev, NULL); } int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); void netdev_freemem(struct net_device *dev); int init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { return NAPI_GRO_CB(skb)->data_offset; } static inline unsigned int skb_gro_len(const struct sk_buff *skb) { return skb->len - NAPI_GRO_CB(skb)->data_offset; } static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) { NAPI_GRO_CB(skb)->data_offset += len; } static inline void *skb_gro_header_fast(struct sk_buff *skb, unsigned int offset) { return NAPI_GRO_CB(skb)->frag0 + offset; } static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) { return NAPI_GRO_CB(skb)->frag0_len < hlen; } static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) { NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; } static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { if (!pskb_may_pull(skb, hlen)) return NULL; skb_gro_frag0_invalidate(skb); return skb->data + offset; } static inline void *skb_gro_network_header(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + skb_network_offset(skb); } static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (NAPI_GRO_CB(skb)->csum_valid) NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, csum_partial(start, len, 0)); } /* GRO checksum functions. These are logical equivalents of the normal * checksum functions (in skbuff.h) except that they operate on the GRO * offsets and fields in sk_buff. */ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb); static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); } static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { return ((skb->ip_summed != CHECKSUM_PARTIAL || skb_checksum_start_offset(skb) < skb_gro_offset(skb)) && !skb_at_gro_remcsum_start(skb) && NAPI_GRO_CB(skb)->csum_cnt == 0 && (!zero_okay || check)); } static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, __wsum psum) { if (NAPI_GRO_CB(skb)->csum_valid && !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) return 0; NAPI_GRO_CB(skb)->csum = psum; return __skb_gro_checksum_complete(skb); } static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->csum_cnt > 0) { /* Consume a checksum from CHECKSUM_UNNECESSARY */ NAPI_GRO_CB(skb)->csum_cnt--; } else { /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we * verified a new top level checksum or an encapsulated one * during GRO. This saves work if we fallback to normal path. */ __skb_incr_checksum_unnecessary(skb); } } #define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ compute_pseudo) \ ({ \ __sum16 __ret = 0; \ if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_gro_checksum_validate_complete(skb, \ compute_pseudo(skb, proto)); \ if (!__ret) \ skb_gro_incr_csum_unnecessary(skb); \ __ret; \ }) #define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) #define skb_gro_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) #define skb_gro_checksum_simple_validate(skb) \ __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid); } static inline void __skb_gro_checksum_convert(struct sk_buff *skb, __wsum pseudo) { NAPI_GRO_CB(skb)->csum = ~pseudo; NAPI_GRO_CB(skb)->csum_valid = 1; } #define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_gro_checksum_convert_check(skb)) \ __skb_gro_checksum_convert(skb, \ compute_pseudo(skb, proto)); \ } while (0) struct gro_remcsum { int offset; __wsum delta; }; static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) { grc->offset = 0; grc->delta = 0; } static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, unsigned int off, size_t hdrlen, int start, int offset, struct gro_remcsum *grc, bool nopartial) { __wsum delta; size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); if (!nopartial) { NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; return ptr; } ptr = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, off + plen)) { ptr = skb_gro_header_slow(skb, off + plen, off); if (!ptr) return NULL; } delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, start, offset); /* Adjust skb->csum since we changed the packet */ NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); grc->offset = off + hdrlen + offset; grc->delta = delta; return ptr; } static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, struct gro_remcsum *grc) { void *ptr; size_t plen = grc->offset + sizeof(u16); if (!grc->delta) return; ptr = skb_gro_header_fast(skb, grc->offset); if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { ptr = skb_gro_header_slow(skb, plen, grc->offset); if (!ptr) return; } remcsum_unadjust((__sum16 *)ptr, grc->delta); } #ifdef CONFIG_XFRM_OFFLOAD static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, struct sk_buff *pp, int flush, struct gro_remcsum *grc) { if (PTR_ERR(pp) != -EINPROGRESS) { NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, grc); skb->remcsum_offload = 0; } } #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, struct sk_buff *pp, int flush, struct gro_remcsum *grc) { NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, grc); skb->remcsum_offload = 0; } #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { if (!dev->header_ops || !dev->header_ops->create) return 0; return dev->header_ops->create(skb, dev, type, daddr, saddr, len); } static inline int dev_parse_header(const struct sk_buff *skb, unsigned char *haddr) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse) return 0; return dev->header_ops->parse(skb, haddr); } static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse_protocol) return 0; return dev->header_ops->parse_protocol(skb); } /* ll_header must have at least hard_header_len allocated */ static inline bool dev_validate_header(const struct net_device *dev, char *ll_header, int len) { if (likely(len >= dev->hard_header_len)) return true; if (len < dev->min_header_len) return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); return true; } if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); return false; } static inline bool dev_has_header(const struct net_device *dev) { return dev->header_ops && dev->header_ops->create; } #ifdef CONFIG_NET_FLOW_LIMIT #define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ struct sd_flow_limit { u64 count; unsigned int num_buckets; unsigned int history_head; u16 history[FLOW_LIMIT_HISTORY]; u8 buckets[]; }; extern int netdev_flow_limit_table_len; #endif /* CONFIG_NET_FLOW_LIMIT */ /* * Incoming packets are placed on per-CPU queues */ struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; /* stats */ unsigned int processed; unsigned int time_squeeze; unsigned int received_rps; #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif struct Qdisc *output_queue; struct Qdisc **output_queue_tailp; struct sk_buff *completion_queue; #ifdef CONFIG_XFRM_OFFLOAD struct sk_buff_head xfrm_backlog; #endif /* written and read only by owning cpu: */ struct { u16 recursion; u8 more; } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. */ unsigned int input_queue_head ____cacheline_aligned_in_smp; /* Elements below can be accessed between CPUs for RPS/RFS */ call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; unsigned int input_queue_tail; #endif unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; }; static inline void input_queue_head_incr(struct softnet_data *sd) { #ifdef CONFIG_RPS sd->input_queue_head++; #endif } static inline void input_queue_tail_incr_save(struct softnet_data *sd, unsigned int *qtail) { #ifdef CONFIG_RPS *qtail = ++sd->input_queue_tail; #endif } DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } #define XMIT_RECURSION_LIMIT 8 static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > XMIT_RECURSION_LIMIT); } static inline void dev_xmit_recursion_inc(void) { __this_cpu_inc(softnet_data.xmit.recursion); } static inline void dev_xmit_recursion_dec(void) { __this_cpu_dec(softnet_data.xmit.recursion); } void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); static inline void netif_tx_schedule_all(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) netif_schedule_queue(netdev_get_tx_queue(dev, i)); } static __always_inline void netif_tx_start_queue(struct netdev_queue *dev_queue) { clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_start_queue - allow transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. */ static inline void netif_start_queue(struct net_device *dev) { netif_tx_start_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif_tx_start_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_start_queue(txq); } } void netif_tx_wake_queue(struct netdev_queue *dev_queue); /** * netif_wake_queue - restart transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. * Used for flow control when transmit resources are available. */ static inline void netif_wake_queue(struct net_device *dev) { netif_tx_wake_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif_tx_wake_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_wake_queue(txq); } } static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_stop_queue - stop transmitted packets * @dev: network device * * Stop upper layers calling the device hard_start_xmit routine. * Used for flow control when transmit resources are unavailable. */ static inline void netif_stop_queue(struct net_device *dev) { netif_tx_stop_queue(netdev_get_tx_queue(dev, 0)); } void netif_tx_stop_all_queues(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_queue_stopped - test if transmit queue is flowblocked * @dev: network device * * Test if transmit queue on device is currently unable to send. */ static inline bool netif_queue_stopped(const struct net_device *dev) { return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0)); } static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF; } static inline bool netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN; } static inline bool netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN; } /** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their ndo_start_xmit(), * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue) { #ifdef CONFIG_BQL prefetchw(&dev_queue->dql.num_queued); #endif } /** * netdev_txq_bql_complete_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their TX completion path, * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue) { #ifdef CONFIG_BQL prefetchw(&dev_queue->dql.limit); #endif } static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { #ifdef CONFIG_BQL dql_queued(&dev_queue->dql, bytes); if (likely(dql_avail(&dev_queue->dql) >= 0)) return; set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* * The XOFF flag must be set before checking the dql_avail below, * because in netdev_tx_completed_queue we update the dql_completed * before checking the XOFF flag. */ smp_mb(); /* check again in case another CPU has just made room avail */ if (unlikely(dql_avail(&dev_queue->dql) >= 0)) clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); #endif } /* Variant of netdev_tx_sent_queue() for drivers that are aware * that they should not test BQL status themselves. * We do want to change __QUEUE_STATE_STACK_XOFF only for the last * skb of a batch. * Returns true if the doorbell must be used to kick the NIC. */ static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes, bool xmit_more) { if (xmit_more) { #ifdef CONFIG_BQL dql_queued(&dev_queue->dql, bytes); #endif return netif_tx_queue_stopped(dev_queue); } netdev_tx_sent_queue(dev_queue, bytes); return true; } /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device * @bytes: number of bytes queued to the hardware device queue * * Report the number of bytes queued for sending/completion to the network * device hardware queue. @bytes should be a good approximation and should * exactly match netdev_completed_queue() @bytes */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); } static inline bool __netdev_sent_queue(struct net_device *dev, unsigned int bytes, bool xmit_more) { return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes, xmit_more); } static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { #ifdef CONFIG_BQL if (unlikely(!bytes)) return; dql_completed(&dev_queue->dql, bytes); /* * Without the memory barrier there is a small possiblity that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ smp_mb(); if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state)) netif_schedule_queue(dev_queue); #endif } /** * netdev_completed_queue - report bytes and packets completed by device * @dev: network device * @pkts: actual number of packets sent over the medium * @bytes: actual number of bytes sent over the medium * * Report the number of bytes and packets transmitted by the network device * hardware queue over the physical medium, @bytes must exactly match the * @bytes amount passed to netdev_sent_queue() */ static inline void netdev_completed_queue(struct net_device *dev, unsigned int pkts, unsigned int bytes) { netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes); } static inline void netdev_tx_reset_queue(struct netdev_queue *q) { #ifdef CONFIG_BQL clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state); dql_reset(&q->dql); #endif } /** * netdev_reset_queue - reset the packets and bytes count of a network device * @dev_queue: network device * * Reset the bytes and packet count of a network device and clear the * software flow control OFF bit for this network device */ static inline void netdev_reset_queue(struct net_device *dev_queue) { netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); } /** * netdev_cap_txqueue - check if selected tx queue exceeds device queues * @dev: network device * @queue_index: given tx queue index * * Returns 0 if given tx queue index >= number of device tx queues, * otherwise returns the originally passed tx queue index. */ static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) { if (unlikely(queue_index >= dev->real_num_tx_queues)) { net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", dev->name, queue_index, dev->real_num_tx_queues); return 0; } return queue_index; } /** * netif_running - test if up * @dev: network device * * Test if the device has been brought up. */ static inline bool netif_running(const struct net_device *dev) { return test_bit(__LINK_STATE_START, &dev->state); } /* * Routines to manage the subqueues on a device. We only need start, * stop, and a check if it's stopped. All other device management is * done at the overall netdevice level. * Also test the device if we're multiqueue. */ /** * netif_start_subqueue - allow sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Start individual transmit queue of a device with multiple transmit queues. */ static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_start_queue(txq); } /** * netif_stop_subqueue - stop sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Stop individual transmit queue of a device with multiple transmit queues. */ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_stop_queue(txq); } /** * netif_subqueue_stopped - test status of subqueue * @dev: network device * @queue_index: sub queue index * * Check individual transmit queue of a device with multiple transmit queues. */ static inline bool __netif_subqueue_stopped(const struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); return netif_tx_queue_stopped(txq); } static inline bool netif_subqueue_stopped(const struct net_device *dev, struct sk_buff *skb) { return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } /** * netif_wake_subqueue - allow sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Resume individual transmit queue of a device with multiple transmit queues. */ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_wake_queue(txq); } #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, bool is_rxqs_map); /** * netif_attr_test_mask - Test a CPU or Rx queue set in a mask * @j: CPU/Rx queue index * @mask: bitmask of all cpus/rx queues * @nr_bits: number of bits in the bitmask * * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. */ static inline bool netif_attr_test_mask(unsigned long j, const unsigned long *mask, unsigned int nr_bits) { cpu_max_bits_warn(j, nr_bits); return test_bit(j, mask); } /** * netif_attr_test_online - Test for online CPU/Rx queue * @j: CPU/Rx queue index * @online_mask: bitmask for CPUs/Rx queues that are online * @nr_bits: number of bits in the bitmask * * Returns true if a CPU/Rx queue is online. */ static inline bool netif_attr_test_online(unsigned long j, const unsigned long *online_mask, unsigned int nr_bits) { cpu_max_bits_warn(j, nr_bits); if (online_mask) return test_bit(j, online_mask); return (j < nr_bits); } /** * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask * @n: CPU/Rx queue index * @srcp: the cpumask/Rx queue mask pointer * @nr_bits: number of bits in the bitmask * * Returns >= nr_bits if no further CPUs/Rx queues set. */ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { /* -1 is a legal arg here. */ if (n != -1) cpu_max_bits_warn(n, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); return n + 1; } /** * netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p * @n: CPU/Rx queue index * @src1p: the first CPUs/Rx queues mask pointer * @src2p: the second CPUs/Rx queues mask pointer * @nr_bits: number of bits in the bitmask * * Returns >= nr_bits if no further CPUs/Rx queues set in both. */ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { /* -1 is a legal arg here. */ if (n != -1) cpu_max_bits_warn(n, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); else if (src1p) return find_next_bit(src1p, nr_bits, n + 1); else if (src2p) return find_next_bit(src2p, nr_bits, n + 1); return n + 1; } #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { return 0; } static inline int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, bool is_rxqs_map) { return 0; } #endif /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device * * Check if device has multiple transmit queues */ static inline bool netif_is_multiqueue(const struct net_device *dev) { return dev->num_tx_queues > 1; } int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); #ifdef CONFIG_SYSFS int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxqs) { dev->real_num_rx_queues = rxqs; return 0; } #endif static inline struct netdev_rx_queue * __netif_get_rx_queue(struct net_device *dev, unsigned int rxq) { return dev->_rx + rxq; } #ifdef CONFIG_SYSFS static inline unsigned int get_netdev_rx_queue_index( struct netdev_rx_queue *queue) { struct net_device *dev = queue->dev; int index = queue - dev->_rx; BUG_ON(index >= dev->num_rx_queues); return index; } #endif #define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); enum skb_free_reason { SKB_REASON_CONSUMED, SKB_REASON_DROPPED, }; void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason); void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware * interrupt context or with hardware interrupts being disabled. * (in_irq() || irqs_disabled()) * * We provide four helpers that can be used in following contexts : * * dev_kfree_skb_irq(skb) when caller drops a packet from irq context, * replacing kfree_skb(skb) * * dev_consume_skb_irq(skb) when caller consumes a packet from irq context. * Typically used in place of consume_skb(skb) in TX completion path * * dev_kfree_skb_any(skb) when caller doesn't know its current irq context, * replacing kfree_skb(skb) * * dev_consume_skb_any(skb) when caller doesn't know its current irq context, * and consumed a packet. Used in place of consume_skb(skb) */ static inline void dev_kfree_skb_irq(struct sk_buff *skb) { __dev_kfree_skb_irq(skb, SKB_REASON_DROPPED); } static inline void dev_consume_skb_irq(struct sk_buff *skb) { __dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED); } static inline void dev_kfree_skb_any(struct sk_buff *skb) { __dev_kfree_skb_any(skb, SKB_REASON_DROPPED); } static inline void dev_consume_skb_any(struct sk_buff *skb) { __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_rx_any_context(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); struct packet_offload *gro_find_receive_by_type(__be16 type); struct packet_offload *gro_find_complete_by_type(__be16 type); static inline void napi_free_frags(struct napi_struct *napi) { kfree_skb(napi->skb); napi->skb = NULL; } bool netdev_is_rx_handler_busy(struct net_device *dev); int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data); void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); static inline bool is_socket_ioctl_cmd(unsigned int cmd) { return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; } int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf *, int); int dev_ethtool(struct net *net, struct ifreq *); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); int dev_validate_mtu(struct net_device *dev, int mtu, struct netlink_ext_ack *extack); int dev_set_mtu_ext(struct net_device *dev, int mtu, struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); int dev_change_tx_queue_len(struct net_device *, unsigned long); void dev_set_group(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { if (skb_orphan_frags(skb, GFP_ATOMIC) || unlikely(!is_skb_forwardable(dev, skb))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); /** * dev_put - release reference to device * @dev: network device * * Release reference to device to allow it to be freed. */ static inline void dev_put(struct net_device *dev) { if (dev) this_cpu_dec(*dev->pcpu_refcnt); } /** * dev_hold - get reference to device * @dev: network device * * Hold reference to device to keep it from being freed. */ static inline void dev_hold(struct net_device *dev) { if (dev) this_cpu_inc(*dev->pcpu_refcnt); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. * * The name carrier is inappropriate, these functions should really be * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ void linkwatch_init_dev(struct net_device *dev); void linkwatch_fire_event(struct net_device *dev); void linkwatch_forget_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present * @dev: network device * * Check if carrier is present on device */ static inline bool netif_carrier_ok(const struct net_device *dev) { return !test_bit(__LINK_STATE_NOCARRIER, &dev->state); } unsigned long dev_trans_start(struct net_device *dev); void __netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); void netif_carrier_off(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. * @dev: network device * * Mark device as dormant (as per RFC2863). * * The dormant state indicates that the relevant interface is not * actually in a condition to pass packets (i.e., it is not 'up') but is * in a "pending" state, waiting for some external event. For "on- * demand" interfaces, this new state identifies the situation where the * interface is waiting for events to place it in the up state. */ static inline void netif_dormant_on(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state)) linkwatch_fire_event(dev); } /** * netif_dormant_off - set device as not dormant. * @dev: network device * * Device is not in dormant state. */ static inline void netif_dormant_off(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state)) linkwatch_fire_event(dev); } /** * netif_dormant - test if device is dormant * @dev: network device * * Check if device is dormant. */ static inline bool netif_dormant(const struct net_device *dev) { return test_bit(__LINK_STATE_DORMANT, &dev->state); } /** * netif_testing_on - mark device as under test. * @dev: network device * * Mark device as under test (as per RFC2863). * * The testing state indicates that some test(s) must be performed on * the interface. After completion, of the test, the interface state * will change to up, dormant, or down, as appropriate. */ static inline void netif_testing_on(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) linkwatch_fire_event(dev); } /** * netif_testing_off - set device as not under test. * @dev: network device * * Device is not in testing state. */ static inline void netif_testing_off(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) linkwatch_fire_event(dev); } /** * netif_testing - test if device is under test * @dev: network device * * Check if device is under test */ static inline bool netif_testing(const struct net_device *dev) { return test_bit(__LINK_STATE_TESTING, &dev->state); } /** * netif_oper_up - test if device is operational * @dev: network device * * Check if carrier is operational */ static inline bool netif_oper_up(const struct net_device *dev) { return (dev->operstate == IF_OPER_UP || dev->operstate == IF_OPER_UNKNOWN /* backward compat */); } /** * netif_device_present - is device available or removed * @dev: network device * * Check if device has not been removed from system. */ static inline bool netif_device_present(struct net_device *dev) { return test_bit(__LINK_STATE_PRESENT, &dev->state); } void netif_device_detach(struct net_device *dev); void netif_device_attach(struct net_device *dev); /* * Network interface message level settings */ enum { NETIF_MSG_DRV_BIT, NETIF_MSG_PROBE_BIT, NETIF_MSG_LINK_BIT, NETIF_MSG_TIMER_BIT, NETIF_MSG_IFDOWN_BIT, NETIF_MSG_IFUP_BIT, NETIF_MSG_RX_ERR_BIT, NETIF_MSG_TX_ERR_BIT, NETIF_MSG_TX_QUEUED_BIT, NETIF_MSG_INTR_BIT, NETIF_MSG_TX_DONE_BIT, NETIF_MSG_RX_STATUS_BIT, NETIF_MSG_PKTDATA_BIT, NETIF_MSG_HW_BIT, NETIF_MSG_WOL_BIT, /* When you add a new bit above, update netif_msg_class_names array * in net/ethtool/common.c */ NETIF_MSG_CLASS_COUNT, }; /* Both ethtool_ops interface and internal driver implementation use u32 */ static_assert(NETIF_MSG_CLASS_COUNT <= 32); #define __NETIF_MSG_BIT(bit) ((u32)1 << (bit)) #define __NETIF_MSG(name) __NETIF_MSG_BIT(NETIF_MSG_ ## name ## _BIT) #define NETIF_MSG_DRV __NETIF_MSG(DRV) #define NETIF_MSG_PROBE __NETIF_MSG(PROBE) #define NETIF_MSG_LINK __NETIF_MSG(LINK) #define NETIF_MSG_TIMER __NETIF_MSG(TIMER) #define NETIF_MSG_IFDOWN __NETIF_MSG(IFDOWN) #define NETIF_MSG_IFUP __NETIF_MSG(IFUP) #define NETIF_MSG_RX_ERR __NETIF_MSG(RX_ERR) #define NETIF_MSG_TX_ERR __NETIF_MSG(TX_ERR) #define NETIF_MSG_TX_QUEUED __NETIF_MSG(TX_QUEUED) #define NETIF_MSG_INTR __NETIF_MSG(INTR) #define NETIF_MSG_TX_DONE __NETIF_MSG(TX_DONE) #define NETIF_MSG_RX_STATUS __NETIF_MSG(RX_STATUS) #define NETIF_MSG_PKTDATA __NETIF_MSG(PKTDATA) #define NETIF_MSG_HW __NETIF_MSG(HW) #define NETIF_MSG_WOL __NETIF_MSG(WOL) #define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV) #define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE) #define netif_msg_link(p) ((p)->msg_enable & NETIF_MSG_LINK) #define netif_msg_timer(p) ((p)->msg_enable & NETIF_MSG_TIMER) #define netif_msg_ifdown(p) ((p)->msg_enable & NETIF_MSG_IFDOWN) #define netif_msg_ifup(p) ((p)->msg_enable & NETIF_MSG_IFUP) #define netif_msg_rx_err(p) ((p)->msg_enable & NETIF_MSG_RX_ERR) #define netif_msg_tx_err(p) ((p)->msg_enable & NETIF_MSG_TX_ERR) #define netif_msg_tx_queued(p) ((p)->msg_enable & NETIF_MSG_TX_QUEUED) #define netif_msg_intr(p) ((p)->msg_enable & NETIF_MSG_INTR) #define netif_msg_tx_done(p) ((p)->msg_enable & NETIF_MSG_TX_DONE) #define netif_msg_rx_status(p) ((p)->msg_enable & NETIF_MSG_RX_STATUS) #define netif_msg_pktdata(p) ((p)->msg_enable & NETIF_MSG_PKTDATA) #define netif_msg_hw(p) ((p)->msg_enable & NETIF_MSG_HW) #define netif_msg_wol(p) ((p)->msg_enable & NETIF_MSG_WOL) static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) { /* use default */ if (debug_value < 0 || debug_value >= (sizeof(u32) * 8)) return default_msg_enable_bits; if (debug_value == 0) /* no output */ return 0; /* set low N bits */ return (1U << debug_value) - 1; } static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) { __acquire(&txq->_xmit_lock); return true; } static inline void __netif_tx_release(struct netdev_queue *txq) { __release(&txq->_xmit_lock); } static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } static inline void txq_trans_update(struct netdev_queue *txq) { if (txq->xmit_lock_owner != -1) txq->trans_start = jiffies; } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); if (txq->trans_start != jiffies) txq->trans_start = jiffies; } /** * netif_tx_lock - grab network device transmit lock * @dev: network device * * Get network device transmit lock */ static inline void netif_tx_lock(struct net_device *dev) { unsigned int i; int cpu; spin_lock(&dev->tx_global_lock); cpu = smp_processor_id(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* We are the only thread of execution doing a * freeze, but we have to grab the _xmit_lock in * order to synchronize with threads which are in * the ->hard_start_xmit() handler and already * checked the frozen bit. */ __netif_tx_lock(txq, cpu); set_bit(__QUEUE_STATE_FROZEN, &txq->state); __netif_tx_unlock(txq); } } static inline void netif_tx_lock_bh(struct net_device *dev) { local_bh_disable(); netif_tx_lock(dev); } static inline void netif_tx_unlock(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* No need to grab the _xmit_lock here. If the * queue is not stopped for another reason, we * force a schedule. */ clear_bit(__QUEUE_STATE_FROZEN, &txq->state); netif_schedule_queue(txq); } spin_unlock(&dev->tx_global_lock); } static inline void netif_tx_unlock_bh(struct net_device *dev) { netif_tx_unlock(dev); local_bh_enable(); } #define HARD_TX_LOCK(dev, txq, cpu) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_lock(txq, cpu); \ } else { \ __netif_tx_acquire(txq); \ } \ } #define HARD_TX_TRYLOCK(dev, txq) \ (((dev->features & NETIF_F_LLTX) == 0) ? \ __netif_tx_trylock(txq) : \ __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_unlock(txq); \ } else { \ __netif_tx_release(txq); \ } \ } static inline void netif_tx_disable(struct net_device *dev) { unsigned int i; int cpu; local_bh_disable(); cpu = smp_processor_id(); spin_lock(&dev->tx_global_lock); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); __netif_tx_lock(txq, cpu); netif_tx_stop_queue(txq); __netif_tx_unlock(txq); } spin_unlock(&dev->tx_global_lock); local_bh_enable(); } static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; #ifdef CONFIG_LOCKDEP nest_level = dev->nested_level; #endif spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { unsigned char nest_level = 0; #ifdef CONFIG_LOCKDEP nest_level = dev->nested_level; #endif local_bh_disable(); spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) { spin_unlock(&dev->addr_list_lock); } static inline void netif_addr_unlock_bh(struct net_device *dev) { spin_unlock_bh(&dev->addr_list_lock); } /* * dev_addrs walker. Should be used only for read access. Call with * rcu_read_lock held. */ #define for_each_dev_addr(dev, ha) \ list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list) /* These functions live elsewhere (drivers/net/net_init.c, but related) */ void ether_setup(struct net_device *dev); /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) #define alloc_netdev_mq(sizeof_priv, name, name_assign_type, setup, count) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, count, \ count) int register_netdev(struct net_device *dev); void unregister_netdev(struct net_device *dev); int devm_register_netdev(struct device *dev, struct net_device *ndev); /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)); int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)); void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)); void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)); void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ static inline void __dev_addr_set(struct net_device *dev, const u8 *addr, size_t len) { memcpy(dev->dev_addr, addr, len); } static inline void dev_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, dev->addr_len); } static inline void dev_addr_mod(struct net_device *dev, unsigned int offset, const u8 *addr, size_t len) { memcpy(&dev->dev_addr[offset], addr, len); } int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); void dev_addr_flush(struct net_device *dev); int dev_addr_init(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); int dev_uc_del(struct net_device *dev, const unsigned char *addr); int dev_uc_sync(struct net_device *to, struct net_device *from); int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); void dev_uc_unsync(struct net_device *to, struct net_device *from); void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** * __dev_uc_sync - Synchonize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * Add newly added addresses to the interface, and release * addresses that have been deleted. */ static inline int __dev_uc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync); } /** * __dev_uc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_uc_sync(). */ static inline void __dev_uc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { __hw_addr_unsync_dev(&dev->uc, dev, unsync); } /* Functions used for multicast addresses handling */ int dev_mc_add(struct net_device *dev, const unsigned char *addr); int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); int dev_mc_del(struct net_device *dev, const unsigned char *addr); int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); int dev_mc_sync(struct net_device *to, struct net_device *from); int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); void dev_mc_unsync(struct net_device *to, struct net_device *from); void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** * __dev_mc_sync - Synchonize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * Add newly added addresses to the interface, and release * addresses that have been deleted. */ static inline int __dev_mc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync); } /** * __dev_mc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_mc_sync(). */ static inline void __dev_mc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { __hw_addr_unsync_dev(&dev->mc, dev, unsync); } /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); void __dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); void netdev_notify_peers(struct net_device *dev); void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ void dev_load(struct net *net, const char *name); struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage); void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats); void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; extern int dev_weight_rx_bias; extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, }; #define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) #define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) #define NESTED_SYNC_IMM __NESTED_SYNC(IMM) #define NESTED_SYNC_TODO __NESTED_SYNC(TODO) struct netdev_nested_priv { unsigned char flags; void *data; }; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); static inline void net_unlink_todo(struct net_device *dev) { if (list_empty(&dev->unlink_list)) list_add_tail(&dev->unlink_list, &net_unlink_list); } #endif /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ updev; \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); bool netdev_has_any_upper_dev(struct net_device *dev); void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_private(dev, priv, iter) \ for (iter = (dev)->adj_list.lower.next, \ priv = netdev_lower_get_next_private(dev, &(iter)); \ priv; \ priv = netdev_lower_get_next_private(dev, &(iter))) #define netdev_for_each_lower_private_rcu(dev, priv, iter) \ for (iter = &(dev)->adj_list.lower, \ priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \ priv; \ priv = netdev_lower_get_next_private_rcu(dev, &(iter))) void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_dev(dev, ldev, iter) \ for (iter = (dev)->adj_list.lower.next, \ ldev = netdev_lower_get_next(dev, &(iter)); \ ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); struct netdev_bonding_info { ifslave slave; ifbond master; }; struct netdev_notifier_bonding_info { struct netdev_notifier_info info; /* must be first */ struct netdev_bonding_info bonding_info; }; void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info); #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data); #else static inline void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) { } #endif static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { return __skb_gso_segment(skb, features, true); } __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { if (protocol == htons(ETH_P_FCOE)) return !!(features & NETIF_F_FCOE_CRC); /* Assume this is an IP checksum (not SCTP CRC) */ if (features & NETIF_F_HW_CSUM) { /* Can checksum everything */ return true; } switch (protocol) { case htons(ETH_P_IP): return !!(features & NETIF_F_IP_CSUM); case htons(ETH_P_IPV6): return !!(features & NETIF_F_IPV6_CSUM); default: return false; } } #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb); #else static inline void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { } #endif /* rx skb timestamps */ void net_enable_timestamp(void); void net_disable_timestamp(void); #ifdef CONFIG_PROC_FS int __init dev_proc_init(void); #else #define dev_proc_init() 0 #endif static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) { __this_cpu_write(softnet_data.xmit.more, more); return ops->ndo_start_xmit(skb, dev); } static inline bool netdev_xmit_more(void) { return __this_cpu_read(softnet_data.xmit.more); } static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { const struct net_device_ops *ops = dev->netdev_ops; netdev_tx_t rc; rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); void linkwatch_run_queue(void); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { if ((f1 ^ f2) & NETIF_F_HW_CSUM) { if (f1 & NETIF_F_HW_CSUM) f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); else f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) { return (dev->features & ~dev->hw_features) | dev->wanted_features; } netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask); /* Allow TSO being used on stacked device : * Performing the GSO segmentation before last device * is a performance improvement. */ static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, netdev_features_t mask) { return netdev_increment_features(features, NETIF_F_ALL_TSO | NETIF_F_ALL_FOR_ALL, mask); } int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_IPXIP4 != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_IPXIP6 != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); } static inline bool netif_needs_gso(struct sk_buff *skb, netdev_features_t features) { return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || unlikely((skb->ip_summed != CHECKSUM_PARTIAL) && (skb->ip_summed != CHECKSUM_UNNECESSARY))); } static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { dev->gso_max_size = size; } static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) { skb->protocol = protocol; skb->encapsulation = 1; skb_push(skb, pulled_hlen); skb_reset_transport_header(skb); skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; } static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; } static inline bool netif_is_macvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN_PORT; } static inline bool netif_is_bond_master(const struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; } static inline bool netif_is_bond_slave(const struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } static inline bool netif_supports_nofcs(struct net_device *dev) { return dev->priv_flags & IFF_SUPP_NOFCS; } static inline bool netif_has_l3_rx_handler(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; } static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; } static inline bool netif_is_l3_slave(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_SLAVE; } static inline bool netif_is_bridge_master(const struct net_device *dev) { return dev->priv_flags & IFF_EBRIDGE; } static inline bool netif_is_bridge_port(const struct net_device *dev) { return dev->priv_flags & IFF_BRIDGE_PORT; } static inline bool netif_is_ovs_master(const struct net_device *dev) { return dev->priv_flags & IFF_OPENVSWITCH; } static inline bool netif_is_ovs_port(const struct net_device *dev) { return dev->priv_flags & IFF_OVS_DATAPATH; } static inline bool netif_is_any_bridge_port(const struct net_device *dev) { return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); } static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; } static inline bool netif_is_team_port(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM_PORT; } static inline bool netif_is_lag_master(const struct net_device *dev) { return netif_is_bond_master(dev) || netif_is_team_master(dev); } static inline bool netif_is_lag_port(const struct net_device *dev) { return netif_is_bond_slave(dev) || netif_is_team_port(dev); } static inline bool netif_is_rxfh_configured(const struct net_device *dev) { return dev->priv_flags & IFF_RXFH_CONFIGURED; } static inline bool netif_is_failover(const struct net_device *dev) { return dev->priv_flags & IFF_FAILOVER; } static inline bool netif_is_failover_slave(const struct net_device *dev) { return dev->priv_flags & IFF_FAILOVER_SLAVE; } /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } /* return true if dev can't cope with mtu frames that need vlan tag insertion */ static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ return dev->priv_flags & IFF_MACSEC; } extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* netdev_printk helpers, similar to dev_printk */ static inline const char *netdev_name(const struct net_device *dev) { if (!dev->name[0] || strchr(dev->name, '%')) return "(unnamed net_device)"; return dev->name; } static inline bool netdev_unregistering(const struct net_device *dev) { return dev->reg_state == NETREG_UNREGISTERING; } static inline const char *netdev_reg_state(const struct net_device *dev) { switch (dev->reg_state) { case NETREG_UNINITIALIZED: return " (uninitialized)"; case NETREG_REGISTERED: return ""; case NETREG_UNREGISTERING: return " (unregistering)"; case NETREG_UNREGISTERED: return " (unregistered)"; case NETREG_RELEASED: return " (released)"; case NETREG_DUMMY: return " (dummy)"; } WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state); return " (unknown)"; } __printf(3, 4) __cold void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_emerg(const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_alert(const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_crit(const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_err(const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_warn(const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_notice(const struct net_device *dev, const char *format, ...); __printf(2, 3) __cold void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ do { \ static bool __print_once __read_mostly; \ \ if (!__print_once) { \ __print_once = true; \ netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ } \ } while (0) #define netdev_emerg_once(dev, fmt, ...) \ netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) #define netdev_alert_once(dev, fmt, ...) \ netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) #define netdev_crit_once(dev, fmt, ...) \ netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) #define netdev_err_once(dev, fmt, ...) \ netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) #define netdev_warn_once(dev, fmt, ...) \ netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) #define netdev_notice_once(dev, fmt, ...) \ netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) #define netdev_info_once(dev, fmt, ...) \ netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define netdev_dbg(__dev, format, args...) \ do { \ dynamic_netdev_dbg(__dev, format, ##args); \ } while (0) #elif defined(DEBUG) #define netdev_dbg(__dev, format, args...) \ netdev_printk(KERN_DEBUG, __dev, format, ##args) #else #define netdev_dbg(__dev, format, args...) \ ({ \ if (0) \ netdev_printk(KERN_DEBUG, __dev, format, ##args); \ }) #endif #if defined(VERBOSE_DEBUG) #define netdev_vdbg netdev_dbg #else #define netdev_vdbg(dev, format, args...) \ ({ \ if (0) \ netdev_printk(KERN_DEBUG, dev, format, ##args); \ 0; \ }) #endif /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the * file/line information and a backtrace. */ #define netdev_WARN(dev, format, args...) \ WARN(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) #define netdev_WARN_ONCE(dev, format, args...) \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) /* netif printk helpers, similar to netdev_printk */ #define netif_printk(priv, type, level, dev, fmt, args...) \ do { \ if (netif_msg_##type(priv)) \ netdev_printk(level, (dev), fmt, ##args); \ } while (0) #define netif_level(level, priv, type, dev, fmt, args...) \ do { \ if (netif_msg_##type(priv)) \ netdev_##level(dev, fmt, ##args); \ } while (0) #define netif_emerg(priv, type, dev, fmt, args...) \ netif_level(emerg, priv, type, dev, fmt, ##args) #define netif_alert(priv, type, dev, fmt, args...) \ netif_level(alert, priv, type, dev, fmt, ##args) #define netif_crit(priv, type, dev, fmt, args...) \ netif_level(crit, priv, type, dev, fmt, ##args) #define netif_err(priv, type, dev, fmt, args...) \ netif_level(err, priv, type, dev, fmt, ##args) #define netif_warn(priv, type, dev, fmt, args...) \ netif_level(warn, priv, type, dev, fmt, ##args) #define netif_notice(priv, type, dev, fmt, args...) \ netif_level(notice, priv, type, dev, fmt, ##args) #define netif_info(priv, type, dev, fmt, args...) \ netif_level(info, priv, type, dev, fmt, ##args) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define netif_dbg(priv, type, netdev, format, args...) \ do { \ if (netif_msg_##type(priv)) \ dynamic_netdev_dbg(netdev, format, ##args); \ } while (0) #elif defined(DEBUG) #define netif_dbg(priv, type, dev, format, args...) \ netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) #else #define netif_dbg(priv, type, dev, format, args...) \ ({ \ if (0) \ netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ 0; \ }) #endif /* if @cond then downgrade to debug, else print at @level */ #define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ do { \ if (cond) \ netif_dbg(priv, type, netdev, fmt, ##args); \ else \ netif_ ## level(priv, type, netdev, fmt, ##args); \ } while (0) #if defined(VERBOSE_DEBUG) #define netif_vdbg netif_dbg #else #define netif_vdbg(priv, type, dev, format, args...) \ ({ \ if (0) \ netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ 0; \ }) #endif /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. * * Why 16. Because with 16 the only overlap we get on a hash of the * low nibble of the protocol value is RARP/SNAP/X.25. * * 0800 IP * 0001 802.3 * 0002 AX.25 * 0004 802.2 * 8035 RARP * 0005 SNAP * 0805 X.25 * 0806 ARP * 8137 IPX * 0009 Localtalk * 86DD IPv6 */ #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) extern struct net_device *blackhole_netdev; /* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ #define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) #define DEV_STATS_ADD(DEV, FIELD, VAL) \ atomic_long_add((VAL), &(DEV)->stats.__##FIELD) #define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD) #endif /* _LINUX_NETDEVICE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H #define _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H #ifndef __LITTLE_ENDIAN #define __LITTLE_ENDIAN 1234 #endif #ifndef __LITTLE_ENDIAN_BITFIELD #define __LITTLE_ENDIAN_BITFIELD #endif #include <linux/types.h> #include <linux/swab.h> #define __constant_htonl(x) ((__force __be32)___constant_swab32((x))) #define __constant_ntohl(x) ___constant_swab32((__force __be32)(x)) #define __constant_htons(x) ((__force __be16)___constant_swab16((x))) #define __constant_ntohs(x) ___constant_swab16((__force __be16)(x)) #define __constant_cpu_to_le64(x) ((__force __le64)(__u64)(x)) #define __constant_le64_to_cpu(x) ((__force __u64)(__le64)(x)) #define __constant_cpu_to_le32(x) ((__force __le32)(__u32)(x)) #define __constant_le32_to_cpu(x) ((__force __u32)(__le32)(x)) #define __constant_cpu_to_le16(x) ((__force __le16)(__u16)(x)) #define __constant_le16_to_cpu(x) ((__force __u16)(__le16)(x)) #define __constant_cpu_to_be64(x) ((__force __be64)___constant_swab64((x))) #define __constant_be64_to_cpu(x) ___constant_swab64((__force __u64)(__be64)(x)) #define __constant_cpu_to_be32(x) ((__force __be32)___constant_swab32((x))) #define __constant_be32_to_cpu(x) ___constant_swab32((__force __u32)(__be32)(x)) #define __constant_cpu_to_be16(x) ((__force __be16)___constant_swab16((x))) #define __constant_be16_to_cpu(x) ___constant_swab16((__force __u16)(__be16)(x)) #define __cpu_to_le64(x) ((__force __le64)(__u64)(x)) #define __le64_to_cpu(x) ((__force __u64)(__le64)(x)) #define __cpu_to_le32(x) ((__force __le32)(__u32)(x)) #define __le32_to_cpu(x) ((__force __u32)(__le32)(x)) #define __cpu_to_le16(x) ((__force __le16)(__u16)(x)) #define __le16_to_cpu(x) ((__force __u16)(__le16)(x)) #define __cpu_to_be64(x) ((__force __be64)__swab64((x))) #define __be64_to_cpu(x) __swab64((__force __u64)(__be64)(x)) #define __cpu_to_be32(x) ((__force __be32)__swab32((x))) #define __be32_to_cpu(x) __swab32((__force __u32)(__be32)(x)) #define __cpu_to_be16(x) ((__force __be16)__swab16((x))) #define __be16_to_cpu(x) __swab16((__force __u16)(__be16)(x)) static __always_inline __le64 __cpu_to_le64p(const __u64 *p) { return (__force __le64)*p; } static __always_inline __u64 __le64_to_cpup(const __le64 *p) { return (__force __u64)*p; } static __always_inline __le32 __cpu_to_le32p(const __u32 *p) { return (__force __le32)*p; } static __always_inline __u32 __le32_to_cpup(const __le32 *p) { return (__force __u32)*p; } static __always_inline __le16 __cpu_to_le16p(const __u16 *p) { return (__force __le16)*p; } static __always_inline __u16 __le16_to_cpup(const __le16 *p) { return (__force __u16)*p; } static __always_inline __be64 __cpu_to_be64p(const __u64 *p) { return (__force __be64)__swab64p(p); } static __always_inline __u64 __be64_to_cpup(const __be64 *p) { return __swab64p((__u64 *)p); } static __always_inline __be32 __cpu_to_be32p(const __u32 *p) { return (__force __be32)__swab32p(p); } static __always_inline __u32 __be32_to_cpup(const __be32 *p) { return __swab32p((__u32 *)p); } static __always_inline __be16 __cpu_to_be16p(const __u16 *p) { return (__force __be16)__swab16p(p); } static __always_inline __u16 __be16_to_cpup(const __be16 *p) { return __swab16p((__u16 *)p); } #define __cpu_to_le64s(x) do { (void)(x); } while (0) #define __le64_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_le32s(x) do { (void)(x); } while (0) #define __le32_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_le16s(x) do { (void)(x); } while (0) #define __le16_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_be64s(x) __swab64s((x)) #define __be64_to_cpus(x) __swab64s((x)) #define __cpu_to_be32s(x) __swab32s((x)) #define __be32_to_cpus(x) __swab32s((x)) #define __cpu_to_be16s(x) __swab16s((x)) #define __be16_to_cpus(x) __swab16s((x)) #endif /* _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Events for filesystem locks * * Copyright 2013 Jeff Layton <jlayton@poochiereds.net> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filelock #if !defined(_TRACE_FILELOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILELOCK_H #include <linux/tracepoint.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/kdev_t.h> #define show_fl_flags(val) \ __print_flags(val, "|", \ { FL_POSIX, "FL_POSIX" }, \ { FL_FLOCK, "FL_FLOCK" }, \ { FL_DELEG, "FL_DELEG" }, \ { FL_ACCESS, "FL_ACCESS" }, \ { FL_EXISTS, "FL_EXISTS" }, \ { FL_LEASE, "FL_LEASE" }, \ { FL_CLOSE, "FL_CLOSE" }, \ { FL_SLEEP, "FL_SLEEP" }, \ { FL_DOWNGRADE_PENDING, "FL_DOWNGRADE_PENDING" }, \ { FL_UNLOCK_PENDING, "FL_UNLOCK_PENDING" }, \ { FL_OFDLCK, "FL_OFDLCK" }, \ { FL_RECLAIM, "FL_RECLAIM"}) #define show_fl_type(val) \ __print_symbolic(val, \ { F_RDLCK, "F_RDLCK" }, \ { F_WRLCK, "F_WRLCK" }, \ { F_UNLCK, "F_UNLCK" }) TRACE_EVENT(locks_get_lock_context, TP_PROTO(struct inode *inode, int type, struct file_lock_context *ctx), TP_ARGS(inode, type, ctx), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned char, type) __field(struct file_lock_context *, ctx) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->type = type; __entry->ctx = ctx; ), TP_printk("dev=0x%x:0x%x ino=0x%lx type=%s ctx=%p", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, show_fl_type(__entry->type), __entry->ctx) ); DECLARE_EVENT_CLASS(filelock_lock, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret), TP_STRUCT__entry( __field(struct file_lock *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock *, fl_blocker) __field(fl_owner_t, fl_owner) __field(unsigned int, fl_pid) __field(unsigned int, fl_flags) __field(unsigned char, fl_type) __field(loff_t, fl_start) __field(loff_t, fl_end) __field(int, ret) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->fl_blocker = fl ? fl->fl_blocker : NULL; __entry->fl_owner = fl ? fl->fl_owner : NULL; __entry->fl_pid = fl ? fl->fl_pid : 0; __entry->fl_flags = fl ? fl->fl_flags : 0; __entry->fl_type = fl ? fl->fl_type : 0; __entry->fl_start = fl ? fl->fl_start : 0; __entry->fl_end = fl ? fl->fl_end : 0; __entry->ret = ret; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->fl_blocker, __entry->fl_owner, __entry->fl_pid, show_fl_flags(__entry->fl_flags), show_fl_type(__entry->fl_type), __entry->fl_start, __entry->fl_end, __entry->ret) ); DEFINE_EVENT(filelock_lock, posix_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, fcntl_setlk, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, locks_remove_posix, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, flock_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DECLARE_EVENT_CLASS(filelock_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(struct file_lock *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock *, fl_blocker) __field(fl_owner_t, fl_owner) __field(unsigned int, fl_flags) __field(unsigned char, fl_type) __field(unsigned long, fl_break_time) __field(unsigned long, fl_downgrade_time) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->fl_blocker = fl ? fl->fl_blocker : NULL; __entry->fl_owner = fl ? fl->fl_owner : NULL; __entry->fl_flags = fl ? fl->fl_flags : 0; __entry->fl_type = fl ? fl->fl_type : 0; __entry->fl_break_time = fl ? fl->fl_break_time : 0; __entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->fl_blocker, __entry->fl_owner, show_fl_flags(__entry->fl_flags), show_fl_type(__entry->fl_type), __entry->fl_break_time, __entry->fl_downgrade_time) ); DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); TRACE_EVENT(generic_add_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(int, wcount) __field(int, rcount) __field(int, icount) __field(dev_t, s_dev) __field(fl_owner_t, fl_owner) __field(unsigned int, fl_flags) __field(unsigned char, fl_type) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->wcount = atomic_read(&inode->i_writecount); __entry->rcount = atomic_read(&inode->i_readcount); __entry->icount = atomic_read(&inode->i_count); __entry->fl_owner = fl->fl_owner; __entry->fl_flags = fl->fl_flags; __entry->fl_type = fl->fl_type; ), TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->wcount, __entry->rcount, __entry->icount, __entry->fl_owner, show_fl_flags(__entry->fl_flags), show_fl_type(__entry->fl_type)) ); TRACE_EVENT(leases_conflict, TP_PROTO(bool conflict, struct file_lock *lease, struct file_lock *breaker), TP_ARGS(conflict, lease, breaker), TP_STRUCT__entry( __field(void *, lease) __field(void *, breaker) __field(unsigned int, l_fl_flags) __field(unsigned int, b_fl_flags) __field(unsigned char, l_fl_type) __field(unsigned char, b_fl_type) __field(bool, conflict) ), TP_fast_assign( __entry->lease = lease; __entry->l_fl_flags = lease->fl_flags; __entry->l_fl_type = lease->fl_type; __entry->breaker = breaker; __entry->b_fl_flags = breaker->fl_flags; __entry->b_fl_type = breaker->fl_type; __entry->conflict = conflict; ), TP_printk("conflict %d: lease=%p fl_flags=%s fl_type=%s; breaker=%p fl_flags=%s fl_type=%s", __entry->conflict, __entry->lease, show_fl_flags(__entry->l_fl_flags), show_fl_type(__entry->l_fl_type), __entry->breaker, show_fl_flags(__entry->b_fl_flags), show_fl_type(__entry->b_fl_type)) ); #endif /* _TRACE_FILELOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void update_process_times(int user); extern void xtime_update(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family: read the current time in a multitude of ways, * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones wit * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Returns monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct ktime_timestanps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t raw; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the pointer to the * corresponding clocksource * @cycles: System counter value * @cs: Clocksource corresponding to system counter value. Used by * timekeeping code to verify comparibility of two cycle values */ struct system_counterval_t { u64 cycles; struct clocksource *cs; }; /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_H #define _ASM_X86_UACCESS_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/extable.h> /* * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. */ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) { /* * If we have used "sizeof()" for the size, * we know it won't overflow the limit (but * it might overflow the 'addr', so it's * important to subtract the size from the * limit, not add it to the address). */ if (__builtin_constant_p(size)) return unlikely(addr > limit - size); /* Arbitrary sizes? Be careful about overflow */ addr += size; if (unlikely(addr < size)) return true; return unlikely(addr > limit); } #define __range_not_ok(addr, size, limit) \ ({ \ __chk_user_ptr(addr); \ __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ }) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline bool pagefault_disabled(void); # define WARN_ON_IN_IRQ() \ WARN_ON_ONCE(!in_task() && !pagefault_disabled()) #else # define WARN_ON_IN_IRQ() #endif /** * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check * @size: Size of block to check * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Checks if a pointer to a block of memory in user space is valid. * * Note that, depending on architecture, this function probably just * checks that the pointer is in the user space range - after calling * this function, memory access functions may still return -EFAULT. * * Return: true (nonzero) if the memory block may be valid, false (zero) * if it is definitely invalid. */ #define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ likely(!__range_not_ok(addr, size, TASK_SIZE_MAX)); \ }) extern int __get_user_1(void); extern int __get_user_2(void); extern int __get_user_4(void); extern int __get_user_8(void); extern int __get_user_nocheck_1(void); extern int __get_user_nocheck_2(void); extern int __get_user_nocheck_4(void); extern int __get_user_nocheck_8(void); extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() #define __uaccess_begin_nospec() \ ({ \ stac(); \ barrier_nospec(); \ }) /* * This is the smallest unsigned integer type that can fit a value * (up to 'long long') */ #define __inttype(x) __typeof__( \ __typefits(x,char, \ __typefits(x,short, \ __typefits(x,int, \ __typefits(x,long,0ULL))))) #define __typefits(x,type,not) \ __builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not) /* * This is used for both get_user() and __get_user() to expand to * the proper special function call that has odd calling conventions * due to returning both a value and an error, and that depends on * the size of the pointer passed in. * * Careful: we have to cast the result to the type of the pointer * for sign reasons. * * The use of _ASM_DX as the register specifier is a bit of a * simplification, as gcc only cares about it as the starting point * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits * (%ecx being the next register in gcc's x86 register sequence), and * %rdx on 64 bits. * * Clang/LLVM cares about the size of the register, but still wants * the base register for something that ends up being a pair. */ #define do_get_user_call(fn,x,ptr) \ ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ asm volatile("call __" #fn "_%P4" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ }) /** * get_user - Get a simple variable from user space. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); }) /** * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr) #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ asm_volatile_goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ _ASM_EXTABLE_UA(2b, %l2) \ : : "A" (x), "r" (addr) \ : : label) #else #define __put_user_goto_u64(x, ptr, label) \ __put_user_goto(x, ptr, "q", "er", label) #endif extern void __put_user_bad(void); /* * Strange magic calling convention: pointer in %ecx, * value in %eax(:%edx), return value in %ecx. clobbers %rbx */ extern void __put_user_1(void); extern void __put_user_2(void); extern void __put_user_4(void); extern void __put_user_8(void); extern void __put_user_nocheck_1(void); extern void __put_user_nocheck_2(void); extern void __put_user_nocheck_4(void); extern void __put_user_nocheck_8(void); /* * ptr must be evaluated and assigned to the temporary __ptr_pu before * the assignment of x to __val_pu, to avoid any function calls * involved in the ptr expression (possibly implicitly generated due * to KASAN) from clobbering %ax. */ #define do_put_user_call(fn,x,ptr) \ ({ \ int __ret_pu; \ void __user *__ptr_pu; \ register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ __chk_user_ptr(ptr); \ __ptr_pu = (ptr); \ __val_pu = (x); \ asm volatile("call __" #fn "_%P[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ "r" (__val_pu), \ [size] "i" (sizeof(*(ptr))) \ :"ebx"); \ __builtin_expect(__ret_pu, 0); \ }) /** * put_user - Write a simple value into user space. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Return: zero on success, or -EFAULT on error. */ #define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); }) /** * __put_user - Write a simple value into user space, with less checking. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. */ #define __put_user(x, ptr) do_put_user_call(put_user_nocheck,x,ptr) #define __put_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __put_user_goto(x, ptr, "b", "iq", label); \ break; \ case 2: \ __put_user_goto(x, ptr, "w", "ir", label); \ break; \ case 4: \ __put_user_goto(x, ptr, "l", "ir", label); \ break; \ case 8: \ __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, label) do { \ unsigned int __gu_low, __gu_high; \ const unsigned int __user *__gu_ptr; \ __gu_ptr = (const void __user *)(ptr); \ __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ } while (0) #else #define __get_user_asm_u64(x, ptr, label) \ __get_user_asm(x, ptr, "q", "=r", label) #endif #define __get_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: { \ unsigned char x_u8__; \ __get_user_asm(x_u8__, ptr, "b", "=q", label); \ (x) = x_u8__; \ break; \ } \ case 2: \ __get_user_asm(x, ptr, "w", "=r", label); \ break; \ case 4: \ __get_user_asm(x, ptr, "l", "=r", label); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, label); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ : [umem] "m" (__m(addr)) \ : : label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ asm volatile("\n" \ "1: movl %[lowbits],%%eax\n" \ "2: movl %[highbits],%%edx\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: mov %[efault],%[errout]\n" \ " xorl %%eax,%%eax\n" \ " xorl %%edx,%%edx\n" \ " jmp 3b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 4b) \ _ASM_EXTABLE_UA(2b, 4b) \ : [errout] "=r" (retval), \ [output] "=&A"(x) \ : [lowbits] "m" (__m(__ptr)), \ [highbits] "m" __m(((u32 __user *)(__ptr)) + 1), \ [efault] "i" (-EFAULT), "0" (retval)); \ }) #else #define __get_user_asm_u64(x, ptr, retval) \ __get_user_asm(x, ptr, retval, "q", "=r") #endif #define __get_user_size(x, ptr, size, retval) \ do { \ unsigned char x_u8__; \ \ retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __get_user_asm(x_u8__, ptr, retval, "b", "=q"); \ (x) = x_u8__; \ break; \ case 2: \ __get_user_asm(x, ptr, retval, "w", "=r"); \ break; \ case 4: \ __get_user_asm(x, ptr, retval, "l", "=r"); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, retval); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, itype, ltype) \ asm volatile("\n" \ "1: mov"itype" %[umem],%[output]\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %[efault],%[errout]\n" \ " xorl %k[output],%k[output]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : [errout] "=r" (err), \ [output] ltype(x) \ : [umem] "m" (__m(addr)), \ [efault] "i" (-EFAULT), "0" (err)) #endif // CONFIG_CC_ASM_GOTO_OUTPUT #ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #endif // CONFIG_X86_32 #else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ int __err = 0; \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ CC_SET(z) \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[errout]) \ : CC_OUT(z) (success), \ [errout] "+r" (__err), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 /* * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses * both ESI and EDI for the memory operand, compilation will fail if the error * is an input+output as there will be no register available for input. */ #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ int __result; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ "mov $0, %%ecx\n\t" \ "setz %%cl\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ : [result]"=c" (__result), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory", "cc"); \ if (unlikely(__result < 0)) \ goto label; \ if (unlikely(!__result)) \ *_old = __old; \ likely(__result); }) #endif // CONFIG_X86_32 #endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) /* * Tell gcc we read from memory instead of writing: this is because * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ : : label) extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); #define copy_mc_to_kernel copy_mc_to_kernel unsigned long __must_check copy_mc_to_user(void __user *to, const void *from, unsigned len); #endif /* * movsl can be slow when source and dest are not both 8-byte aligned */ #ifdef CONFIG_X86_INTEL_USERCOPY extern struct movsl_mask { int mask; } ____cacheline_aligned_in_smp movsl_mask; #endif #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> #endif /* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; __uaccess_begin_nospec(); return 1; } #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() #define user_access_save() smap_save() #define user_access_restore(x) smap_restore(x) #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), err_label); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT extern void __try_cmpxchg_user_wrong_size(void); #ifndef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) #endif /* * Force the pointer to u<size> to match the size expected by the asm helper. * clang/LLVM compiles all cases and only discards the unused paths after * processing errors, which breaks i386 if the pointer is an 8-byte value. */ #define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ bool __ret; \ __chk_user_ptr(_ptr); \ switch (sizeof(*(_ptr))) { \ case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ (__force u8 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ (__force u16 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ (__force u32 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ (_nval), _label); \ break; \ default: __try_cmpxchg_user_wrong_size(); \ } \ __ret; }) /* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ #define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ int __ret = -EFAULT; \ __uaccess_begin_nospec(); \ __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ _label: \ __uaccess_end(); \ __ret; \ }) /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. */ #define unsafe_copy_loop(dst, src, len, type, label) \ while (len >= sizeof(type)) { \ unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } #define unsafe_copy_to_user(_dst,_src,_len,label) \ do { \ char __user *__ucu_dst = (_dst); \ const char *__ucu_src = (_src); \ size_t __ucu_len = (_len); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) #define HAVE_GET_KERNEL_NOFAULT #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), err_label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ int __kr_err; \ \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __put_kernel_nofault(dst, src, type, err_label) \ __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ sizeof(type), err_label) #endif /* _ASM_X86_UACCESS_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> #include <linux/init_task.h> #include "internal.h" unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cachep objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { *errorp = PTR_ERR(new_fdt); goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } struct files_struct *get_files_struct(struct task_struct *task) { struct files_struct *files; task_lock(task); files = task->files; if (files) atomic_inc(&files->count); task_unlock(task); return files; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); static struct file *pick_file(struct files_struct *files, unsigned fd) { struct file *file = NULL; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); out_unlock: spin_unlock(&files->file_lock); return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; file = pick_file(files, fd); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /* for ksys_close() */ /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { unsigned int cur_max; struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~CLOSE_RANGE_UNSHARE) return -EINVAL; if (fd > max_fd) return -EINVAL; rcu_read_lock(); cur_max = files_fdtable(cur_fds)->max_fds; rcu_read_unlock(); /* cap to last valid index into fdtable */ cur_max--; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the requested range is greater than the current maximum, * we're closing everything so only copy all file descriptors * beneath the lowest file descriptor. */ if (max_fd >= cur_max) max_unshare_fds = fd; ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } max_fd = min(max_fd, cur_max); while (fd <= max_fd) { struct file *file; file = pick_file(cur_fds, fd++); if (!file) continue; filp_close(file, cur_fds); cond_resched(); } if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /* * See close_fd_get_file() below, this variant assumes current->files->file_lock * is held. */ int __close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; struct fdtable *fdt; fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_err; file = fdt->fd[fd]; if (!file) goto out_err; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); get_file(file); *res = file; return 0; out_err: *res = NULL; return -ENOENT; } /* * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then * an fput(). */ int close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; int ret; spin_lock(&files->file_lock); ret = __close_fd_get_file(fd, res); spin_unlock(&files->file_lock); return ret; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); loop: file = files_lookup_fd_rcu(files, fd); if (file) { /* File object ref couldn't be taken. * dup2() atomicity guarantee is the reason * we loop to catch the new file (or NULL pointer) */ if (file->f_mode & mask) file = NULL; else if (!get_file_rcu_many(file, refs)) goto loop; else if (files_lookup_fd_raw(files, fd) != file) { fput_many(file, refs); goto loop; } } rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) { return __fget_files(current->files, fd, mask, refs); } struct file *fget_many(unsigned int fd, unsigned int refs) { return __fget(fd, FMODE_PATH, refs); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH, 1); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0, 1); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0, 1); task_unlock(task); return file; } struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; struct file *file = NULL; task_lock(task); files = task->files; if (files) file = files_lookup_fd_rcu(files, fd); task_unlock(task); return file; } struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { for (; fd < files_fdtable(files)->max_fds; fd++) { file = files_lookup_fd_rcu(files, fd); if (file) break; } } task_unlock(task); *ret_fd = fd; return file; } /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; if (atomic_read(&files->count) == 1) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget(fd, mask, 1); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || S_ISDIR(file_inode(file)->i_mode)); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; err = do_dup2(files, file, fd, flags); if (err < 0) return err; return 0; out_unlock: spin_unlock(&files->file_lock); return err; } /** * __receive_fd() - Install received file into file descriptor table * * @fd: fd to install into (if negative, a new fd will be allocated) * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; if (fd < 0) { new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; } else { new_fd = fd; } if (ufd) { error = put_user(new_fd, ufd); if (error) { if (fd < 0) put_unused_fd(new_fd); return error; } } if (fd < 0) { fd_install(new_fd, get_file(file)); } else { error = replace_fd(new_fd, file, o_flags); if (error) return error; } /* Bump the sock usage counts, if any. */ __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; int retval = oldfd; rcu_read_lock(); if (!files_lookup_fd_rcu(files, oldfd)) retval = -EBADF; rcu_read_unlock(); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> #include <linux/types.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* * All weight knobs on the default hierarhcy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ #define CGROUP_WEIGHT_MIN 1 #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 /* walk only threadgroup leaders */ #define CSS_TASK_ITER_PROCS (1U << 0) /* walk all threaded css_sets in the domain */ #define CSS_TASK_ITER_THREADED (1U << 1) /* internal flags */ #define CSS_TASK_ITER_SKIPPED (1U << 16) /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; struct list_head *tcset_pos; struct list_head *tcset_head; struct list_head *task_pos; struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) \ extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; #include <linux/cgroup_subsys.h> #undef SUBSYS /** * cgroup_subsys_enabled - fast test on whether a subsys is enabled * @ss: subsystem in question */ #define cgroup_subsys_enabled(ss) \ static_branch_likely(&ss ## _enabled_key) /** * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy * @ss: subsystem in question */ #define cgroup_subsys_on_dfl(ss) \ static_branch_likely(&ss ## _on_dfl_key) bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); extern int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); void cgroup_exit(struct task_struct *p); void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p); int cgroup_init_early(void); int cgroup_init(void); int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v); /* * Iteration helpers and macros. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor * @parent: css whose children to walk * * Walk @parent's children. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_child(pos, parent) \ for ((pos) = css_next_child(NULL, (parent)); (pos); \ (pos) = css_next_child((pos), (parent))) /** * css_for_each_descendant_pre - pre-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * * Walk @root's descendants. @root is included in the iteration and the * first node to be visited. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * For example, the following guarantees that a descendant can't escape * state updates of its ancestors. * * my_online(@css) * { * Lock @css's parent and @css; * Inherit state from the parent; * Unlock both. * } * * my_update_state(@css) * { * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; * if (@pos == @css) * Update @css's state; * else * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } * * As long as the inheriting step, including checking the parent state, is * enclosed inside @pos locking, double-locking the parent isn't necessary * while inheriting. The state update to the parent is guaranteed to be * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. * * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_descendant_pre(pos, css) \ for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ (pos) = css_next_descendant_pre((pos), (css))) /** * css_for_each_descendant_post - post-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. @root is included in the iteration and the last * node to be visited. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * Note that the walk visibility guarantee example described in pre-order * walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple * processes. * * On the v2 hierarchy, there may be tasks from multiple processes and they * may not share the source or destination csses. * * On traditional hierarchies, when there are multiple tasks in @tset, if a * task of a process is in @tset, all tasks of the process are in @tset. * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ #define cgroup_taskset_for_each(task, dst_css, tset) \ for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ (task); \ (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ #define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ (leader); \ (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else /* * Inline functions. */ static inline u64 cgroup_id(struct cgroup *cgrp) { return cgrp->kn->id; } /** * css_get - obtain a reference on the specified css * @css: target css * * The caller must already have a reference. */ static inline void css_get(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) percpu_ref_get(&css->refcnt); } /** * css_get_many - obtain references on the specified css * @css: target css * @n: number of references to get * * The caller must already have a reference. */ static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n) { if (!(css->flags & CSS_NO_REF)) percpu_ref_get_many(&css->refcnt, n); } /** * css_tryget - try to obtain a reference on the specified css * @css: target css * * Obtain a reference on @css unless it already has reached zero and is * being released. This function doesn't care whether @css is on or * offline. The caller naturally needs to ensure that @css is accessible * but doesn't have to be holding a reference on it - IOW, RCU protected * access is good enough for this function. Returns %true if a reference * count was successfully obtained; %false otherwise. */ static inline bool css_tryget(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget(&css->refcnt); return true; } /** * css_tryget_online - try to obtain a reference on the specified css if online * @css: target css * * Obtain a reference on @css if it's online. The caller naturally needs * to ensure that @css is accessible but doesn't have to be holding a * reference on it - IOW, RCU protected access is good enough for this * function. Returns %true if a reference count was successfully obtained; * %false otherwise. */ static inline bool css_tryget_online(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget_live(&css->refcnt); return true; } /** * css_is_dying - test whether the specified css is dying * @css: target css * * Test whether @css is in the process of offlining or already offline. In * most cases, ->css_online() and ->css_offline() callbacks should be * enough; however, the actual offline operations are RCU delayed and this * test returns %true also when @css is scheduled to be offlined. * * This is useful, for example, when the use case requires synchronous * behavior with respect to cgroup removal. cgroup removal schedules css * offlining but the css can seem alive while the operation is being * delayed. If the delay affects user visible semantics, this test can be * used to resolve the situation. */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); } /** * css_put - put a css reference * @css: target css * * Put a reference obtained via css_get() and css_tryget_online(). */ static inline void css_put(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) percpu_ref_put(&css->refcnt); } /** * css_put_many - put css references * @css: target css * @n: number of references to put * * Put references obtained via css_get() and css_tryget_online(). */ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) { if (!(css->flags & CSS_NO_REF)) percpu_ref_put_many(&css->refcnt, n); } static inline void cgroup_get(struct cgroup *cgrp) { css_get(&cgrp->self); } static inline bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); } static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); } /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for * @__c: extra condition expression to be passed to rcu_dereference_check() * * A task's css_set is RCU protected, initialized and exited while holding * task_lock(), and can only be modified while holding both cgroup_mutex * and task_lock() while the task is alive. This macro verifies that the * caller is inside proper critical section and returns @task's css_set. * * The caller can also specify additional allowed conditions via @__c, such * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ rcu_dereference((task)->cgroups) #endif /** * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() * * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ #define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** * task_css_set - obtain a task's css_set * @task: the task to obtain css_set for * * See task_css_set_check(). */ static inline struct css_set *task_css_set(struct task_struct *task) { return task_css_set_check(task, false); } /** * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * See task_css_check(). */ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, false); } /** * task_get_css - find and get the css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) { struct cgroup_subsys_state *css; rcu_read_lock(); while (true) { css = task_css(task, subsys_id); /* * Can't use css_tryget_online() here. A task which has * PF_EXITING set may stay associated with an offline css. * If such task calls this function, css_tryget_online() * will keep failing. */ if (likely(css_tryget(css))) break; cpu_relax(); } rcu_read_unlock(); return css; } /** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID * * Test whether @task belongs to the root css on the specified subsystem. * May be invoked in any context. */ static inline bool task_css_is_root(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, true) == init_css_set.subsys[subsys_id]; } static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { return task_css(task, subsys_id)->cgroup; } static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) { return task_css_set(task)->dfl_cgrp; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ static inline bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); } /** * cgroup_ancestor - find ancestor of cgroup * @cgrp: cgroup to find ancestor of * @ancestor_level: level of ancestor to find starting from root * * Find ancestor of cgroup at specified level starting from root if it exists * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at * @ancestor_level. * * This function is safe to call as long as @cgrp is accessible. */ static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { if (cgrp->level < ancestor_level) return NULL; while (cgrp && cgrp->level > ancestor_level) cgrp = cgroup_parent(cgrp); return cgrp; } /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested * @ancestor: possible ancestor of @task's cgroup * * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. * It follows all the same rules as cgroup_is_descendant, and only applies * to the default hierarchy. */ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { struct css_set *cset = task_css_set(task); return cgroup_is_descendant(cset->dfl_cgrp, ancestor); } /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ static inline struct cftype *of_cft(struct kernfs_open_file *of) { return of->kn->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); /* cft/css accessors for cftype->seq_*() operations */ static inline struct cftype *seq_cft(struct seq_file *seq) { return of_cft(seq->private); } static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) { return of_css(seq->private); } /* * Name / path handling functions. All are thin wrappers around the kernfs * counterparts and can be called under any context. */ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_name(cgrp->kn, buf, buflen); } static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_path(cgrp->kn, buf, buflen); } static inline void pr_cont_cgroup_name(struct cgroup *cgrp) { pr_cont_kernfs_name(cgrp->kn); } static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { pr_cont_kernfs_path(cgrp->kn); } static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return &cgrp->psi; } static inline void cgroup_init_kthreadd(void) { /* * kthreadd is inherited by all kthreads, keep it in the root so * that the new kthreads are guaranteed to stay in the root until * initialization is finished. */ current->no_cgroup_migration = 1; } static inline void cgroup_kthread_ready(void) { /* * This kthread finished initialization. The creator should have * set PF_NO_SETAFFINITY if this kthread should stay in the root. */ current->no_cgroup_migration = 0; } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} static inline int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_exit(struct task_struct *p) {} static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { return NULL; } static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return NULL; } static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS /* * cgroup scalable recursive statistics. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); /* * Basic resource stats. */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} static inline void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) {} #endif void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec); void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec); static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) { struct cgroup *cgrp; cpuacct_charge(task, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); } static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup *cgrp; cpuacct_account_field(task, index, delta_exec); rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) {} static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) {} #endif /* CONFIG_CGROUPS */ /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ struct cgroup_namespace { refcount_t count; struct ns_common ns; struct user_namespace *user_ns; struct ucounts *ucounts; struct css_set *root_cset; }; extern struct cgroup_namespace init_cgroup_ns; #ifdef CONFIG_CGROUPS void free_cgroup_ns(struct cgroup_namespace *ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns); int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); #else /* !CONFIG_CGROUPS */ static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } static inline struct cgroup_namespace * copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { return old_ns; } #endif /* !CONFIG_CGROUPS */ static inline void get_cgroup_ns(struct cgroup_namespace *ns) { if (ns) refcount_inc(&ns->count); } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { if (ns && refcount_dec_and_test(&ns->count)) free_cgroup_ns(ns); } #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); void cgroup_leave_frozen(bool always_leave); void cgroup_update_frozen(struct cgroup *cgrp); void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); static inline bool cgroup_task_freeze(struct task_struct *task) { bool ret; if (task->flags & PF_KTHREAD) return false; rcu_read_lock(); ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags); rcu_read_unlock(); return ret; } static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; } #else /* !CONFIG_CGROUPS */ static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } static inline bool cgroup_task_freeze(struct task_struct *task) { return false; } static inline bool cgroup_task_frozen(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUP_BPF static inline void cgroup_bpf_get(struct cgroup *cgrp) { percpu_ref_get(&cgrp->bpf.refcnt); } static inline void cgroup_bpf_put(struct cgroup *cgrp) { percpu_ref_put(&cgrp->bpf.refcnt); } #else /* CONFIG_CGROUP_BPF */ static inline void cgroup_bpf_get(struct cgroup *cgrp) {} static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ #endif /* _LINUX_CGROUP_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0 /* * preemptoff and irqoff tracepoints * * Copyright (C) Joel Fernandes (Google) <joel@joelfernandes.org> */ #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include "trace.h" #define CREATE_TRACE_POINTS #include <trace/events/preemptirq.h> #ifdef CONFIG_TRACE_IRQFLAGS /* Per-cpu variable to prevent redundant calls when IRQs already off */ static DEFINE_PER_CPU(int, tracing_irq_cpu); /* * Like trace_hardirqs_on() but without the lockdep invocation. This is * used in the low level entry code where the ordering vs. RCU is important * and lockdep uses a staged approach which splits the lockdep hardirq * tracking into a RCU on and a RCU off section. */ void trace_hardirqs_on_prepare(void) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } } EXPORT_SYMBOL(trace_hardirqs_on_prepare); NOKPROBE_SYMBOL(trace_hardirqs_on_prepare); void trace_hardirqs_on(void) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } lockdep_hardirqs_on_prepare(CALLER_ADDR0); lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); NOKPROBE_SYMBOL(trace_hardirqs_on); /* * Like trace_hardirqs_off() but without the lockdep invocation. This is * used in the low level entry code where the ordering vs. RCU is important * and lockdep uses a staged approach which splits the lockdep hardirq * tracking into a RCU on and a RCU off section. */ void trace_hardirqs_off_finish(void) { if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); if (!in_nmi()) trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off_finish); NOKPROBE_SYMBOL(trace_hardirqs_off_finish); void trace_hardirqs_off(void) { lockdep_hardirqs_off(CALLER_ADDR0); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off); NOKPROBE_SYMBOL(trace_hardirqs_off); __visible void trace_hardirqs_on_caller(unsigned long caller_addr) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); tracer_hardirqs_on(CALLER_ADDR0, caller_addr); this_cpu_write(tracing_irq_cpu, 0); } lockdep_hardirqs_on_prepare(caller_addr); lockdep_hardirqs_on(caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { lockdep_hardirqs_off(caller_addr); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_TRACE_IRQFLAGS */ #ifdef CONFIG_TRACE_PREEMPT_TOGGLE void trace_preempt_on(unsigned long a0, unsigned long a1) { if (!in_nmi()) trace_preempt_enable_rcuidle(a0, a1); tracer_preempt_on(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { if (!in_nmi()) trace_preempt_disable_rcuidle(a0, a1); tracer_preempt_off(a0, a1); } #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefor each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ lvl * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefor the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT 3 #define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) #define LVL_CLK_MASK (LVL_CLK_DIV - 1) #define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) #define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) /* * The time start value for each level to select the bucket at enqueue * time. We start from the last possible delta of the previous level * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()). */ #define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) /* Size of each clock level */ #define LVL_BITS 6 #define LVL_SIZE (1UL << LVL_BITS) #define LVL_MASK (LVL_SIZE - 1) #define LVL_OFFS(n) ((n) * LVL_SIZE) /* Level depth */ #if HZ > 100 # define LVL_DEPTH 9 # else # define LVL_DEPTH 8 #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) #define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON # define NR_BASES 2 # define BASE_STD 0 # define BASE_DEF 1 #else # define NR_BASES 1 # define BASE_STD 0 # define BASE_DEF 0 #endif struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; #ifdef CONFIG_PREEMPT_RT spinlock_t expiry_lock; atomic_t timer_waiters; #endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; bool next_expiry_recalc; bool is_idle; bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { if (sysctl_timer_migration && tick_nohz_active) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); } #else static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { mutex_lock(&timer_keys_mutex); timers_update_migration(); static_branch_enable(&timers_nohz_active); mutex_unlock(&timer_keys_mutex); } void timers_update_nohz(void) { schedule_work(&timer_update_work); } int timer_migration_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&timer_keys_mutex); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(); mutex_unlock(&timer_keys_mutex); return ret; } static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffie is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, false); } EXPORT_SYMBOL_GPL(__round_jiffies); /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, true); } EXPORT_SYMBOL_GPL(__round_jiffies_up); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); static inline unsigned int timer_get_idx(struct timer_list *timer) { return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | idx << TIMER_ARRAYSHIFT; } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned long expires, unsigned lvl, unsigned long *bucket_expiry) { /* * The timer wheel has to guarantee that a timer does not fire * early. Early expiry can happen due to: * - Timer is armed at the edge of a tick * - Truncation of the expiry time in the outer wheel levels * * Round up with level granularity to prevent this. */ expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl); *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } static int calc_wheel_index(unsigned long expires, unsigned long clk, unsigned long *bucket_expiry) { unsigned long delta = expires - clk; unsigned int idx; if (delta < LVL_START(1)) { idx = calc_index(expires, 0, bucket_expiry); } else if (delta < LVL_START(2)) { idx = calc_index(expires, 1, bucket_expiry); } else if (delta < LVL_START(3)) { idx = calc_index(expires, 2, bucket_expiry); } else if (delta < LVL_START(4)) { idx = calc_index(expires, 3, bucket_expiry); } else if (delta < LVL_START(5)) { idx = calc_index(expires, 4, bucket_expiry); } else if (delta < LVL_START(6)) { idx = calc_index(expires, 5, bucket_expiry); } else if (delta < LVL_START(7)) { idx = calc_index(expires, 6, bucket_expiry); } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { idx = calc_index(expires, 7, bucket_expiry); } else if ((long) delta < 0) { idx = clk & LVL_MASK; *bucket_expiry = clk; } else { /* * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ if (delta >= WHEEL_TIMEOUT_CUTOFF) expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry); } return idx; } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { if (!is_timers_nohz_active()) return; /* * TODO: This wants some optimizing similar to the code below, but we * will do that when we switch from push to pull for deferrable timers. */ if (timer->flags & TIMER_DEFERRABLE) { if (tick_nohz_full_cpu(base->cpu)) wake_up_nohz_cpu(base->cpu); return; } /* * We might have to IPI the remote CPU if the base is idle and the * timer is not deferrable. If the other CPU is on the way to idle * then it can't set base->is_idle as we hold the base lock: */ if (base->is_idle) wake_up_nohz_cpu(base->cpu); } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap, store the index in the timer flags then wake up * the target CPU if needed. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx, unsigned long bucket_expiry) { hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); trace_timer_start(timer, timer->expires, timer->flags); /* * Check whether this is the new first expiring timer. The * effective expiry time of the timer is required here * (bucket_expiry) instead of timer->expires. */ if (time_before(bucket_expiry, base->next_expiry)) { /* * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned long bucket_expiry; unsigned int idx; idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry); enqueue_timer(base, timer, idx, bucket_expiry); } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr timer_debug_descr; static void *timer_debug_hint(void *addr) { return ((struct timer_list *) addr)->function; } static bool timer_is_static_object(void *addr) { struct timer_list *timer = addr; return (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC); } /* * fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { WARN_ON(1); } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; default: return false; } } static const struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .is_static_object = timer_is_static_object, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL_GPL(init_timer_on_stack_key); void destroy_timer_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_timer_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->function = func; if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS)) flags &= TIMER_INIT_FLAGS; timer->flags = flags | raw_smp_processor_id(); lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * init_timer_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * init_timer_key() must be done to a timer prior calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL(init_timer_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { unsigned idx = timer_get_idx(timer); if (!timer_pending(timer)) return 0; if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) { __clear_bit(idx, base->pending_map); base->next_expiry_recalc = true; } detach_timer(timer, clear_pending); return 1; } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); return base; } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = this_cpu_ptr(&timer_bases[BASE_DEF]); return base; } static inline struct timer_base *get_timer_base(u32 tflags) { return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } static inline struct timer_base * get_target_base(struct timer_base *base, unsigned tflags) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !(tflags & TIMER_PINNED)) return get_timer_cpu_base(tflags, get_nohz_timer_target()); #endif return get_timer_this_cpu_base(tflags); } static inline void forward_timer_base(struct timer_base *base) { unsigned long jnow = READ_ONCE(jiffies); /* * No need to forward if we are close enough below jiffies. * Also while executing timers, base->clk is 1 offset ahead * of jiffies to avoid endless requeuing to current jffies. */ if ((long)(jnow - base->clk) < 1) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ if (time_after(base->next_expiry, jnow)) { base->clk = jnow; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { struct timer_base *base; u32 tf; /* * We need to use READ_ONCE() here, otherwise the compiler * might re-read @tf between the check for TIMER_MIGRATING * and spin_lock(). */ tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 #define MOD_TIMER_NOTPENDING 0x04 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { unsigned long clk = 0, flags, bucket_expiry; struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; int ret = 0; BUG_ON(!timer->function); /* * This is a common optimization triggered by the networking code - if * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new * timer with this expiry. */ long diff = timer->expires - expires; if (!diff) return 1; if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* * We lock timer base and calculate the bucket index right * here. If the timer ends up in the same bucket, then we * just update the expiry time and avoid the whole * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && time_before_eq(timer->expires, expires)) { ret = 1; goto out_unlock; } clk = base->clk; idx = calc_wheel_index(expires, clk, &bucket_expiry); /* * Retrieve and compare the array index of the pending * timer. If it matches set the expiry to the new value so a * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { if (!(options & MOD_TIMER_REDUCE)) timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires; ret = 1; goto out_unlock; } } else { base = lock_timer_base(timer, &flags); forward_timer_base(base); } ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; new_base = get_target_base(base, timer->flags); if (base != new_base) { /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); forward_timer_base(base); } } debug_timer_activate(timer); timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance * between calculating 'idx' and possibly switching the base, only * enqueue_timer() is required. Otherwise we need to (re)calculate * the wheel index via internal_add_timer(). */ if (idx != UINT_MAX && clk == base->clk) enqueue_timer(base, timer, idx, bucket_expiry); else internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - Modify a pending timer's timeout * @timer: The pending timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), but * will not activate inactive timers. * * Return: * * %0 - The timer was inactive and not modified * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - Modify a timer's timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * * mod_timer() is more efficient than the above open coded sequence. In * case that the timer is inactive, the del_timer() part is a NOP. The * timer is in any case activated with the new expiry time @expires. * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * Return: * * %0 - The timer was inactive and started * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires did * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, 0); } EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only * modify an enqueued timer if that would reduce the expiration time. If * @timer is not enqueued it starts the timer. * * Return: * * %0 - The timer was inactive and started * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires * did not change the effective expiry time such that the * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_REDUCE); } EXPORT_SYMBOL(timer_reduce); /** * add_timer - Start a timer * @timer: The timer to be started * * Start @timer to expire at @timer->expires in the future. @timer->expires * is the absolute expiry time measured in 'jiffies'. When the timer expires * timer->function(timer) will be invoked from soft interrupt context. * * The @timer->expires and @timer->function fields must be set prior * to calling this function. * * If @timer->expires is already in the past @timer will be queued to * expire at the next timer tick. * * This can only operate on an inactive timer. Attempts to invoke this on * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { BUG_ON(timer_pending(timer)); __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); /** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * * Same as add_timer() except that it starts the timer on the given CPU. * * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { struct timer_base *new_base, *base; unsigned long flags; BUG_ON(timer_pending(timer) || !timer->function); new_base = get_timer_cpu_base(timer->flags, cpu); /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); if (base != new_base) { timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } forward_timer_base(base); debug_timer_activate(timer); internal_add_timer(base, timer); raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** * del_timer - Deactivate a timer. * @timer: The timer to be deactivated * * The function only deactivates a pending timer, but contrary to * timer_delete_sync() it does not take into account whether the timer's * callback function is concurrently executed on a different CPU or not. * It neither prevents rearming of the timer. If @timer can be rearmed * concurrently then the return value of this function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int del_timer(struct timer_list *timer) { struct timer_base *base; unsigned long flags; int ret = 0; debug_assert_init(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; } EXPORT_SYMBOL(del_timer); /** * try_to_del_timer_sync - Try to deactivate a timer * @timer: Timer to deactivate * * This function tries to deactivate a timer. On success the timer is not * queued and the timer callback function is not running on any CPU. * * This function does not guarantee that the timer cannot be rearmed right * after dropping the base lock. That needs to be prevented by the calling * code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { struct timer_base *base; unsigned long flags; int ret = -1; debug_assert_init(timer); base = lock_timer_base(timer, &flags); if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { spin_lock_init(&base->expiry_lock); } static inline void timer_base_lock_expiry(struct timer_base *base) { spin_lock(&base->expiry_lock); } static inline void timer_base_unlock_expiry(struct timer_base *base) { spin_unlock(&base->expiry_lock); } /* * The counterpart to del_timer_wait_running(). * * If there is a waiter for base->expiry_lock, then it was waiting for the * timer callback to finish. Drop expiry_lock and reaquire it. That allows * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); raw_spin_lock_irq(&base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion, if the softirq thread on a remote CPU * got preempted, and it prevents a life lock when the task which tries to * delete a timer preempted the softirq thread running the timer callback * function. */ static void del_timer_wait_running(struct timer_list *timer) { u32 tf; tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { struct timer_base *base = get_timer_base(tf); /* * Mark the base as contended and grab the expiry lock, * which is held by the softirq across the timer * callback. Drop the lock immediately so the softirq can * expire the next timer. In theory the timer could already * be running again, but that's more than unlikely and just * causes another wait loop. */ atomic_inc(&base->timer_waiters); spin_lock_bh(&base->expiry_lock); atomic_dec(&base->timer_waiters); spin_unlock_bh(&base->expiry_lock); } } #else static inline void timer_base_init_expiry_lock(struct timer_base *base) { } static inline void timer_base_lock_expiry(struct timer_base *base) { } static inline void timer_base_unlock_expiry(struct timer_base *base) { } static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif /** * timer_delete_sync - Deactivate a timer and wait for the handler to finish. * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's callback * function. The timer's handler must not call add_timer_on(). Upon exit * the timer is not queued and the handler is not running on any CPU. * * For !irqsafe timers, the caller must not hold locks that are held in * interrupt context. Even if the lock has nothing to do with the timer in * question. Here's why:: * * CPU0 CPU1 * ---- ---- * <SOFTIRQ> * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * * Now timer_delete_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but it has * interrupted the softirq that CPU0 is waiting to finish. * * This function cannot guarantee that the timer is not rearmed again by * some concurrent or preempting code, right after it dropped the base * lock. If there is the possibility of a concurrent rearm then the return * value of the function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete_sync(struct timer_list *timer) { int ret; #ifdef CONFIG_LOCKDEP unsigned long flags; /* * If lockdep gives a backtrace here, please reference * the synchronization rules above. */ local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it * could lead to deadlock. */ WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); do { ret = try_to_del_timer_sync(timer); if (unlikely(ret < 0)) { del_timer_wait_running(timer); cpu_relax(); } } while (ret < 0); return ret; } EXPORT_SYMBOL(timer_delete_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), unsigned long baseclk) { int count = preempt_count(); #ifdef CONFIG_LOCKDEP /* * It is permissible to free the timer from inside the * function that is called from it, this we need to take into * account for lockdep too. To avoid bogus "held lock freed" * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at * timer_delete_sync() by acquiring the lock_map around the fn() * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent * chance to survive and extract information. If the * callback kept a lock held, bad luck, but not worse * than the BUG() we had. */ preempt_count_set(count); } } static void expire_timers(struct timer_base *base, struct hlist_head *head) { /* * This value is required only for tracing. base->clk was * incremented directly before expire_timers was called. But expiry * is related to the old base->clk value. */ unsigned long baseclk = base->clk - 1; while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); timer = hlist_entry(head->first, struct timer_list, entry); base->running_timer = timer; detach_timer(timer, true); fn = timer->function; if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); } } } static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { unsigned long clk = base->clk = base->next_expiry; struct hlist_head *vec; int i, levels = 0; unsigned int idx; for (i = 0; i < LVL_DEPTH; i++) { idx = (clk & LVL_MASK) + i * LVL_SIZE; if (__test_and_clear_bit(idx, base->pending_map)) { vec = base->vectors + idx; hlist_move_list(vec, heads++); levels++; } /* Is it time to look at the next level? */ if (clk & LVL_CLK_MASK) break; /* Shift clock for the next level granularity */ clk >>= LVL_CLK_SHIFT; } return levels; } /* * Find the next pending bucket of a level. Search from level start (@offset) * + @clk upwards and if nothing there, search from start of the level * (@offset) up to @offset + clk. */ static int next_pending_bucket(struct timer_base *base, unsigned offset, unsigned clk) { unsigned pos, start = offset + clk; unsigned end = offset + LVL_SIZE; pos = find_next_bit(base->pending_map, end, start); if (pos < end) return pos - start; pos = find_next_bit(base->pending_map, start, offset); return pos < start ? pos + LVL_SIZE - start : -1; } /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. */ static unsigned long __next_timer_interrupt(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; next = base->clk + NEXT_TIMER_MAX_DELTA; clk = base->clk; for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { int pos = next_pending_bucket(base, offset, clk & LVL_MASK); unsigned long lvl_clk = clk & LVL_CLK_MASK; if (pos >= 0) { unsigned long tmp = clk + (unsigned long) pos; tmp <<= LVL_SHIFT(lvl); if (time_before(tmp, next)) next = tmp; /* * If the next expiration happens before we reach * the next level, no need to check further. */ if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK)) break; } /* * Clock for the next level. If the current level clock lower * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next * expiring jiffie. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 * * we have to look at all levels @index 0. With * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 2 * * LVL0 has the next expiring bucket @index 2. The upper * levels have the next expiring bucket @index 1. * * In case that the propagation wraps the next level the same * rules apply: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 F 2 * * So after looking at LVL0 we get: * * LVL5 LVL4 LVL3 LVL2 LVL1 * 0 0 0 1 0 * * So no propagation from LVL1 to LVL2 because that happened * with the add already, but then we need to propagate further * from LVL2 to LVL3. * * So the simple check whether the lower bits of the current * level are 0 or not is sufficient for all cases. */ adj = lvl_clk ? 1 : 0; clk >>= LVL_CLK_SHIFT; clk += adj; } base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); return next; } #ifdef CONFIG_NO_HZ_COMMON /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); /* * If high resolution timers are enabled * hrtimer_get_next_event() returns KTIME_MAX. */ if (expires <= nextevt) return expires; /* * If the next timer is already expired, return the tick base * time so the tick is fired immediately. */ if (nextevt <= basem) return basem; /* * Round up to the next jiffie. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. * * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } /** * get_next_timer_interrupt - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending * timer or KTIME_MAX if no timer is pending. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; /* * Pretend that there is no timer pending if the cpu is offline. * Possible pending timers will be migrated later to an active cpu. */ if (cpu_is_offline(smp_processor_id())) return expires; raw_spin_lock(&base->lock); if (base->next_expiry_recalc) base->next_expiry = __next_timer_interrupt(base); nextevt = base->next_expiry; /* * We have a fresh next event. Check whether we can forward the * base. We can only do that when @basej is past base->clk * otherwise we might rewind base->clk. */ if (time_after(basej, base->clk)) { if (time_after(nextevt, basej)) base->clk = basej; else if (time_after(nextevt, base->clk)) base->clk = nextevt; } if (time_before_eq(nextevt, basej)) { expires = basem; base->is_idle = false; } else { if (base->timers_pending) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle. * Also the tick is stopped so any added timer must forward * the base clk itself to keep granularity small. This idle * logic is only maintained for the BASE_STD base, deferrable * timers may still see large granularity skew (by design). */ if ((expires - basem) > TICK_NSEC) base->is_idle = true; } raw_spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * We do this unlocked. The worst outcome is a remote enqueue sending * a pointless IPI, but taking the lock would just make the window for * sending the IPI a few instructions smaller for the cost of taking * the lock in the exit from idle path. */ base->is_idle = false; } #endif /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { struct task_struct *p = current; PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0); /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { struct hlist_head heads[LVL_DEPTH]; int levels; if (time_before(jiffies, base->next_expiry)) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * NEXT_TIMER_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); base->clk++; base->next_expiry = __next_timer_interrupt(base); while (levels--) expire_timers(base, heads + levels); } raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); } /* * Called by the local, per-CPU timer interrupt on SMP. */ void run_local_timers(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); hrtimer_run_queues(); /* Raise the softirq only if required. */ if (time_before(jiffies, base->next_expiry)) { if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) return; /* CPU is awake, so check the deferrable base. */ base++; if (time_before(jiffies, base->next_expiry)) return; } raise_softirq(TIMER_SOFTIRQ); } /* * Since schedule_timeout()'s timer is defined on the stack, it must store * the target task on the stack as well. */ struct process_timer { struct timer_list timer; struct task_struct *task; }; static void process_timeout(struct timer_list *t) { struct process_timer *timeout = from_timer(timeout, t, timer); wake_up_process(timeout->task); } /** * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * * Make the current task sleep until @timeout jiffies have elapsed. * The function behavior depends on the current task state * (see also set_current_state() description): * * %TASK_RUNNING - the scheduler is called, but the task does not sleep * at all. That happens because sched_submit_work() does nothing for * tasks in %TASK_RUNNING state. * * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be %TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule * the CPU away without a bound on the timeout. In this case the return * value will be %MAX_SCHEDULE_TIMEOUT. * * Returns 0 when the timer has expired otherwise the remaining time in * jiffies will be returned. In all cases the return value is guaranteed * to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) { struct process_timer timer; unsigned long expire; switch (timeout) { case MAX_SCHEDULE_TIMEOUT: /* * These two special cases are useful to be comfortable * in the caller. Nothing more. We could take * MAX_SCHEDULE_TIMEOUT from one of the negative value * but I' d like to return a valid offset (>=0) to allow * the caller to do everything it want with the retval. */ schedule(); goto out; default: /* * Another bit of PARANOID. Note that the retval will be * 0 since no piece of kernel is supposed to do a check * for a negative retval of schedule_timeout() (since it * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ if (timeout < 0) { printk(KERN_ERR "schedule_timeout: wrong timeout " "value %lx\n", timeout); dump_stack(); current->state = TASK_RUNNING; goto out; } } expire = timeout + jiffies; timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); schedule(); del_singleshot_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } EXPORT_SYMBOL(schedule_timeout); /* * We can use __set_current_state() here because schedule_timeout() calls * schedule() unconditionally. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { __set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_interruptible); signed long __sched schedule_timeout_killable(signed long timeout) { __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_killable); signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_uninterruptible); /* * Like schedule_timeout_uninterruptible(), except this task will not contribute * to load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { __set_current_state(TASK_IDLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_idle); #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } int timers_prepare_cpu(unsigned int cpu) { struct timer_base *base; int b; for (b = 0; b < NR_BASES; b++) { base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; base->timers_pending = false; base->is_idle = false; } return 0; } int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; int b, i; BUG_ON(cpu_online(cpu)); for (b = 0; b < NR_BASES; b++) { old_base = per_cpu_ptr(&timer_bases[b], cpu); new_base = get_cpu_ptr(&timer_bases[b]); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock_irq(&new_base->lock); raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); /* * The current CPUs base clock might be stale. Update it * before moving the timers over. */ forward_timer_base(new_base); BUG_ON(old_base->running_timer); for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); raw_spin_unlock(&old_base->lock); raw_spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } return 0; } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { struct timer_base *base; int i; for (i = 0; i < NR_BASES; i++) { base = per_cpu_ptr(&timer_bases[i], cpu); base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; timer_base_init_expiry_lock(base); } } static void __init init_timer_cpus(void) { int cpu; for_each_possible_cpu(cpu) init_timer_cpu(cpu); } void __init init_timers(void) { init_timer_cpus(); posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Time in milliseconds to sleep for */ void msleep(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout) timeout = schedule_timeout_uninterruptible(timeout); } EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals * @msecs: Time in milliseconds to sleep for */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); /** * usleep_range - Sleep for an approximate time * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep * * In non-atomic context where the exact wakeup time is flexible, use * usleep_range() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ void __sched usleep_range(unsigned long min, unsigned long max) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { __set_current_state(TASK_UNINTERRUPTIBLE); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } EXPORT_SYMBOL(usleep_range); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { atomic_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (atomic_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) extern struct group_info init_groups; #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; #ifdef CONFIG_DEBUG_CREDENTIALS atomic_t subscribers; /* number of processes subscribed */ void *put_addr; unsigned magic; #define CRED_MAGIC 0x43736564 #define CRED_MAGIC_DEAD 0x44656144 #endif kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* subjective LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int change_create_files_as(struct cred *, struct inode *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); /* * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS extern void __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); extern bool creds_are_invalid(const struct cred *cred); static inline void __validate_creds(const struct cred *cred, const char *file, unsigned line) { if (unlikely(creds_are_invalid(cred))) __invalid_creds(cred, file, line); } #define validate_creds(cred) \ do { \ __validate_creds((cred), __FILE__, __LINE__); \ } while(0) #define validate_process_creds() \ do { \ __validate_process_creds(current, __FILE__, __LINE__); \ } while(0) extern void validate_creds_for_do_exit(struct task_struct *); #else static inline void validate_creds(const struct cred *cred) { } static inline void validate_creds_for_do_exit(struct task_struct *tsk) { } static inline void validate_process_creds(void) { } #endif static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { atomic_long_inc(&cred->usage); return cred; } /** * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred(const struct cred *_cred) { struct cred *cred = (struct cred *) _cred; if (cred) { validate_creds(cred); if (atomic_long_dec_and_test(&(cred)->usage)) __put_cred(cred); } } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <trace/events/writeback.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget() * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __read_mostly; static unsigned int i_hash_shift __read_mostly; static struct hlist_head *inode_hashtable __read_mostly; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); /* * Statistics gathering.. */ struct inodes_stat_t inodes_stat; static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __read_mostly; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; if (sb->s_type->fs_flags & FS_THP_SUPPORT) __set_bit(AS_THP_SUPPORT, &mapping->flags); mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; mapping->writeback_index = 0; inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } static struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * inode->i_lock must be held */ void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else inode->i_state |= I_REFERENCED; } /* * Add inode to LRU if needed (inode is unused and clean). * * Needs inode->i_lock held. */ void inode_add_lru(struct inode *inode) { if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) && !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE) inode_lru_list_add(inode); } static void inode_lru_list_del(struct inode *inode) { if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } static void inode_pin_lru_isolating(struct inode *inode) { lockdep_assert_held(&inode->i_lock); WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); inode->i_state |= I_LRU_ISOLATING; } static void inode_unpin_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); inode->i_state &= ~I_LRU_ISOLATING; smp_mb(); wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); } static void inode_wait_for_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); if (inode->i_state & I_LRU_ISOLATING) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_LRU_ISOLATING); } spin_unlock(&inode->i_lock); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: unsigned long value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void clear_inode(struct inode *inode) { /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __delete_from_page_cache()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); BUG_ON(inode->i_data.nrexceptional); xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode); inode_wait_for_lru_isolating(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); spin_lock(&inode->i_lock); wake_up_bit(&inode->i_state, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; spin_lock(&inode->i_lock); if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on * @kill_dirty: flag to guide handling of dirty inodes * * Attempts to free all inodes for a given superblock. If there were any * busy inodes return a non-zero value, else zero. * If @kill_dirty is set, discard dirty inodes too, otherwise treat * them as busy. */ int invalidate_inodes(struct super_block *sb, bool kill_dirty) { int busy = 0; struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & I_DIRTY_ALL && !kill_dirty) { spin_unlock(&inode->i_lock); busy = 1; continue; } if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); busy = 1; continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); return busy; } /* * Isolate the inode from the LRU in preparation for freeing it. * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. If the inode has metadata buffers attached to * mapping->private_list then try to remove them. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * we are inverting the lru lock/inode->i_lock here, so use a trylock. * If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Referenced or dirty inodes are still in use. Give them another pass * through the LRU as we canot reclaim them now. */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } if (inode_has_buffers(inode) || inode->i_data.nrpages) { inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += reap; } inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode_pseudo - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *new_inode_pseudo(struct super_block *sb) { struct inode *inode = alloc_inode(sb); if (inode) { spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); INIT_LIST_HEAD(&inode->i_sb_list); } return inode; } /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; spin_lock_prefetch(&sb->s_inode_list_lock); inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_inodes - lock two inodes (may be regular files but also dirs) * * Lock any non-NULL argument. The caller must make sure that if he is passing * in two directories, one is not ancestor of the other. Zero, one or two * objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock * @subclass1: inode lock subclass for the first lock obtained * @subclass2: inode lock subclass for the second lock obtained */ void lock_two_inodes(struct inode *inode1, struct inode *inode2, unsigned subclass1, unsigned subclass2) { if (!inode1 || !inode2) { /* * Make sure @subclass1 will be used for the acquired lock. * This is not strictly necessary (no current caller cares) but * let's keep things consistent. */ if (!inode1) swap(inode1, inode2); goto lock; } /* * If one object is directory and the other is not, we must make sure * to lock directory first as the other object may be its child. */ if (S_ISDIR(inode2->i_mode) == S_ISDIR(inode1->i_mode)) { if (inode1 > inode2) swap(inode1, inode2); } else if (!S_ISDIR(inode1->i_mode)) swap(inode1, inode2); lock: if (inode1) inode_lock_nested(inode1, subclass1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, subclass2); } /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument that is not a directory. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1 > inode2) swap(inode1, inode2); if (inode1 && !S_ISDIR(inode1->i_mode)) inode_lock(inode1); if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1 && !S_ISDIR(inode1->i_mode)) inode_unlock(inode1); if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) inode_unlock(inode2); } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a variant of iget5_locked() for callers that don't want to fail on memory * allocation of inode. * * If the inode is not in cache, insert the pre-allocated inode to cache and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; bool creating = inode->i_state & I_CREATING; again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { inode = NULL; goto unlock; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); if (!creating) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { new->i_state = 0; inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; hlist_for_each_entry_rcu(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) return 0; } return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; again: inode = ilookup5_nowait(sb, hashval, test, data); if (inode) { wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, unsigned long hashval, int (*match)(struct inode *, unsigned long, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); /** * find_inode_rcu - find an inode in the inode cache * @sb: Super block of file system to search * @hashval: Key to hash * @test: Function to test match on an inode * @data: Data for test function * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_rcu); /** * find_inode_by_rcu - Find an inode in the inode cache * @sb: Super block of file system to search * @ino: The inode number to match * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_by_ino_rcu(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_by_ino_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_by_ino_rcu); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); if (old->i_state & (I_FREEING|I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (unlikely(old->i_state & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; inode->i_state |= I_CREATING; old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int generic_delete_inode(struct inode *inode) { return 1; } EXPORT_SYMBOL(generic_delete_inode); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; unsigned long state; int drop; WARN_ON(inode->i_state & I_NEW); if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); if (!drop && !(inode->i_state & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { inode_add_lru(inode); spin_unlock(&inode->i_lock); return; } state = inode->i_state; if (!drop) { WRITE_ONCE(inode->i_state, state | I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); state = inode->i_state; WARN_ON(state & I_NEW); state &= ~I_WILL_FREE; } WRITE_ONCE(inode->i_state, state | I_FREEING); if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { if (!inode) return; BUG_ON(inode->i_state & I_CLEAR); retry: if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } iput_final(inode); } } EXPORT_SYMBOL(iput); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in ``*block`` with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in ``*block``, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and ``*block`` is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than either the ctime or mtime or if at least a day has * passed since the last atime update. */ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { if (!(mnt->mnt_flags & MNT_RELATIME)) return 1; /* * Is mtime younger than atime? If yes, update atime: */ if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) return 1; /* * Is ctime younger than atime? If yes, update atime: */ if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0) return 1; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60) return 1; /* * Good, we can skip the atime update: */ return 0; } int generic_update_time(struct inode *inode, struct timespec64 *time, int flags) { int iflags = I_DIRTY_TIME; bool dirty = false; if (flags & S_ATIME) inode->i_atime = *time; if (flags & S_VERSION) dirty = inode_maybe_inc_iversion(inode, false); if (flags & S_CTIME) inode->i_ctime = *time; if (flags & S_MTIME) inode->i_mtime = *time; if ((flags & (S_ATIME | S_CTIME | S_MTIME)) && !(inode->i_sb->s_flags & SB_LAZYTIME)) dirty = true; if (dirty) iflags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, iflags); return 0; } EXPORT_SYMBOL(generic_update_time); /* * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ int inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, time, flags); return generic_update_time(inode, time, flags); } EXPORT_SYMBOL(inode_update_time); /** * touch_atime - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; if (timespec64_equal(&inode->i_atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); struct timespec64 now; if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (__mnt_want_write(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ now = current_time(inode); inode_update_time(inode, &now, S_ATIME); __mnt_drop_write(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = setattr_should_drop_suidgid(inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(dentry, &newattrs, NULL); } /* * Remove special file priviledges (suid, capabilities) when file is written * to or truncated. */ int file_remove_privs(struct file *file) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int kill; int error = 0; /* * Fast path for nothing security related. * As well for non-regular files, e.g. blkdev inodes. * For example, blkdev_write_iter() might get here * trying to remove privs which it is not allowed to. */ if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); if (kill < 0) return kill; if (kill) error = __remove_privs(dentry, kill); if (!error) inode_has_no_xattr(inode); return error; } EXPORT_SYMBOL(file_remove_privs); /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode * for writeback. Note that this function is meant exclusively for * usage in the file write path of filesystems, and filesystems may * choose to explicitly ignore update via this function with the * S_NOCMTIME inode flag, e.g. for network filesystem where these * timestamps are handled by the server. This can return an error for * file systems who need to allocate space in order to update an inode. */ int file_update_time(struct file *file) { struct inode *inode = file_inode(file); struct timespec64 now; int sync_it = 0; int ret; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; now = current_time(inode); if (!timespec64_equal(&inode->i_mtime, &now)) sync_it = S_MTIME; if (!timespec64_equal(&inode->i_ctime, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) sync_it |= S_VERSION; if (!sync_it) return 0; /* Finally allowed to write? Takes lock. */ if (__mnt_want_write_file(file)) return 0; ret = inode_update_time(inode, &now, sync_it); __mnt_drop_write_file(file); return ret; } EXPORT_SYMBOL(file_update_time); /* Caller must hold the file's inode lock */ int file_modified(struct file *file) { int err; /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ err = file_remove_privs(file); if (err) return err; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; return file_update_time(file); } EXPORT_SYMBOL(file_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wq_entry); spin_lock(&inode_hash_lock); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { if (!str) return 0; ihash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; if (S_ISCHR(mode)) { inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode */ void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode) { inode->i_uid = current_fsuid(); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode->i_gid = current_fsgid(); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. */ bool inode_owner_or_capable(const struct inode *inode) { struct user_namespace *ns; if (uid_eq(current_fsuid(), inode->i_uid)) return true; ns = current_user_ns(); if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ static void __inode_dio_wait(struct inode *inode) { wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); finish_wait(wq, &q.wq_entry); } /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ void inode_dio_wait(struct inode *inode) { if (atomic_read(&inode->i_dio_count)) __inode_dio_wait(inode); } EXPORT_SYMBOL(inode_dio_wait); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_mutex, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_mutex is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * current_time - Return FS time * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs. * * Note that inode and inode->sb cannot be NULL. * Otherwise, the function warns and returns time without truncation. */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; ktime_get_coarse_real_ts64(&now); if (unlikely(!inode->i_sb)) { WARN(1, "current_time() called with uninitialized super_block in the inode"); return now; } return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); /* * Generic function to check FS_IOC_SETFLAGS values and reject any invalid * configurations. * * Note: the caller should be holding i_mutex, or else be sure that they have * exclusive access to the inode structure. */ int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, unsigned int flags) { /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. * * This test looks nicer. Thanks to Pauline Middelink */ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; return fscrypt_prepare_setflags(inode, oldflags, flags); } EXPORT_SYMBOL(vfs_ioc_setflags_prepare); /* * Generic function to check FS_IOC_FSSETXATTR values and reject any invalid * configurations. * * Note: the caller should be holding i_mutex, or else be sure that they have * exclusive access to the inode structure. */ int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, struct fsxattr *fa) { /* * Can't modify an immutable/append-only file unless we have * appropriate permission. */ if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_fa->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } EXPORT_SYMBOL(vfs_ioc_fssetxattr_check); /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * * Set the inode->i_ctime to the current value for the inode. Returns * the current value that was assigned to i_ctime. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now = current_time(inode); inode_set_ctime(inode, now.tv_sec, now.tv_nsec); return now; } EXPORT_SYMBOL(inode_set_ctime_current); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @inode: inode to check * @gid: the new/current gid of @inode * * Check wether @gid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * * Return: true if the caller is sufficiently privileged, false if not. */ bool in_group_or_capable(const struct inode *inode, kgid_t gid) { if (in_group_p(gid)) return true; if (capable_wrt_inode_uidgid(inode, CAP_FSETID)) return true; return false; } /** * mode_strip_sgid - handle the sgid bit for non-directories * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_or_capable(dir, dir->i_gid)) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef RQ_QOS_H #define RQ_QOS_H #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blk_types.h> #include <linux/atomic.h> #include <linux/wait.h> #include <linux/blk-mq.h> #include "blk-mq-debugfs.h" struct blk_mq_debugfs_attr; enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_LATENCY, RQ_QOS_COST, }; struct rq_wait { wait_queue_head_t wait; atomic_t inflight; }; struct rq_qos { struct rq_qos_ops *ops; struct request_queue *q; enum rq_qos_id id; struct rq_qos *next; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; #endif }; struct rq_qos_ops { void (*throttle)(struct rq_qos *, struct bio *); void (*track)(struct rq_qos *, struct request *, struct bio *); void (*merge)(struct rq_qos *, struct request *, struct bio *); void (*issue)(struct rq_qos *, struct request *); void (*requeue)(struct rq_qos *, struct request *); void (*done)(struct rq_qos *, struct request *); void (*done_bio)(struct rq_qos *, struct bio *); void (*cleanup)(struct rq_qos *, struct bio *); void (*queue_depth_changed)(struct rq_qos *); void (*exit)(struct rq_qos *); const struct blk_mq_debugfs_attr *debugfs_attrs; }; struct rq_depth { unsigned int max_depth; int scale_step; bool scaled_max; unsigned int queue_depth; unsigned int default_depth; }; static inline struct rq_qos *rq_qos_id(struct request_queue *q, enum rq_qos_id id) { struct rq_qos *rqos; for (rqos = q->rq_qos; rqos; rqos = rqos->next) { if (rqos->id == id) break; } return rqos; } static inline struct rq_qos *wbt_rq_qos(struct request_queue *q) { return rq_qos_id(q, RQ_QOS_WBT); } static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q) { return rq_qos_id(q, RQ_QOS_LATENCY); } static inline const char *rq_qos_id_to_name(enum rq_qos_id id) { switch (id) { case RQ_QOS_WBT: return "wbt"; case RQ_QOS_LATENCY: return "latency"; case RQ_QOS_COST: return "cost"; } return "unknown"; } static inline void rq_wait_init(struct rq_wait *rq_wait) { atomic_set(&rq_wait->inflight, 0); init_waitqueue_head(&rq_wait->wait); } static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { /* * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. * * Reuse ->queue_lock for protecting against other concurrent * rq_qos adding/deleting */ blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); rqos->next = q->rq_qos; q->rq_qos = rqos; spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); if (rqos->ops->debugfs_attrs) blk_mq_debugfs_register_rqos(rqos); } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { struct rq_qos **cur; /* * See comment in rq_qos_add() about freezing queue & using * ->queue_lock. */ blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); blk_mq_debugfs_unregister_rqos(rqos); } typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data); typedef void (cleanup_cb_t)(struct rq_wait *rqw, void *private_data); void rq_qos_wait(struct rq_wait *rqw, void *private_data, acquire_inflight_cb_t *acquire_inflight_cb, cleanup_cb_t *cleanup_cb); bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit); bool rq_depth_scale_up(struct rq_depth *rqd); bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle); bool rq_depth_calc_max_depth(struct rq_depth *rqd); void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio); void __rq_qos_done(struct rq_qos *rqos, struct request *rq); void __rq_qos_issue(struct rq_qos *rqos, struct request *rq); void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq); void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio); void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio); void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio); void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio); void __rq_qos_queue_depth_changed(struct rq_qos *rqos); static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { if (q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); } static inline void rq_qos_done(struct request_queue *q, struct request *rq) { if (q->rq_qos) __rq_qos_done(q->rq_qos, rq); } static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { if (q->rq_qos) __rq_qos_issue(q->rq_qos, rq); } static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { if (q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); } static inline void rq_qos_done_bio(struct request_queue *q, struct bio *bio) { if (q->rq_qos) __rq_qos_done_bio(q->rq_qos, bio); } static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { /* * BIO_TRACKED lets controllers know that a bio went through the * normal rq_qos path. */ bio_set_flag(bio, BIO_TRACKED); if (q->rq_qos) __rq_qos_throttle(q->rq_qos, bio); } static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { if (q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); } static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { if (q->rq_qos) __rq_qos_merge(q->rq_qos, rq, bio); } static inline void rq_qos_queue_depth_changed(struct request_queue *q) { if (q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); } void rq_qos_exit(struct request_queue *); #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 | // SPDX-License-Identifier: GPL-2.0 /* bounce buffer handling for block devices * * - Split from highmem.c */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/gfp.h> #include <linux/bio.h> #include <linux/pagemap.h> #include <linux/mempool.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> #include <linux/memblock.h> #include <linux/printk.h> #include <asm/tlbflush.h> #include <trace/events/block.h> #include "blk.h" #define POOL_SIZE 64 #define ISA_POOL_SIZE 16 static struct bio_set bounce_bio_set, bounce_bio_split; static mempool_t page_pool, isa_page_pool; static void init_bounce_bioset(void) { static bool bounce_bs_setup; int ret; if (bounce_bs_setup) return; ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); BUG_ON(ret); if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE)) BUG_ON(1); ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0); BUG_ON(ret); bounce_bs_setup = true; } #if defined(CONFIG_HIGHMEM) static __init int init_emergency_pool(void) { int ret; #if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG) if (max_pfn <= max_low_pfn) return 0; #endif ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0); BUG_ON(ret); pr_info("pool size: %d pages\n", POOL_SIZE); init_bounce_bioset(); return 0; } __initcall(init_emergency_pool); #endif #ifdef CONFIG_HIGHMEM /* * highmem version, map in to vec */ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) { unsigned char *vto; vto = kmap_atomic(to->bv_page); memcpy(vto + to->bv_offset, vfrom, to->bv_len); kunmap_atomic(vto); } #else /* CONFIG_HIGHMEM */ #define bounce_copy_vec(to, vfrom) \ memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len) #endif /* CONFIG_HIGHMEM */ /* * allocate pages in the DMA region for the ISA pool */ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data) { return mempool_alloc_pages(gfp_mask | GFP_DMA, data); } static DEFINE_MUTEX(isa_mutex); /* * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA * as the max address, so check if the pool has already been created. */ int init_emergency_isa_pool(void) { int ret; mutex_lock(&isa_mutex); if (mempool_initialized(&isa_page_pool)) { mutex_unlock(&isa_mutex); return 0; } ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa, mempool_free_pages, (void *) 0); BUG_ON(ret); pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE); init_bounce_bioset(); mutex_unlock(&isa_mutex); return 0; } /* * Simple bounce buffer support for highmem pages. Depending on the * queue gfp mask set, *to may or may not be a highmem page. kmap it * always, it will do the Right Thing */ static void copy_to_high_bio_irq(struct bio *to, struct bio *from) { unsigned char *vfrom; struct bio_vec tovec, fromvec; struct bvec_iter iter; /* * The bio of @from is created by bounce, so we can iterate * its bvec from start to end, but the @from->bi_iter can't be * trusted because it might be changed by splitting. */ struct bvec_iter from_iter = BVEC_ITER_ALL_INIT; bio_for_each_segment(tovec, to, iter) { fromvec = bio_iter_iovec(from, from_iter); if (tovec.bv_page != fromvec.bv_page) { /* * fromvec->bv_offset and fromvec->bv_len might have * been modified by the block layer, so use the original * copy, bounce_copy_vec already uses tovec->bv_len */ vfrom = page_address(fromvec.bv_page) + tovec.bv_offset; bounce_copy_vec(&tovec, vfrom); flush_dcache_page(tovec.bv_page); } bio_advance_iter(from, &from_iter, tovec.bv_len); } } static void bounce_end_io(struct bio *bio, mempool_t *pool) { struct bio *bio_orig = bio->bi_private; struct bio_vec *bvec, orig_vec; struct bvec_iter orig_iter = bio_orig->bi_iter; struct bvec_iter_all iter_all; /* * free up bounce indirect pages used */ bio_for_each_segment_all(bvec, bio, iter_all) { orig_vec = bio_iter_iovec(bio_orig, orig_iter); if (bvec->bv_page != orig_vec.bv_page) { dec_zone_page_state(bvec->bv_page, NR_BOUNCE); mempool_free(bvec->bv_page, pool); } bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len); } bio_orig->bi_status = bio->bi_status; bio_endio(bio_orig); bio_put(bio); } static void bounce_end_io_write(struct bio *bio) { bounce_end_io(bio, &page_pool); } static void bounce_end_io_write_isa(struct bio *bio) { bounce_end_io(bio, &isa_page_pool); } static void __bounce_end_io_read(struct bio *bio, mempool_t *pool) { struct bio *bio_orig = bio->bi_private; if (!bio->bi_status) copy_to_high_bio_irq(bio_orig, bio); bounce_end_io(bio, pool); } static void bounce_end_io_read(struct bio *bio) { __bounce_end_io_read(bio, &page_pool); } static void bounce_end_io_read_isa(struct bio *bio) { __bounce_end_io_read(bio, &isa_page_pool); } static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, struct bio_set *bs) { struct bvec_iter iter; struct bio_vec bv; struct bio *bio; /* * Pre immutable biovecs, __bio_clone() used to just do a memcpy from * bio_src->bi_io_vec to bio->bi_io_vec. * * We can't do that anymore, because: * * - The point of cloning the biovec is to produce a bio with a biovec * the caller can modify: bi_idx and bi_bvec_done should be 0. * * - The original bio could've had more than BIO_MAX_PAGES biovecs; if * we tried to clone the whole thing bio_alloc_bioset() would fail. * But the clone should succeed as long as the number of biovecs we * actually need to allocate is fewer than BIO_MAX_PAGES. * * - Lastly, bi_vcnt should not be looked at or relied upon by code * that does not own the bio - reason being drivers don't use it for * iterating over the biovec anymore, so expecting it to be kept up * to date (i.e. for clones that share the parent biovec) is just * asking for trouble and would force extra work on * __bio_clone_fast() anyways. */ bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs); if (!bio) return NULL; bio->bi_disk = bio_src->bi_disk; bio->bi_opf = bio_src->bi_opf; bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: break; case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; break; default: bio_for_each_segment(bv, bio_src, iter) bio->bi_io_vec[bio->bi_vcnt++] = bv; break; } if (bio_crypt_clone(bio, bio_src, gfp_mask) < 0) goto err_put; if (bio_integrity(bio_src) && bio_integrity_clone(bio, bio_src, gfp_mask) < 0) goto err_put; bio_clone_blkg_association(bio, bio_src); blkcg_bio_issue_init(bio); return bio; err_put: bio_put(bio); return NULL; } static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, mempool_t *pool) { struct bio *bio; int rw = bio_data_dir(*bio_orig); struct bio_vec *to, from; struct bvec_iter iter; unsigned i = 0; bool bounce = false; int sectors = 0; bool passthrough = bio_is_passthrough(*bio_orig); bio_for_each_segment(from, *bio_orig, iter) { if (i++ < BIO_MAX_PAGES) sectors += from.bv_len >> 9; if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn) bounce = true; } if (!bounce) return; if (!passthrough && sectors < bio_sectors(*bio_orig)) { bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split); bio_chain(bio, *bio_orig); submit_bio_noacct(*bio_orig); *bio_orig = bio; } bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL : &bounce_bio_set); /* * Bvec table can't be updated by bio_for_each_segment_all(), * so retrieve bvec from the table directly. This way is safe * because the 'bio' is single-page bvec. */ for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) { struct page *page = to->bv_page; if (page_to_pfn(page) <= q->limits.bounce_pfn) continue; to->bv_page = mempool_alloc(pool, q->bounce_gfp); inc_zone_page_state(to->bv_page, NR_BOUNCE); if (rw == WRITE) { char *vto, *vfrom; flush_dcache_page(page); vto = page_address(to->bv_page) + to->bv_offset; vfrom = kmap_atomic(page) + to->bv_offset; memcpy(vto, vfrom, to->bv_len); kunmap_atomic(vfrom); } } trace_block_bio_bounce(q, *bio_orig); bio->bi_flags |= (1 << BIO_BOUNCED); if (pool == &page_pool) { bio->bi_end_io = bounce_end_io_write; if (rw == READ) bio->bi_end_io = bounce_end_io_read; } else { bio->bi_end_io = bounce_end_io_write_isa; if (rw == READ) bio->bi_end_io = bounce_end_io_read_isa; } bio->bi_private = *bio_orig; *bio_orig = bio; } void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) { mempool_t *pool; /* * Data-less bio, nothing to bounce */ if (!bio_has_data(*bio_orig)) return; /* * for non-isa bounce case, just check if the bounce pfn is equal * to or bigger than the highest pfn in the system -- in that case, * don't waste time iterating over bio segments */ if (!(q->bounce_gfp & GFP_DMA)) { if (q->limits.bounce_pfn >= blk_max_pfn) return; pool = &page_pool; } else { BUG_ON(!mempool_initialized(&isa_page_pool)); pool = &isa_page_pool; } /* * slow path */ __blk_queue_bounce(q, bio_orig, pool); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SIGNAL_H #define _LINUX_SIGNAL_H #include <linux/bug.h> #include <linux/signal_types.h> #include <linux/string.h> struct task_struct; /* for sysctl */ extern int print_fatal_signals; static inline void copy_siginfo(kernel_siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } #define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) static inline void copy_siginfo_to_external(siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*from)); memset(((char *)to) + sizeof(struct kernel_siginfo), 0, SI_EXPANSION_SIZE); } int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); enum siginfo_layout { SIL_KILL, SIL_TIMER, SIL_POLL, SIL_FAULT, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, SIL_CHLD, SIL_RT, SIL_SYS, }; enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. */ #ifndef __HAVE_ARCH_SIG_BITOPS #include <linux/bitops.h> /* We don't use <linux/bitops.h> for these because there is no need to be atomic. */ static inline void sigaddset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] |= 1UL << sig; else set->sig[sig / _NSIG_BPW] |= 1UL << (sig % _NSIG_BPW); } static inline void sigdelset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] &= ~(1UL << sig); else set->sig[sig / _NSIG_BPW] &= ~(1UL << (sig % _NSIG_BPW)); } static inline int sigismember(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) return 1 & (set->sig[0] >> sig); else return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW)); } #endif /* __HAVE_ARCH_SIG_BITOPS */ static inline int sigisemptyset(sigset_t *set) { switch (_NSIG_WORDS) { case 4: return (set->sig[3] | set->sig[2] | set->sig[1] | set->sig[0]) == 0; case 2: return (set->sig[1] | set->sig[0]) == 0; case 1: return set->sig[0] == 0; default: BUILD_BUG(); return 0; } } static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) { switch (_NSIG_WORDS) { case 4: return (set1->sig[3] == set2->sig[3]) && (set1->sig[2] == set2->sig[2]) && (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 2: return (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 1: return set1->sig[0] == set2->sig[0]; } return 0; } #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS #include <linux/string.h> #define _SIG_SET_BINOP(name, op) \ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ { \ unsigned long a0, a1, a2, a3, b0, b1, b2, b3; \ \ switch (_NSIG_WORDS) { \ case 4: \ a3 = a->sig[3]; a2 = a->sig[2]; \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_or(x,y) ((x) | (y)) _SIG_SET_BINOP(sigorsets, _sig_or) #define _sig_and(x,y) ((x) & (y)) _SIG_SET_BINOP(sigandsets, _sig_and) #define _sig_andn(x,y) ((x) & ~(y)) _SIG_SET_BINOP(sigandnsets, _sig_andn) #undef _SIG_SET_BINOP #undef _sig_or #undef _sig_and #undef _sig_andn #define _SIG_SET_OP(name, op) \ static inline void name(sigset_t *set) \ { \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_not(x) (~(x)) _SIG_SET_OP(signotset, _sig_not) #undef _SIG_SET_OP #undef _sig_not static inline void sigemptyset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; fallthrough; case 1: set->sig[0] = 0; break; } } static inline void sigfillset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; fallthrough; case 1: set->sig[0] = -1; break; } } /* Some extensions for manipulating the low 32 signals in particular. */ static inline void sigaddsetmask(sigset_t *set, unsigned long mask) { set->sig[0] |= mask; } static inline void sigdelsetmask(sigset_t *set, unsigned long mask) { set->sig[0] &= ~mask; } static inline int sigtestsetmask(sigset_t *set, unsigned long mask) { return (set->sig[0] & mask) != 0; } static inline void siginitset(sigset_t *set, unsigned long mask) { set->sig[0] = mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = 0; break; case 1: ; } } static inline void siginitsetinv(sigset_t *set, unsigned long mask) { set->sig[0] = ~mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = -1; break; case 1: ; } } #endif /* __HAVE_ARCH_SIG_SETOPS */ static inline void init_sigpending(struct sigpending *sig) { sigemptyset(&sig->signal); INIT_LIST_HEAD(&sig->list); } extern void flush_sigqueue(struct sigpending *queue); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) { return sig <= _NSIG ? 1 : 0; } struct timespec; struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; extern bool get_signal(struct ksignal *ksig); extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void exit_signals(struct task_struct *tsk); extern void kernel_sigaction(int, __sighandler_t); #define SIG_KTHREAD ((__force __sighandler_t)2) #define SIG_KTHREAD_KERNEL ((__force __sighandler_t)3) static inline void allow_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know it'll be handled, so that they don't get converted to * SIGKILL or just silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD); } static inline void allow_kernel_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know signals sent by the kernel will be handled, so that they * don't get silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD_KERNEL); } static inline void disallow_signal(int sig) { kernel_sigaction(sig, SIG_IGN); } extern struct kmem_cache *sighand_cachep; extern bool unhandled_signal(struct task_struct *tsk, int sig); /* * In POSIX a signal is sent either to a specific thread (Linux task) * or to the process as a whole (Linux thread group). How the signal * is sent determines whether it's to one thread or the whole group, * which determines which signal mask(s) are involved in blocking it * from being delivered until later. When the signal is delivered, * either it's caught or ignored by a user handler or it has a default * effect that applies to the whole thread group (POSIX process). * * The possible effects an unblocked signal set to SIG_DFL can have are: * ignore - Nothing Happens * terminate - kill the process, i.e. all threads in the group, * similar to exit_group. The group leader (only) reports * WIFSIGNALED status to its parent. * coredump - write a core dump file describing all threads using * the same mm and then kill all those threads * stop - stop all the threads in the group, i.e. TASK_STOPPED state * * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored. * Other signals when not blocked and set to SIG_DFL behaves as follows. * The job control signals also have other special effects. * * +--------------------+------------------+ * | POSIX signal | default action | * +--------------------+------------------+ * | SIGHUP | terminate | * | SIGINT | terminate | * | SIGQUIT | coredump | * | SIGILL | coredump | * | SIGTRAP | coredump | * | SIGABRT/SIGIOT | coredump | * | SIGBUS | coredump | * | SIGFPE | coredump | * | SIGKILL | terminate(+) | * | SIGUSR1 | terminate | * | SIGSEGV | coredump | * | SIGUSR2 | terminate | * | SIGPIPE | terminate | * | SIGALRM | terminate | * | SIGTERM | terminate | * | SIGCHLD | ignore | * | SIGCONT | ignore(*) | * | SIGSTOP | stop(*)(+) | * | SIGTSTP | stop(*) | * | SIGTTIN | stop(*) | * | SIGTTOU | stop(*) | * | SIGURG | ignore | * | SIGXCPU | coredump | * | SIGXFSZ | coredump | * | SIGVTALRM | terminate | * | SIGPROF | terminate | * | SIGPOLL/SIGIO | terminate | * | SIGSYS/SIGUNUSED | coredump | * | SIGSTKFLT | terminate | * | SIGWINCH | ignore | * | SIGPWR | terminate | * | SIGRTMIN-SIGRTMAX | terminate | * +--------------------+------------------+ * | non-POSIX signal | default action | * +--------------------+------------------+ * | SIGEMT | coredump | * +--------------------+------------------+ * * (+) For SIGKILL and SIGSTOP the action is "always", not just "default". * (*) Special job control effects: * When SIGCONT is sent, it resumes the process (all threads in the group) * from TASK_STOPPED state and also clears any pending/queued stop signals * (any of those marked with "stop(*)"). This happens regardless of blocking, * catching, or ignoring SIGCONT. When any stop signal is sent, it clears * any pending/queued SIGCONT signals; this happens regardless of blocking, * catching, or ignored the stop signal, though (except for SIGSTOP) the * default action of stopping the process may happen later or never. */ #ifdef SIGEMT #define SIGEMT_MASK rt_sigmask(SIGEMT) #else #define SIGEMT_MASK 0 #endif #if SIGRTMIN > BITS_PER_LONG #define rt_sigmask(sig) (1ULL << ((sig)-1)) #else #define rt_sigmask(sig) sigmask(sig) #endif #define siginmask(sig, mask) \ ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) #define SIG_KERNEL_STOP_MASK (\ rt_sigmask(SIGSTOP) | rt_sigmask(SIGTSTP) | \ rt_sigmask(SIGTTIN) | rt_sigmask(SIGTTOU) ) #define SIG_KERNEL_COREDUMP_MASK (\ rt_sigmask(SIGQUIT) | rt_sigmask(SIGILL) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGABRT) | \ rt_sigmask(SIGFPE) | rt_sigmask(SIGSEGV) | \ rt_sigmask(SIGBUS) | rt_sigmask(SIGSYS) | \ rt_sigmask(SIGXCPU) | rt_sigmask(SIGXFSZ) | \ SIGEMT_MASK ) #define SIG_KERNEL_IGNORE_MASK (\ rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) #define SIG_SPECIFIC_SICODES_MASK (\ rt_sigmask(SIGILL) | rt_sigmask(SIGFPE) | \ rt_sigmask(SIGSEGV) | rt_sigmask(SIGBUS) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGPOLL) | rt_sigmask(SIGSYS) | \ SIGEMT_MASK ) #define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) #define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) #define sig_specific_sicodes(sig) siginmask(sig, SIG_SPECIFIC_SICODES_MASK) #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL) void signals_init(void); int restore_altstack(const stack_t __user *); int __save_altstack(stack_t __user *, unsigned long); #define unsafe_save_altstack(uss, sp, label) do { \ stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ if (t->sas_ss_flags & SS_AUTODISARM) \ sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); #endif #endif /* _LINUX_SIGNAL_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * Basic idea behind the notification queue: An fsnotify group (like inotify) * sends the userspace notification about events asynchronously some time after * the event happened. When inotify gets an event it will need to add that * event to the group notify queue. Since a single event might need to be on * multiple group's notification queues we can't add the event directly to each * queue and instead add a small "event_holder" to each queue. This event_holder * has a pointer back to the original event. Since the majority of events are * going to end up on one, and only one, notification queue we embed one * event_holder into each event. This means we have a single allocation instead * of always needing two. If the embedded event_holder is already in use by * another group a new event_holder (from fsnotify_event_holder_cachep) will be * allocated and used. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" static atomic_t fsnotify_sync_cookie = ATOMIC_INIT(0); /** * fsnotify_get_cookie - return a unique cookie for use in synchronizing events. * Called from fsnotify_move, which is inlined into filesystem modules. */ u32 fsnotify_get_cookie(void) { return atomic_inc_return(&fsnotify_sync_cookie); } EXPORT_SYMBOL_GPL(fsnotify_get_cookie); void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event) { /* Overflow events are per-group and we don't want to free them */ if (!event || event == group->overflow_event) return; /* * If the event is still queued, we have a problem... Do an unreliable * lockless check first to avoid locking in the common case. The * locking may be necessary for permission events which got removed * from the list by a different CPU than the one freeing the event. */ if (!list_empty(&event->list)) { spin_lock(&group->notification_lock); WARN_ON(!list_empty(&event->list)); spin_unlock(&group->notification_lock); } group->ops->free_event(group, event); } /* * Try to add an event to the notification queue. * The group can later pull this event off the queue to deal with. * The group can use the @merge hook to merge the event with a queued event. * The group can use the @insert hook to insert the event into hash table. * The function returns: * 0 if the event was added to a queue * 1 if the event was merged with some other queued event * 2 if the event was not queued - either the queue of events has overflown * or the group is shutting down. */ int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)) { int ret = 0; struct list_head *list = &group->notification_list; pr_debug("%s: group=%p event=%p\n", __func__, group, event); spin_lock(&group->notification_lock); if (group->shutdown) { spin_unlock(&group->notification_lock); return 2; } if (event == group->overflow_event || group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ if (!list_empty(&group->overflow_event->list)) { spin_unlock(&group->notification_lock); return ret; } event = group->overflow_event; goto queue; } if (!list_empty(list) && merge) { ret = merge(group, event); if (ret) { spin_unlock(&group->notification_lock); return ret; } } queue: group->q_len++; list_add_tail(&event->list, list); if (insert) insert(group, event); spin_unlock(&group->notification_lock); wake_up(&group->notification_waitq); kill_fasync(&group->fsn_fa, SIGIO, POLL_IN); return ret; } void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event) { assert_spin_locked(&group->notification_lock); /* * We need to init list head for the case of overflow event so that * check in fsnotify_add_event() works */ list_del_init(&event->list); group->q_len--; } /* * Return the first event on the notification list without removing it. * Returns NULL if the list is empty. */ struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); if (fsnotify_notify_queue_is_empty(group)) return NULL; return list_first_entry(&group->notification_list, struct fsnotify_event, list); } /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event */ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group) { struct fsnotify_event *event = fsnotify_peek_first_event(group); if (!event) return NULL; pr_debug("%s: group=%p event=%p\n", __func__, group, event); fsnotify_remove_queued_event(group, event); return event; } /* * Called when a group is being torn down to clean up any outstanding * event notifications. */ void fsnotify_flush_notify(struct fsnotify_group *group) { struct fsnotify_event *event; spin_lock(&group->notification_lock); while (!fsnotify_notify_queue_is_empty(group)) { event = fsnotify_remove_first_event(group); spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, event); spin_lock(&group->notification_lock); } spin_unlock(&group->notification_lock); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->i_ino = page->mapping->host->i_ino; __entry->index = page->index; if (page->mapping->host->i_sb) __entry->s_dev = page->mapping->host->i_sb->s_dev; else __entry->s_dev = page->mapping->host->i_rdev; ), TP_printk("dev %d:%d ino %lx page=%p pfn=%lu ofs=%lu", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, pfn_to_page(__entry->pfn), __entry->pfn, __entry->index << PAGE_SHIFT) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct page *page), TP_ARGS(page) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct page *page), TP_ARGS(page) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } #else static inline int posix_acl_chmod(struct inode *inode, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that makes the machine dump writes/reads and block dirtyings. */ int block_dump; /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Unreclaimable memory (kernel memory or anonymous memory * without swap) can bring down the dirtyable pages below * the zone's dirty balance reserve and the above calculation * will underflow. However we still want to add in nodes * which are below threshold (negative values) to get a more * accurate calculation but make sure that the total never * underflows. */ if ((long)x < 0) x = 0; /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ if (thresh > UINT_MAX) thresh = UINT_MAX; /* This makes sure bg_thresh is within 32-bits as well */ if (bg_thresh >= thresh) bg_thresh = thresh / 2; dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ return min_t(unsigned long, dirty, UINT_MAX); } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; unsigned long old_bytes = dirty_background_bytes; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) { if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) > UINT_MAX) { dirty_background_bytes = old_bytes; return -ERANGE; } dirty_background_ratio = 0; } return ret; } int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { vm_dirty_bytes = 0; writeback_set_ratelimit(); } return ret; } int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) { vm_dirty_bytes = old_bytes; return -ERANGE; } writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_inc(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac) { __fprop_inc_percpu_max(&dom->completions, completions, max_prop_frac); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from test_clear_page_writeback(). */ static inline void __wb_writeout_inc(struct bdi_writeback *wb) { struct wb_domain *cgdom; inc_wb_stat(wb, WB_WRITTEN); wb_domain_writeout_inc(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_inc(wb); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { min_ratio -= bdi->min_ratio; if (bdi_min_ratio + min_ratio < 100) { bdi_min_ratio += min_ratio; bdi->min_ratio += min_ratio; } else { ret = -EINVAL; } } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) { int ret = 0; if (max_ratio > 100) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; } spin_unlock_bh(&bdi_lock); return ret; } EXPORT_SYMBOL(bdi_set_max_ratio); static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } /** * __wb_calc_thresh - @wb's share of dirty throttling threshold * @dtc: dirty_throttle_context of interest * * Note that balance_dirty_pages() will only seriously take it as a hard limit * when sleeping max_pause per page is not enough to keep the dirty pages under * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty and PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this BDI's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / 100; if (wb_thresh > (thresh * wb_max_ratio) / 100) wb_thresh = thresh * wb_max_ratio / 100; return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb), .thresh = thresh }; return __wb_calc_thresh(&gdtc); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 .............* * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to account_page_redirty(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; wb->avg_write_bandwidth = avg; } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_bandwidth(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; wb->dirty_ratelimit = max(dirty_ratelimit, 1UL); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, unsigned long start_time, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed = now - wb->bw_time_stamp; unsigned long dirtied; unsigned long written; lockdep_assert_held(&wb->list_lock); /* * rate-limit, only update once every 200ms. */ if (elapsed < BANDWIDTH_INTERVAL) return; dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); /* * Skip quiet periods when disk bandwidth is under-utilized. * (at least 1s idle time between two flusher runs) */ if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) goto snapshot; if (update_ratelimit) { domain_update_bandwidth(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_bandwidth(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); snapshot: wb->dirtied_stamp = dirtied; wb->written_stamp = written; wb->bw_time_stamp = now; } void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, start_time, false); } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = wb->avg_write_bandwidth; unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(wb->avg_write_bandwidth); long lo = ilog2(wb->dirty_ratelimit); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static void balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty */ long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; unsigned long m_dirty = 0; /* stop bogus uninit warnings */ unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { wb_dirty_limits(gdtc); dirty = gdtc->wb_dirty; thresh = gdtc->wb_thresh; bg_thresh = gdtc->wb_bg_thresh; } else { dirty = gdtc->dirty; thresh = gdtc->thresh; bg_thresh = gdtc->bg_thresh; } if (mdtc) { unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc->dirty += writeback; mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); if (unlikely(strictlimit)) { wb_dirty_limits(mdtc); m_dirty = mdtc->wb_dirty; m_thresh = mdtc->wb_thresh; m_bg_thresh = mdtc->wb_bg_thresh; } else { m_dirty = mdtc->dirty; m_thresh = mdtc->thresh; m_bg_thresh = mdtc->bg_thresh; } } /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the wb limits are ramping up in case of !strictlimit. * * In strictlimit case make decision based on the wb counters * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. * * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } if (dirty_exceeded && !wb->dirty_exceeded) wb->dirty_exceeded = 1; if (time_is_before_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL)) { spin_lock(&wb->list_lock); __wb_update_bandwidth(gdtc, mdtc, start_time, true); spin_unlock(&wb->list_lock); } /* throttle according to the chosen dtc */ dirty_ratelimit = wb->dirty_ratelimit; task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); __set_current_state(TASK_KILLABLE); wb->dirty_sleep = now; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponding NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } if (!dirty_exceeded && wb->dirty_exceeded) wb->dirty_exceeded = 0; if (writeback_in_progress(wb)) return; /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (laptop_mode) return; if (nr_reclaimable > gdtc->bg_thresh) wb_start_background_writeback(wb); } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited - balance dirty memory state * @mapping: address_space which was dirtied * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * On really big machines, get_writeback_state is expensive, so try to avoid * calling it too often (ratelimiting). But once we're over the dirty memory * limit we decrease the ratelimiting by a lot, to prevent individual processes * from overshooting the limit by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) balance_dirty_pages(wb, current->nr_dirtied); wb_put(wb); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; /* * Similar to balance_dirty_pages() but ignores pages being written * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; if (wb_stat(wb, WB_RECLAIMABLE) > wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { unsigned long filepages, headroom, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) return true; if (wb_stat(wb, WB_RECLAIMABLE) > wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } return false; } /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #ifdef CONFIG_BLOCK void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } #endif /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * If it is too low then SMP machines will call the (expensive) * get_writeback_state too often. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); } /** * tag_pages_for_writeback - tag pages to be written by write_cache_pages * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is * that write_cache_pages (or whoever calls this function) will then use * TOWRITE tag to identify pages eligible for writeback. This mechanism is * used to avoid livelocking of writeback by a process steadily creating new * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. * * To avoid livelocks (when other process dirties new pages), we first tag * pages which should be written back with TOWRITE tag and only then start * writing them. For data-integrity sync we have to be careful so that we do * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). * * To avoid deadlocks between range_cyclic writeback and callers that hold * pages in PageWriteback to aggregate IO until write_cache_pages() returns, * we do not loop back to the start of the file. Doing so causes a page * lock/page writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping back to the start * of the file violates that rule and causes deadlocks. * * Return: %0 on success, negative error code otherwise */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { int ret = 0; int done = 0; int error; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int range_whole = 0; xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { index = mapping->writeback_index; /* prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { tag_pages_for_writeback(mapping, index, end); tag = PAGECACHE_TAG_TOWRITE; } else { tag = PAGECACHE_TAG_DIRTY; } done_index = index; while (!done && (index <= end)) { int i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, tag); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; done_index = page->index; lock_page(page); /* * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no * real expectation of this data interity operation * even if there is now a new, dirty page at the same * pagecache address. */ if (unlikely(page->mapping != mapping)) { continue_unlock: unlock_page(page); continue; } if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) wait_on_page_writeback(page); else goto continue_unlock; } BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); error = (*writepage)(page, wbc, data); if (unlikely(error)) { /* * Handle errors according to the type of * writeback. There's no need to continue for * background writeback. Just push done_index * past this page so media errors won't choke * writeout for the entire file. For integrity * writeback, we must process the entire dirty * set regardless of errors because the fs may * still have state to clear for each page. In * that case we continue processing and return * the first error. */ if (error == AOP_WRITEPAGE_ACTIVATE) { unlock_page(page); error = 0; } else if (wbc->sync_mode != WB_SYNC_ALL) { ret = error; done_index = page->index + 1; done = 1; break; } if (!ret) ret = error; } /* * We stop writing back only if we are not doing * integrity sync. In case of integrity sync we have to * keep going until we have written all the pages * we tagged for writeback prior to entering this loop. */ if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } } pagevec_release(&pvec); cond_resched(); } /* * If we hit the last page and there is more work to be done: wrap * back the index back to the start of the file for the next * time we are called. */ if (wbc->range_cyclic && !done) done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; } EXPORT_SYMBOL(write_cache_pages); /* * Function used by generic_writepages to call the real writepage * function and set the mapping flags on error */ static int __writepage(struct page *page, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(page, wbc); mapping_set_error(mapping, ret); return ret; } /** * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * * This is a library function, which implements the writepages() * address_space_operation. * * Return: %0 on success, negative error code otherwise */ int generic_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct blk_plug plug; int ret; /* deal with chardevs and other special file */ if (!mapping->a_ops->writepage) return 0; blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, __writepage, mapping); blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(generic_writepages); int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (wbc->nr_to_write <= 0) return 0; while (1) { if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); else ret = generic_writepages(mapping, wbc); if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) break; cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); } return ret; } /** * write_one_page - write out a single page and wait on I/O * @page: the page to write * * The page must be locked by the caller and will be unlocked upon return. * * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this * function returns. * * Return: %0 on success, negative error code otherwise */ int write_one_page(struct page *page) { struct address_space *mapping = page->mapping; int ret = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 1, }; BUG_ON(!PageLocked(page)); wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { get_page(page); ret = mapping->a_ops->writepage(page, &wbc); if (ret == 0) wait_on_page_writeback(page); put_page(page); } else { unlock_page(page); } if (!ret) ret = filemap_check_errors(mapping); return ret; } EXPORT_SYMBOL(write_one_page); /* * For address_spaces which do not use buffers nor write back. */ int __set_page_dirty_no_writeback(struct page *page) { if (!PageDirty(page)) return !TestSetPageDirty(page); return 0; } /* * Helper function for set_page_dirty family. * * Caller must hold lock_page_memcg(). * * NOTE: This relies on being atomic wrt interrupts. */ void account_page_dirtied(struct page *page, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_page(page, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; inode_attach_wb(inode, page); wb = inode_to_wb(inode); __inc_lruvec_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); __inc_node_page_state(page, NR_DIRTIED); inc_wb_stat(wb, WB_RECLAIMABLE); inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); mem_cgroup_track_foreign_dirty(page, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold lock_page_memcg(). */ void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb) { if (mapping_can_writeback(mapping)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); task_io_account_cancelled_write(PAGE_SIZE); } } /* * For address_spaces which do not use buffers. Just tag the page as dirty in * the xarray. * * This is also used when a single buffer is being dirtied: we want to set the * page dirty in that case, but not all the buffers. This is a "bottom-up" * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will simply * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and * the pte lock held, which also locks out truncation. */ int __set_page_dirty_nobuffers(struct page *page) { lock_page_memcg(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); unsigned long flags; if (!mapping) { unlock_page_memcg(page); return 1; } xa_lock_irqsave(&mapping->i_pages, flags); BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } unlock_page_memcg(page); return 0; } EXPORT_SYMBOL(__set_page_dirty_nobuffers); /* * Call this whenever redirtying a page, to de-account the dirty counters * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to * systematic errors in balanced_dirty_ratelimit and the dirty pages position * control. */ void account_page_redirty(struct page *page) { struct address_space *mapping = page->mapping; if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); /* * When a writepage implementation decides that it doesn't want to write this * page for some reason, it should redirty the locked page via * redirty_page_for_writepage() and it should then unlock the page and return 0 */ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { int ret; wbc->pages_skipped++; ret = __set_page_dirty_nobuffers(page); account_page_redirty(page); return ret; } EXPORT_SYMBOL(redirty_page_for_writepage); /* * Dirty a page. * * For pages with a mapping this should be done under the page lock * for the benefit of asynchronous memory errors who prefer a consistent * dirty state. This rule can be broken in some special cases, * but should be better not to. * * If the mapping doesn't provide a set_page_dirty a_op, then * just fall through and assume that it wants buffer_heads. */ int set_page_dirty(struct page *page) { struct address_space *mapping = page_mapping(page); page = compound_head(page); if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; /* * readahead/lru_deactivate_page could remain * PG_readahead/PG_reclaim due to race with end_page_writeback * About readahead, if the page is written, the flags would be * reset. So no problem. * About lru_deactivate_page, if the page is redirty, the flag * will be reset. So no problem. but if the page is used by readahead * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ if (PageReclaim(page)) ClearPageReclaim(page); #ifdef CONFIG_BLOCK if (!spd) spd = __set_page_dirty_buffers; #endif return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) return 1; } return 0; } EXPORT_SYMBOL(set_page_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __cancel_dirty_page(struct page *page) { struct address_space *mapping = page_mapping(page); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; lock_page_memcg(page); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); } } EXPORT_SYMBOL(__cancel_dirty_page); /* * Clear a page's dirty flag, while caring for dirty memory accounting. * Returns true if the page was previously dirty. * * This is for preparing to put the page under writeout. We leave the page * tagged as dirty in the xarray so that a concurrent write-for-sync * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage * implementation will run either set_page_writeback() or set_page_dirty(), * at which stage we bring the page's dirty flag and xarray dirty tag * back into sync. * * This incoherency between the page's dirty flag and xarray tag is * unfortunate, but it only exists while the page is locked. */ int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); int ret = 0; VM_BUG_ON_PAGE(!PageLocked(page), page); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole page dirty if it was * dirty in a pagetable. Only to then * (c) clean the page again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "set_page_dirty(page)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the page "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (page_mkclean(page)) set_page_dirty(page); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the page dirty * at this point. We do this by having them hold the * page lock while dirtying the page, and pages are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page); } EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); struct mem_cgroup *memcg; struct lruvec *lruvec; int ret; memcg = lock_page_memcg(page); lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = TestClearPageWriteback(page); if (ret) { __xa_clear_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); dec_wb_stat(wb, WB_WRITEBACK); __wb_writeout_inc(wb); } } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = TestClearPageWriteback(page); } if (ret) { dec_lruvec_state(lruvec, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); inc_node_page_state(page, NR_WRITTEN); } __unlock_page_memcg(memcg); return ret; } int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret, access_ret; lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, page_index(page)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); ret = TestSetPageWriteback(page); if (!ret) { bool on_wblist; on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); /* * We can come through here when swapping anonymous * pages, so we don't necessarily have an inode to track * for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { ret = TestSetPageWriteback(page); } if (!ret) { inc_lruvec_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); } unlock_page_memcg(page); access_ret = arch_make_page_accessible(page); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_PAGE(access_ret != 0, page); return ret; } EXPORT_SYMBOL(__test_set_page_writeback); /* * Wait for a page to complete writeback */ void wait_on_page_writeback(struct page *page) { while (PageWriteback(page)) { trace_wait_on_page_writeback(page, page_mapping(page)); wait_on_page_bit(page, PG_writeback); } } EXPORT_SYMBOL_GPL(wait_on_page_writeback); /** * wait_for_stable_page() - wait for writeback to finish, if necessary. * @page: The page to wait on. * * This function determines if the given page is related to a backing device * that requires page contents to be held stable during writeback. If so, then * it will wait for any pending writeback to complete. */ void wait_for_stable_page(struct page *page) { page = thp_head(page); if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) wait_on_page_writeback(page); } EXPORT_SYMBOL_GPL(wait_for_stable_page); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM block #if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BLOCK_H #include <linux/blktrace_api.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/tracepoint.h> #define RWBS_LEN 8 DECLARE_EVENT_CLASS(block_buffer, TP_PROTO(struct buffer_head *bh), TP_ARGS(bh), TP_STRUCT__entry ( __field( dev_t, dev ) __field( sector_t, sector ) __field( size_t, size ) ), TP_fast_assign( __entry->dev = bh->b_bdev->bd_dev; __entry->sector = bh->b_blocknr; __entry->size = bh->b_size; ), TP_printk("%d,%d sector=%llu size=%zu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->sector, __entry->size ) ); /** * block_touch_buffer - mark a buffer accessed * @bh: buffer_head being touched * * Called from touch_buffer(). */ DEFINE_EVENT(block_buffer, block_touch_buffer, TP_PROTO(struct buffer_head *bh), TP_ARGS(bh) ); /** * block_dirty_buffer - mark a buffer dirty * @bh: buffer_head being dirtied * * Called from mark_buffer_dirty(). */ DEFINE_EVENT(block_buffer, block_dirty_buffer, TP_PROTO(struct buffer_head *bh), TP_ARGS(bh) ); /** * block_rq_requeue - place block IO request back on a queue * @rq: block IO operation request * * The block operation request @rq is being placed back into queue * @q. For some reason the request was not completed and needs to be * put back in the queue. */ TRACE_EVENT(block_rq_requeue, TP_PROTO(struct request *rq), TP_ARGS(rq), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __array( char, rwbs, RWBS_LEN ) __dynamic_array( char, cmd, 1 ) ), TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); __get_str(cmd)[0] = '\0'; ), TP_printk("%d,%d %s (%s) %llu + %u [%d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, __get_str(cmd), (unsigned long long)__entry->sector, __entry->nr_sector, 0) ); /** * block_rq_complete - block IO operation completed by device driver * @rq: block operations request * @error: status code * @nr_bytes: number of completed bytes * * The block_rq_complete tracepoint event indicates that some portion * of operation request has been completed by the device driver. If * the @rq->bio is %NULL, then there is absolutely no additional work to * do for the request. If @rq->bio is non-NULL then there is * additional work required to complete the request. */ TRACE_EVENT(block_rq_complete, TP_PROTO(struct request *rq, int error, unsigned int nr_bytes), TP_ARGS(rq, error, nr_bytes), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( int, error ) __array( char, rwbs, RWBS_LEN ) __dynamic_array( char, cmd, 1 ) ), TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; __entry->sector = blk_rq_pos(rq); __entry->nr_sector = nr_bytes >> 9; __entry->error = error; blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes); __get_str(cmd)[0] = '\0'; ), TP_printk("%d,%d %s (%s) %llu + %u [%d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, __get_str(cmd), (unsigned long long)__entry->sector, __entry->nr_sector, __entry->error) ); DECLARE_EVENT_CLASS(block_rq, TP_PROTO(struct request *rq), TP_ARGS(rq), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( unsigned int, bytes ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) __dynamic_array( char, cmd, 1 ) ), TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); __entry->bytes = blk_rq_bytes(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); __get_str(cmd)[0] = '\0'; memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("%d,%d %s %u (%s) %llu + %u [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, __entry->bytes, __get_str(cmd), (unsigned long long)__entry->sector, __entry->nr_sector, __entry->comm) ); /** * block_rq_insert - insert block operation request into queue * @rq: block IO operation request * * Called immediately before block operation request @rq is inserted * into queue @q. The fields in the operation request @rq struct can * be examined to determine which device and sectors the pending * operation would access. */ DEFINE_EVENT(block_rq, block_rq_insert, TP_PROTO(struct request *rq), TP_ARGS(rq) ); /** * block_rq_issue - issue pending block IO request operation to device driver * @rq: block IO operation operation request * * Called when block operation request @rq from queue @q is sent to a * device driver for processing. */ DEFINE_EVENT(block_rq, block_rq_issue, TP_PROTO(struct request *rq), TP_ARGS(rq) ); /** * block_rq_merge - merge request with another one in the elevator * @rq: block IO operation operation request * * Called when block operation request @rq from queue @q is merged to another * request queued in the elevator. */ DEFINE_EVENT(block_rq, block_rq_merge, TP_PROTO(struct request *rq), TP_ARGS(rq) ); /** * block_bio_bounce - used bounce buffer when processing block operation * @q: queue holding the block operation * @bio: block operation * * A bounce buffer was used to handle the block operation @bio in @q. * This occurs when hardware limitations prevent a direct transfer of * data between the @bio data memory area and the IO device. Use of a * bounce buffer requires extra copying of data and decreases * performance. */ TRACE_EVENT(block_bio_bounce, TP_PROTO(struct request_queue *q, struct bio *bio), TP_ARGS(q, bio), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("%d,%d %s %llu + %u [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->comm) ); /** * block_bio_complete - completed all work on the block operation * @q: queue holding the block operation * @bio: block operation completed * * This tracepoint indicates there is no further work to do on this * block IO operation @bio. */ TRACE_EVENT(block_bio_complete, TP_PROTO(struct request_queue *q, struct bio *bio), TP_ARGS(q, bio), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned, nr_sector ) __field( int, error ) __array( char, rwbs, RWBS_LEN) ), TP_fast_assign( __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->error = blk_status_to_errno(bio->bi_status); blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u [%d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->error) ); DECLARE_EVENT_CLASS(block_bio_merge, TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), TP_ARGS(q, rq, bio), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("%d,%d %s %llu + %u [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->comm) ); /** * block_bio_backmerge - merging block operation to the end of an existing operation * @q: queue holding operation * @rq: request bio is being merged into * @bio: new block operation to merge * * Merging block request @bio to the end of an existing block request * in queue @q. */ DEFINE_EVENT(block_bio_merge, block_bio_backmerge, TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), TP_ARGS(q, rq, bio) ); /** * block_bio_frontmerge - merging block operation to the beginning of an existing operation * @q: queue holding operation * @rq: request bio is being merged into * @bio: new block operation to merge * * Merging block IO operation @bio to the beginning of an existing block * operation in queue @q. */ DEFINE_EVENT(block_bio_merge, block_bio_frontmerge, TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), TP_ARGS(q, rq, bio) ); /** * block_bio_queue - putting new block IO operation in queue * @q: queue holding operation * @bio: new block operation * * About to place the block IO operation @bio into queue @q. */ TRACE_EVENT(block_bio_queue, TP_PROTO(struct request_queue *q, struct bio *bio), TP_ARGS(q, bio), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("%d,%d %s %llu + %u [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->comm) ); DECLARE_EVENT_CLASS(block_get_rq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), TP_ARGS(q, bio, rw), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( __entry->dev = bio ? bio_dev(bio) : 0; __entry->sector = bio ? bio->bi_iter.bi_sector : 0; __entry->nr_sector = bio ? bio_sectors(bio) : 0; blk_fill_rwbs(__entry->rwbs, bio ? bio->bi_opf : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("%d,%d %s %llu + %u [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, __entry->comm) ); /** * block_getrq - get a free request entry in queue for block IO operations * @q: queue for operations * @bio: pending block IO operation (can be %NULL) * @rw: low bit indicates a read (%0) or a write (%1) * * A request struct for queue @q has been allocated to handle the * block IO operation @bio. */ DEFINE_EVENT(block_get_rq, block_getrq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), TP_ARGS(q, bio, rw) ); /** * block_sleeprq - waiting to get a free request entry in queue for block IO operation * @q: queue for operation * @bio: pending block IO operation (can be %NULL) * @rw: low bit indicates a read (%0) or a write (%1) * * In the case where a request struct cannot be provided for queue @q * the process needs to wait for an request struct to become * available. This tracepoint event is generated each time the * process goes to sleep waiting for request struct become available. */ DEFINE_EVENT(block_get_rq, block_sleeprq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), TP_ARGS(q, bio, rw) ); /** * block_plug - keep operations requests in request queue * @q: request queue to plug * * Plug the request queue @q. Do not allow block operation requests * to be sent to the device driver. Instead, accumulate requests in * the queue to improve throughput performance of the block device. */ TRACE_EVENT(block_plug, TP_PROTO(struct request_queue *q), TP_ARGS(q), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("[%s]", __entry->comm) ); DECLARE_EVENT_CLASS(block_unplug, TP_PROTO(struct request_queue *q, unsigned int depth, bool explicit), TP_ARGS(q, depth, explicit), TP_STRUCT__entry( __field( int, nr_rq ) __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( __entry->nr_rq = depth; memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("[%s] %d", __entry->comm, __entry->nr_rq) ); /** * block_unplug - release of operations requests in request queue * @q: request queue to unplug * @depth: number of requests just added to the queue * @explicit: whether this was an explicit unplug, or one from schedule() * * Unplug request queue @q because device driver is scheduled to work * on elements in the request queue. */ DEFINE_EVENT(block_unplug, block_unplug, TP_PROTO(struct request_queue *q, unsigned int depth, bool explicit), TP_ARGS(q, depth, explicit) ); /** * block_split - split a single bio struct into two bio structs * @q: queue containing the bio * @bio: block operation being split * @new_sector: The starting sector for the new bio * * The bio request @bio in request queue @q needs to be split into two * bio requests. The newly created @bio request starts at * @new_sector. This split may be required due to hardware limitation * such as operation crossing device boundaries in a RAID system. */ TRACE_EVENT(block_split, TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int new_sector), TP_ARGS(q, bio, new_sector), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( sector_t, new_sector ) __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), TP_fast_assign( __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->new_sector = new_sector; blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), TP_printk("%d,%d %s %llu / %llu [%s]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, (unsigned long long)__entry->new_sector, __entry->comm) ); /** * block_bio_remap - map request for a logical device to the raw device * @q: queue holding the operation * @bio: revised operation * @dev: device for the operation * @from: original sector for the operation * * An operation for a logical device has been mapped to the * raw block device. */ TRACE_EVENT(block_bio_remap, TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev, sector_t from), TP_ARGS(q, bio, dev, from), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( dev_t, old_dev ) __field( sector_t, old_sector ) __array( char, rwbs, RWBS_LEN) ), TP_fast_assign( __entry->dev = bio_dev(bio); __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, MAJOR(__entry->old_dev), MINOR(__entry->old_dev), (unsigned long long)__entry->old_sector) ); /** * block_rq_remap - map request for a block operation request * @rq: block IO operation request * @dev: device for the operation * @from: original sector for the operation * * The block operation request @rq in @q has been remapped. The block * operation request @rq holds the current information and @from hold * the original sector. */ TRACE_EVENT(block_rq_remap, TP_PROTO(struct request *rq, dev_t dev, sector_t from), TP_ARGS(rq, dev, from), TP_STRUCT__entry( __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( dev_t, old_dev ) __field( sector_t, old_sector ) __field( unsigned int, nr_bios ) __array( char, rwbs, RWBS_LEN) ), TP_fast_assign( __entry->dev = disk_devt(rq->rq_disk); __entry->sector = blk_rq_pos(rq); __entry->nr_sector = blk_rq_sectors(rq); __entry->old_dev = dev; __entry->old_sector = from; __entry->nr_bios = blk_rq_count_bios(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, MAJOR(__entry->old_dev), MINOR(__entry->old_dev), (unsigned long long)__entry->old_sector, __entry->nr_bios) ); #endif /* _TRACE_BLOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ #include <linux/efi.h> /* efi_recover_from_page_fault()*/ #include <linux/mm_types.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> /* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) return -1; return 0; } /* * Prefetch quirks: * * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * * Sometimes the CPU reports invalid exceptions on prefetch. * Check that here and ignore it. * * Opcode checker based on code by Richard Brunner. */ static inline int check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, unsigned char opcode, int *prefetch) { unsigned char instr_hi = opcode & 0xf0; unsigned char instr_lo = opcode & 0x0f; switch (instr_hi) { case 0x20: case 0x30: /* * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. * In X86_64 long mode, the CPU will signal invalid * opcode if some of these prefixes are present so * X86_64 will never get here anyway */ return ((instr_lo & 7) == 0x6); #ifdef CONFIG_X86_64 case 0x40: /* * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif case 0x60: /* 0x64 thru 0x67 are valid prefixes in all modes. */ return (instr_lo & 0xC) == 0x4; case 0xF0: /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */ return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && (opcode == 0x0D || opcode == 0x18); return 0; default: return 0; } } static int is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) { unsigned char *max_instr; unsigned char *instr; int prefetch = 0; /* * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; /* * This code has historically always bailed out if IP points to a * not-present page (e.g. due to a race). No one has ever * complained about this. */ pagefault_disable(); while (instr < max_instr) { unsigned char opcode; if (user_mode(regs)) { if (get_user(opcode, instr)) break; } else { if (get_kernel_nofault(opcode, instr)) break; } instr++; if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } pagefault_enable(); return prefetch; } DEFINE_SPINLOCK(pgd_lock); LIST_HEAD(pgd_list); #ifdef CONFIG_X86_32 static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; pgd += index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) return NULL; /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would * set_p4d/set_pud. */ p4d = p4d_offset(pgd, address); p4d_k = p4d_offset(pgd_k, address); if (!p4d_present(*p4d_k)) return NULL; pud = pud_offset(p4d, address); pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); if (!pmd_present(*pmd_k)) return NULL; else BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } /* * Handle a fault on the vmalloc or module mapping area * * This is needed because there is a race condition between the time * when the vmalloc mapping code updates the PMD to the point in time * where it synchronizes this update with the other page-tables in the * system. * * In this race window another thread/CPU can map an area on the same * PMD, finds it already present and does not synchronize it with the * rest of the system yet. As a result v[mz]alloc might return areas * which are not mapped in every page-table in the system, causing an * unhandled page-fault when they are accessed. */ static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; /* Make sure we are in vmalloc area: */ if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; /* * Synchronize this task's top level page-table * with the 'reference' page table. * * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; if (pmd_large(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; return 0; } NOKPROBE_SYMBOL(vmalloc_fault); void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start & PMD_MASK; addr >= TASK_SIZE_MAX && addr < VMALLOC_END; addr += PMD_SIZE) { struct page *page; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); vmalloc_sync_one(page_address(page), addr); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } /* * Did it hit the DOS screen memory VA from vm86 mode? */ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { #ifdef CONFIG_VM86 unsigned long bit; if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) tsk->thread.vm86->screen_bitmap |= 1 << bit; #endif } static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; #ifdef CONFIG_X86_PAE pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #define pr_pde pr_cont #else #define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); #undef pr_pde /* * We must not directly access the pte in the highpte * case if the page table is located in highmem. * And let's rather not kmap-atomic the pte, just in case * it's allocated already: */ if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: pr_cont("\n"); } #else /* CONFIG_X86_64: */ #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" "******* Working around it, but it may cause SEGVs or burn power.\n" "******* Please consider a BIOS update.\n" "******* Disabling USB legacy in the BIOS may also help.\n"; #endif /* * No vm86 mode in 64-bit mode: */ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { } static int bad_address(void *p) { unsigned long dummy; return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; if (bad_address(pgd)) goto bad; pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (bad_address(p4d)) goto bad; pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_large(*p4d)) goto out; pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_large(*pud)) goto out; pmd = pmd_offset(pud, address); if (bad_address(pmd)) goto bad; pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_large(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); if (bad_address(pte)) goto bad; pr_cont("PTE %lx", pte_val(*pte)); out: pr_cont("\n"); return; bad: pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ /* * Workaround for K8 erratum #93 & buggy BIOS. * * BIOS SMM functions are required to use a specific workaround * to avoid corruption of the 64bit RIP register on C stepping K8. * * A lot of BIOS that didn't get tested properly miss this. * * The OS sees this as a page fault with the upper 32bits of RIP cleared. * Try to work around it here. * * Note we only handle faults in kernel here. * Does nothing on 32-bit. */ static int is_errata93(struct pt_regs *regs, unsigned long address) { #if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD || boot_cpu_data.x86 != 0xf) return 0; if (user_mode(regs)) return 0; if (address != regs->ip) return 0; if ((address >> 32) != 0) return 0; address |= 0xffffffffUL << 32; if ((address >= (u64)_stext && address <= (u64)_etext) || (address >= MODULES_VADDR && address <= MODULES_END)) { printk_once(errata93_warning); regs->ip = address; return 1; } #endif return 0; } /* * Work around K8 erratum #100 K8 in compat mode occasionally jumps * to illegal addresses >4GB. * * We catch this in the page fault handler because these addresses * are not reachable. Just detect this case and return. Any code * segment in LDT is compatibility mode. */ static int is_errata100(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_64 if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32)) return 1; #endif return 0; } /* Pentium F0 0F C7 C8 bug workaround: */ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_F00F_BUG if (boot_cpu_has_bug(X86_BUG_F00F) && idt_is_f00f_address(address)) { handle_invalid_op(regs); return 1; } #endif return 0; } static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) { u32 offset = (index >> 3) * sizeof(struct desc_struct); unsigned long addr; struct ldttss_desc desc; if (index == 0) { pr_alert("%s: NULL\n", name); return; } if (offset + sizeof(struct ldttss_desc) >= gdt->size) { pr_alert("%s: 0x%hx -- out of bounds\n", name, index); return; } if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); return; } addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n", name, index, addr, (desc.limit0 | (desc.limit1 << 16))); } static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!oops_may_print()) return; if (error_code & X86_PF_INSTR) { unsigned int level; pgd_t *pgd; pte_t *pte; pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); if (pte && pte_present(*pte) && pte_exec(*pte) && (pgd_flags(*pgd) & _PAGE_USER) && (__read_cr4() & X86_CR4_SMEP)) pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); } if (address < PAGE_SIZE && !user_mode(regs)) pr_alert("BUG: kernel NULL pointer dereference, address: %px\n", (void *)address); else pr_alert("BUG: unable to handle page fault for address: %px\n", (void *)address); pr_alert("#PF: %s %s in %s mode\n", (error_code & X86_PF_USER) ? "user" : "supervisor", (error_code & X86_PF_INSTR) ? "instruction fetch" : (error_code & X86_PF_WRITE) ? "write access" : "read access", user_mode(regs) ? "user" : "kernel"); pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code, !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { struct desc_ptr idt, gdt; u16 ldtr, tr; /* * This can happen for quite a few reasons. The more obvious * ones are faults accessing the GDT, or LDT. Perhaps * surprisingly, if the CPU tries to deliver a benign or * contributory exception from user code and gets a page fault * during delivery, the page fault can be delivered as though * it originated directly from user code. This could happen * due to wrong permissions on the IDT, GDT, LDT, TSS, or * kernel or IST stack. */ store_idt(&idt); /* Usable even on Xen PV -- it's just slow. */ native_store_gdt(&gdt); pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n", idt.address, idt.size, gdt.address, gdt.size); store_ldt(ldtr); show_ldttss(&gdt, "LDTR", ldtr); store_tr(tr); show_ldttss(&gdt, "TR", tr); } dump_pagetable(address); } static noinline void pgtable_bad(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct task_struct *tsk; unsigned long flags; int sig; flags = oops_begin(); tsk = current; sig = SIGKILL; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", tsk->comm, address); dump_pagetable(address); if (__die("Bad pagetable", regs, error_code)) sig = 0; oops_end(flags, regs, sig); } static void set_signal_archinfo(unsigned long address, unsigned long error_code) { struct task_struct *tsk = current; /* * To avoid leaking information about the kernel page * table layout, pretend that user-mode accesses to * kernel addresses are always protection faults. * * NB: This means that failed vsyscalls with vsyscall=none * will have the PROT bit. This doesn't leak any * information and does not appear to cause any problems. */ if (address >= TASK_SIZE_MAX) error_code |= X86_PF_PROT; tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; } static noinline void no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; unsigned long flags; int sig; if (user_mode(regs)) { /* * This is an implicit supervisor-mode access from user * mode. Bypass all the kernel-mode recovery code and just * OOPS. */ goto oops; } /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; #ifdef CONFIG_VMAP_STACK /* * Stack overflow? During boot, we can fault near the initial * stack in the direct map, but that's not an overflow -- check * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *); /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but * double-fault even before we get this far, in which case * we're fine: the double-fault handler will deal with it. * * We don't want to make it all the way into the oops code * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ asm volatile ("movq %[stack], %%rsp\n\t" "call handle_stack_overflow\n\t" "1: jmp 1b" : ASM_CALL_CONSTRAINT : "D" ("kernel stack overflow (page fault)"), "S" (regs), "d" (address), [stack] "rm" (stack)); unreachable(); } #endif /* * 32-bit: * * Valid to do another page fault here, because if this fault * had been triggered by is_prefetch fixup_exception would have * handled it. * * 64-bit: * * Hall of shame of CPU/BIOS bugs. */ if (is_prefetch(regs, error_code, address)) return; /* * Buggy firmware could access regions which might page fault, try to * recover from such faults. */ if (IS_ENABLED(CONFIG_EFI)) efi_recover_from_page_fault(address); oops: /* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice: */ flags = oops_begin(); show_fault_oops(regs, error_code, address); if (task_stack_end_corrupted(tsk)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); sig = SIGKILL; if (__die("Oops", regs, error_code)) sig = 0; /* Executive summary in case the body of the oops scrolled away */ printk(KERN_DEFAULT "CR2: %016lx\n", address); oops_end(flags, regs, sig); } /* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: */ static inline void show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; if (!unhandled_signal(tsk, SIGSEGV)) return; if (!printk_ratelimit()) return; printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", loglvl, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); print_vma_addr(KERN_CONT " in ", regs->ip); printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); } static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct task_struct *tsk = current; /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs) && (error_code & X86_PF_USER)) { /* * It's possible to have interrupts off here: */ local_irq_enable(); /* * Valid to do another page fault here because this one came * from user space: */ if (is_prefetch(regs, error_code, address)) return; if (is_errata100(regs, address)) return; /* * To avoid leaking information about the kernel page table * layout, pretend that user-mode accesses to kernel addresses * are always protection faults. */ if (address >= TASK_SIZE_MAX) error_code |= X86_PF_PROT; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); set_signal_archinfo(address, error_code); if (si_code == SEGV_PKUERR) force_sig_pkuerr((void __user *)address, pkey); force_sig_fault(SIGSEGV, si_code, (void __user *)address); local_irq_disable(); return; } if (is_f00f_bug(regs, address)) return; no_context(regs, error_code, address, SIGSEGV, si_code); } static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR); } static void __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ mmap_read_unlock(mm); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } static noinline void bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area(regs, error_code, address, 0, SEGV_MAPERR); } static inline bool bad_area_access_from_pkeys(unsigned long error_code, struct vm_area_struct *vma) { /* This code is always called on the current mm */ bool foreign = false; if (!boot_cpu_has(X86_FEATURE_OSPKE)) return false; if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return true; return false; } static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. * But, doing it this way allows compiler optimizations * if pkeys are compiled out. */ if (bad_area_access_from_pkeys(error_code, vma)) { /* * A protection key fault means that the PKRU value did not allow * access to some PTE. Userspace can figure out what PKRU was * from the XSAVE state. This function captures the pkey from * the vma and passes it to userspace so userspace can discover * which protection key was set on the PTE. * * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set PKRU to deny access to pkey=4, touches page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ u32 pkey = vma_pkey(vma); __bad_area(regs, error_code, address, pkey, SEGV_PKUERR); } else { __bad_area(regs, error_code, address, 0, SEGV_ACCERR); } } static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } /* User-space => ok to do another page fault: */ if (is_prefetch(regs, error_code, address)) return; set_signal_archinfo(address, error_code); #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { struct task_struct *tsk = current; unsigned lsb = 0; pr_err( "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n", tsk->comm, tsk->pid, address); if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); if (fault & VM_FAULT_HWPOISON) lsb = PAGE_SHIFT; force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb); return; } #endif force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; return 1; } /* * Handle a spurious fault caused by a stale TLB entry. * * This allows us to lazily refresh the TLB when increasing the * permissions of a kernel page (RO -> RW or NX -> X). Doing it * eagerly is very expensive since that implies doing a full * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * * Spurious faults may only occur if the TLB contains an entry with * fewer permission than the page table entry. Non-present (P = 0) * and reserved bit (R = 1) faults are never spurious. * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. * * Returns non-zero if a spurious fault was handled, zero otherwise. * * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 * (Optional Invalidation). */ static noinline int spurious_kernel_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; int ret; /* * Only writes to RO or instruction fetches from NX may cause * spurious faults. * * These could be from user or supervisor accesses but the TLB * is only lazily flushed after a kernel mapping protection * change, so user accesses are not expected to cause spurious * faults. */ if (error_code != (X86_PF_WRITE | X86_PF_PROT) && error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); if (!pgd_present(*pgd)) return 0; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) return 0; if (p4d_large(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_large(*pmd)) return spurious_kernel_fault_check(error_code, (pte_t *) pmd); pte = pte_offset_kernel(pmd, address); if (!pte_present(*pte)) return 0; ret = spurious_kernel_fault_check(error_code, pte); if (!ret) return 0; /* * Make sure we have permissions in PMD. * If not, then there's a bug in the page tables: */ ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd); WARN_ONCE(!ret, "PMD has incorrect permission bits\n"); return ret; } NOKPROBE_SYMBOL(spurious_kernel_fault); int show_unhandled_signals = 1; static inline int access_error(unsigned long error_code, struct vm_area_struct *vma) { /* This is only called for the current mm, so: */ bool foreign = false; /* * Read or write was blocked by protection keys. This is * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ if (error_code & X86_PF_PK) return 1; /* * Make sure to check the VMA so that we do not perform * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return 1; if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } /* read, present: */ if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ if (unlikely(!vma_is_accessible(vma))) return 1; return 0; } bool fault_in_kernel_space(unsigned long address) { /* * On 64-bit systems, the vsyscall page is at an address above * TASK_SIZE_MAX, but is not considered part of the kernel * address space. */ if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address)) return false; return address >= TASK_SIZE_MAX; } /* * Called for all faults where 'address' is part of the kernel address * space. Might get called for faults that originate from *code* that * ran in userspace or the kernel. */ static void do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { /* * Protection keys exceptions only happen on user pages. We * have no user pages in the kernel portion of the address * space, so do not expect them here. */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); #ifdef CONFIG_X86_32 /* * We can fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. * * NOTE! We MUST NOT take any locks for this case. We may * be in an interrupt or a critical region, and should * only copy the information from the master page table, * nothing more. * * Before doing this on-demand faulting, ensure that the * fault is not any of the following: * 1. A fault on a PTE with a reserved bit set. * 2. A fault caused by a user-mode access. (Do not demand- * fault kernel memory due to user-mode accesses). * 3. A fault caused by a page-level protection violation. * (A demand fault would be on a non-present page which * would have X86_PF_PROT==0). * * This is only needed to close a race condition on x86-32 in * the vmalloc mapping/unmapping code. See the comment above * vmalloc_fault() for details. On x86-64 the race does not * exist as the vmalloc mappings don't need to be synchronized * there. */ if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; } #endif /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; /* kprobes don't want to hook the spurious faults: */ if (kprobe_page_fault(regs, X86_TRAP_PF)) return; /* * Note, despite being a "bad area", there are quite a few * acceptable reasons to get here, such as erratum fixups * and handling kernel code that can fault, like get_user(). * * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock: */ bad_area_nosemaphore(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_kern_addr_fault); /* Handle faults in the user portion of the address space */ static inline void do_user_addr_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; if (unlikely((error_code & (X86_PF_USER | X86_PF_INSTR)) == X86_PF_INSTR)) { /* * Whoops, this is kernel mode code trying to execute from * user memory. Unless this is AMD erratum #93, which * corrupts RIP such that it looks like a user address, * this is unrecoverable. Don't even try to look up the * VMA. */ if (is_errata93(regs, address)) return; bad_area_nosemaphore(regs, error_code, address); return; } /* kprobes don't want to hook the spurious faults: */ if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Reserved bits are never expected to be set on * entries in the user portion of the page tables. */ if (unlikely(error_code & X86_PF_RSVD)) pgtable_bad(regs, error_code, address); /* * If SMAP is on, check for invalid kernel (supervisor) access to user * pages in the user address space. The odd case here is WRUSS, * which, according to the preliminary documentation, does not respect * SMAP and will have the USER bit set so, in all cases, SMAP * enforcement appears to be consistent with the USER bit. */ if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) && !(error_code & X86_PF_USER) && !(regs->flags & X86_EFLAGS_AC))) { bad_area_nosemaphore(regs, error_code, address); return; } /* * If we're in an interrupt, have no user context or are running * in a region with pagefaults disabled then we must not take the fault */ if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. * * User-mode registers count as a user access even for any * potential system fault or CPU buglet: */ if (user_mode(regs)) { local_irq_enable(); flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The * vsyscall page is at a high address (>PAGE_OFFSET), but is * considered to be part of the user address space. * * The vsyscall page does not have a "real" VMA, so do this * emulation before we go searching for VMAs. * * PKRU never rejects instruction fetches, so we don't need * to consider the PF_PK bit. */ if (is_vsyscall_vaddr(address)) { if (emulate_vsyscall(error_code, regs, address)) return; } #endif /* * Kernel-mode access to the user address space should only occur * on well-defined single instructions listed in the exception * tables. But, an erroneous kernel fault occurring outside one of * those areas which also holds mmap_lock might deadlock attempting * to validate the fault against the address space. * * Only do the expensive exception table search when we might be at * risk of a deadlock. This happens if we * 1. Failed to acquire mmap_lock, and * 2. The access did not originate in userspace. */ if (unlikely(!mmap_read_trylock(mm))) { if (!user_mode(regs) && !search_exception_tables(regs->ip)) { /* * Fault from code in kernel from * which we do not expect faults. */ bad_area_nosemaphore(regs, error_code, address); return; } retry: mmap_read_lock(mm); } else { /* * The above down_read_trylock() might have succeeded in * which case we'll have missed the might_sleep() from * down_read(): */ might_sleep(); } vma = find_vma(mm, address); if (unlikely(!vma)) { bad_area(regs, error_code, address); return; } if (likely(vma->vm_start <= address)) goto good_area; if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { bad_area(regs, error_code, address); return; } if (unlikely(expand_stack(vma, address))) { bad_area(regs, error_code, address); return; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ good_area: if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address, vma); return; } /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked. * * Note that handle_userfault() may also release and reacquire mmap_lock * (and not return with VM_FAULT_RETRY), when returning to userland to * repeat the page fault later with a VM_FAULT_NOPAGE retval * (potentially after handling any pending signal during the return to * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); if (likely(!(fault & VM_FAULT_ERROR))) return; if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { no_context(regs, error_code, address, 0, 0); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; } /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got * oom-killed): */ pagefault_out_of_memory(); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); else if (fault & VM_FAULT_SIGSEGV) bad_area_nosemaphore(regs, error_code, address); else BUG(); } check_v8086_mode(regs, address, tsk); } NOKPROBE_SYMBOL(do_user_addr_fault); static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!trace_pagefault_enabled()) return; if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); else trace_page_fault_kernel(address, regs, error_code); } static __always_inline void handle_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { trace_page_fault_entries(regs, error_code, address); if (unlikely(kmmio_fault(regs, address))) return; /* Was the fault on kernel-controlled part of the address space? */ if (unlikely(fault_in_kernel_space(address))) { do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); /* * User address page fault handling might have reenabled * interrupts. Fixing up all potential exit points of * do_user_addr_fault() and its leaf functions is just not * doable w/o creating an unholy mess or turning the code * upside down. */ local_irq_disable(); } } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { unsigned long address = read_cr2(); irqentry_state_t state; prefetchw(¤t->mm->mmap_lock); /* * KVM uses #PF vector to deliver 'page not present' events to guests * (asynchronous page fault mechanism). The event happens when a * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event * which is injected when the memory becomes available, is delived via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * * We are relying on the interrupted context being sane (valid RSP, * relevant locks not held, etc.), which is fine as long as the * interrupted context had IF=1. We are also relying on the KVM * async pf type field and CR2 being read consistently instead of * getting values from real and async page faults mixed up. * * Fingers crossed. * * The async #PF handling code takes care of idtentry handling * itself. */ if (kvm_handle_async_pf(regs, (u32)address)) return; /* * Entry handling for valid #PF from kernel mode is slightly * different: RCU is already watching and rcu_irq_enter() must not * be invoked because a kernel fault on a user space address might * sleep. * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps * debugability. */ state = irqentry_enter(regs); instrumentation_begin(); handle_page_fault(regs, error_code, address); instrumentation_end(); irqentry_exit(regs, state); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter_start(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __FS_NOTIFY_FSNOTIFY_H_ #define __FS_NOTIFY_FSNOTIFY_H_ #include <linux/list.h> #include <linux/fsnotify.h> #include <linux/srcu.h> #include <linux/types.h> #include "../mount.h" static inline struct inode *fsnotify_conn_inode( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct inode, i_fsnotify_marks); } static inline struct mount *fsnotify_conn_mount( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct mount, mnt_fsnotify_marks); } static inline struct super_block *fsnotify_conn_sb( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct super_block, s_fsnotify_marks); } static inline struct super_block *fsnotify_connector_sb( struct fsnotify_mark_connector *conn) { switch (conn->type) { case FSNOTIFY_OBJ_TYPE_INODE: return fsnotify_conn_inode(conn)->i_sb; case FSNOTIFY_OBJ_TYPE_VFSMOUNT: return fsnotify_conn_mount(conn)->mnt.mnt_sb; case FSNOTIFY_OBJ_TYPE_SB: return fsnotify_conn_sb(conn); default: return NULL; } } /* destroy all events sitting in this groups notification queue */ extern void fsnotify_flush_notify(struct fsnotify_group *group); /* protects reads of inode and vfsmount marks list */ extern struct srcu_struct fsnotify_mark_srcu; /* compare two groups for sorting of marks lists */ extern int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b); /* Destroy all marks attached to an object via connector */ extern void fsnotify_destroy_marks(fsnotify_connp_t *connp); /* run the list of all marks associated with inode and destroy them */ static inline void fsnotify_clear_marks_by_inode(struct inode *inode) { fsnotify_destroy_marks(&inode->i_fsnotify_marks); } /* run the list of all marks associated with vfsmount and destroy them */ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt) { fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks); } /* run the list of all marks associated with sb and destroy them */ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb) { fsnotify_destroy_marks(&sb->s_fsnotify_marks); } /* * update the dentry->d_flags of all of inode's children to indicate if inode cares * about events that happen to its children. */ extern void fsnotify_set_children_dentry_flags(struct inode *inode); extern struct kmem_cache *fsnotify_mark_connector_cachep; #endif /* __FS_NOTIFY_FSNOTIFY_H_ */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> #include <linux/elf.h> #include <linux/elf-randomize.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> #include <linux/uaccess.h> #include "internal.h" /** * kfree_const - conditionally free memory * @x: pointer to the memory * * Function calls kfree only if @x is not in .rodata section. */ void kfree_const(const void *x) { if (!is_kernel_rodata((unsigned long)x)) kfree(x); } EXPORT_SYMBOL(kfree_const); /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrdup(const char *s, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strlen(s) + 1; buf = kmalloc_track_caller(len, gfp); if (buf) memcpy(buf, s, len); return buf; } EXPORT_SYMBOL(kstrdup); /** * kstrdup_const - conditionally duplicate an existing const string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. */ const char *kstrdup_const(const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return kstrdup(s, gfp); } EXPORT_SYMBOL(kstrdup_const); /** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Use kmemdup_nul() instead if the size is known exactly. * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strnlen(s, max); buf = kmalloc_track_caller(len+1, gfp); if (buf) { memcpy(buf, s, len); buf[len] = '\0'; } return buf; } EXPORT_SYMBOL(kstrndup); /** * kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error */ void *kmemdup(const void *src, size_t len, gfp_t gfp) { void *p; p = kmalloc_track_caller(len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify * @len: The size of the data * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { char *buf; if (!s) return NULL; buf = kmalloc_track_caller(len + 1, gfp); if (buf) { memcpy(buf, s, len); buf[len] = '\0'; } return buf; } EXPORT_SYMBOL(kmemdup_nul); /** * memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ void *memdup_user(const void __user *src, size_t len) { void *p; p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(memdup_user); /** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ void *vmemdup_user(const void __user *src, size_t len) { void *p; p = kvmalloc(len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(vmemdup_user); /** * strndup_user - duplicate an existing string from user space * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { char *p; long length; length = strnlen_user(s, n); if (!length) return ERR_PTR(-EFAULT); if (length > n) return ERR_PTR(-EINVAL); p = memdup_user(s, length); if (IS_ERR(p)) return p; p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); /** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. */ void *memdup_user_nul(const void __user *src, size_t len) { char *p; /* * Always use GFP_KERNEL, since copy_from_user() can sleep and * cause pagefault, which makes it pointless to use GFP_NOFS * or GFP_ATOMIC. */ p = kmalloc_track_caller(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } EXPORT_SYMBOL(memdup_user_nul); void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev) { struct vm_area_struct *next; vma->vm_prev = prev; if (prev) { next = prev->vm_next; prev->vm_next = vma; } else { next = mm->mmap; mm->mmap = vma; } vma->vm_next = next; if (next) next->vm_prev = vma; } void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev, *next; next = vma->vm_next; prev = vma->vm_prev; if (prev) prev->vm_next = next; else mm->mmap = next; if (next) next->vm_prev = prev; } /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP return PAGE_ALIGN(stack_top) + random_variable; #else return PAGE_ALIGN(stack_top) - random_variable; #endif } /** * randomize_page - Generate a random, page aligned address * @start: The smallest acceptable address the caller will take. * @range: The size of the area, starting at @start, within which the * random address must fall. * * If @start + @range would overflow, @range is capped. * * NOTE: Historical use of randomize_range, which this replaces, presumed that * @start was already page aligned. We now align it regardless. * * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; start = PAGE_ALIGN(start); } if (start > ULONG_MAX - range) range = ULONG_MAX - start; range >>= PAGE_SHIFT; if (range == 0) return start; return start + (get_random_long() % range << PAGE_SHIFT); } #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) return randomize_page(mm->brk, SZ_32M); return randomize_page(mm->brk, SZ_1G); } unsigned long arch_mmap_rnd(void) { unsigned long rnd; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS if (is_compat_task()) rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } static int mmap_is_legacy(struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; if (rlim_stack->rlim_cur == RLIM_INFINITY) return 1; return sysctl_legacy_va_layout; } /* * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; /* Account for stack randomization if necessary */ if (current->flags & PF_RANDOMIZE) pad += (STACK_RND_MASK << PAGE_SHIFT); /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; } #endif /** * __account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * @task: task used to check RLIMIT_MEMLOCK * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and * that mmap_lock is held as writer. * * Return: * * 0 on success * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim) { unsigned long locked_vm, limit; int ret = 0; mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { if (!bypass_rlim) { limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked_vm + pages > limit) ret = -ENOMEM; } if (!ret) mm->locked_vm = locked_vm + pages; } else { WARN_ON_ONCE(pages > locked_vm); mm->locked_vm = locked_vm - pages; } pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), ret ? " - exceeded" : ""); return ret; } EXPORT_SYMBOL_GPL(__account_locked_vm); /** * account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against, may be NULL * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). * * Return: * * 0 on success, or if mm is NULL * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) { int ret; if (pages == 0 || !mm) return 0; mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } return ret; } unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) { if (unlikely(offset + PAGE_ALIGN(len) < offset)) return -EINVAL; if (unlikely(offset_in_page(offset))) return -EINVAL; return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); } EXPORT_SYMBOL(vm_mmap); /** * kvmalloc_node - attempt to allocate physically contiguous memory, but upon * failure, fall back to non-contiguous (vmalloc) allocation. * @size: size of the request. * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. * @node: numa node to allocate from * * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Please note that any use of gfp flags outside of GFP_KERNEL is careful to not * fall back to vmalloc. * * Return: pointer to the allocated memory of %NULL in case of failure */ void *kvmalloc_node(size_t size, gfp_t flags, int node) { gfp_t kmalloc_flags = flags; void *ret; /* * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) * so the given set of flags has to be compatible. */ if ((flags & GFP_KERNEL) != GFP_KERNEL) return kmalloc_node(size, flags, node); /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore * contribute to a long term fragmentation less than vmalloc fallback. * However make sure that larger requests are not too disruptive - no * OOM killer and no allocation failure warnings as we have a fallback. */ if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; } ret = kmalloc_node(size, kmalloc_flags, node); /* * It doesn't really make sense to fallback to vmalloc for sub page * requests */ if (ret || size <= PAGE_SIZE) return ret; /* Don't even allow crazy sizes */ if (unlikely(size > INT_MAX)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; } return __vmalloc_node(size, 1, flags, node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); /** * kvfree() - Free memory. * @addr: Pointer to allocated memory. * * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). * It is slightly more efficient to use kfree() or vfree() if you are certain * that you know which one to use. * * Context: Either preemptible task context or not-NMI interrupt. */ void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) vfree(addr); else kfree(addr); } EXPORT_SYMBOL(kvfree); /** * kvfree_sensitive - Free a data object containing sensitive information. * @addr: address of the data object to be freed. * @len: length of the data object. * * Use the special memzero_explicit() function to clear the content of a * kvmalloc'ed object containing sensitive data to make sure that the * compiler won't optimize out the data clearing. */ void kvfree_sensitive(const void *addr, size_t len) { if (likely(!ZERO_OR_NULL_PTR(addr))) { memzero_explicit((void *)addr, len); kvfree(addr); } } EXPORT_SYMBOL(kvfree_sensitive); void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) { void *newp; if (oldsize >= newsize) return (void *)p; newp = kvmalloc(newsize, flags); if (!newp) return NULL; memcpy(newp, p, oldsize); kvfree(p); return newp; } EXPORT_SYMBOL(kvrealloc); static inline void *__page_rmapping(struct page *page) { unsigned long mapping; mapping = (unsigned long)page->mapping; mapping &= ~PAGE_MAPPING_FLAGS; return (void *)mapping; } /** * __vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return __vmalloc(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vmalloc_array(size_t n, size_t size) { return __vmalloc_array(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vcalloc(size_t n, size_t size, gfp_t flags) { return __vmalloc_array(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vcalloc(size_t n, size_t size) { return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc); /* Neutral page->mapping pointer to address_space or anon_vma or other */ void *page_rmapping(struct page *page) { page = compound_head(page); return __page_rmapping(page); } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any subpage of compound page is mapped. */ bool page_mapped(struct page *page) { int i; if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) >= 0; page = compound_head(page); if (atomic_read(compound_mapcount_ptr(page)) >= 0) return true; if (PageHuge(page)) return false; for (i = 0; i < compound_nr(page); i++) { if (atomic_read(&page[i]._mapcount) >= 0) return true; } return false; } EXPORT_SYMBOL(page_mapped); struct anon_vma *page_anon_vma(struct page *page) { unsigned long mapping; page = compound_head(page); mapping = (unsigned long)page->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; return __page_rmapping(page); } struct address_space *page_mapping(struct page *page) { struct address_space *mapping; page = compound_head(page); /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(PageSlab(page))) return NULL; if (unlikely(PageSwapCache(page))) { swp_entry_t entry; entry.val = page_private(page); return swap_address_space(entry); } mapping = page->mapping; if ((unsigned long)mapping & PAGE_MAPPING_ANON) return NULL; return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); } EXPORT_SYMBOL(page_mapping); /* * For file cache pages, return the address_space, otherwise return NULL */ struct address_space *page_mapping_file(struct page *page) { if (unlikely(PageSwapCache(page))) return NULL; return page_mapping(page); } /* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) { int ret; ret = atomic_read(&page->_mapcount) + 1; /* * For file THP page->_mapcount contains total number of mapping * of the page: no need to look into compound_mapcount. */ if (!PageAnon(page) && !PageHuge(page)) return ret; page = compound_head(page); ret += atomic_read(compound_mapcount_ptr(page)) + 1; if (PageDoubleMap(page)) ret--; return ret; } EXPORT_SYMBOL_GPL(__page_mapcount); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } static void sync_overcommit_as(struct work_struct *dummy) { percpu_counter_sync(&vm_committed_as); } int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; int ret; /* * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply * with the strict "NEVER", and to avoid possible race condtion (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch * 2. sync percpu count on each CPU * 3. switch the policy */ if (write) { t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); if (new_policy == OVERCOMMIT_NEVER) schedule_on_each_cpu(sync_overcommit_as); sysctl_overcommit_memory = new_policy; } else { ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } return ret; } int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else allowed = ((totalram_pages() - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; } /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; /* * The global memory commitment made in the system can be a metric * that can be used to drive ballooning decisions when Linux is hosted * as a guest. On Hyper-V, the host implements a policy engine for dynamically * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. * * The time cost of this is very low for small platforms, and for big * platform like a 2S/36C/72T Skylake server, in worst case where * vm_committed_as's spinlock is under severe contention, the time cost * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { if (pages > totalram_pages() + total_swap_pages) goto error; return 0; } allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* * Don't let a single process grow so big a user can't recover */ if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: vm_unacct_memory(pages); return -ENOMEM; } /** * get_cmdline() - copy the cmdline value to a buffer. * @task: the task whose cmdline value to copy. * @buffer: the buffer to copy to. * @buflen: the length of the buffer. Larger cmdline values are truncated * to this length. * * Return: the size of the cmdline field copied. Note that the copy does * not guarantee an ending NULL byte. */ int get_cmdline(struct task_struct *task, char *buffer, int buflen) { int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); len = arg_end - arg_start; if (len > buflen) len = buflen; res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); /* * If the nul at the end of args has been overwritten, then * assume application is using setproctitle(3). */ if (res > 0 && buffer[res-1] != '\0' && len < buflen) { len = strnlen(buffer, res); if (len < res) { res = len; } else { len = env_end - env_start; if (len > buflen - res) len = buflen - res; res += access_process_vm(task, env_start, buffer+res, len, FOLL_FORCE); res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_atomic(page1); addr2 = kmap_atomic(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_atomic(addr2); kunmap_atomic(addr1); return ret; } int mmap_file(struct file *file, struct vm_area_struct *vma) { static const struct vm_operations_struct dummy_vm_ops = {}; int err = call_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we most not invoke * any further hooks on it. */ vma->vm_ops = &dummy_vm_ops; return err; } void vma_close(struct vm_area_struct *vma) { static const struct vm_operations_struct dummy_vm_ops = {}; if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &dummy_vm_ops; } } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LLIST_H #define LLIST_H /* * Lock-less NULL terminated single linked list * * Cases where locking is not needed: * If there are multiple producers and multiple consumers, llist_add can be * used in producers and llist_del_all can be used in consumers simultaneously * without locking. Also a single consumer can use llist_del_first while * multiple producers simultaneously use llist_add, without any locking. * * Cases where locking is needed: * If we have multiple consumers with llist_del_first used in one consumer, and * llist_del_first or llist_del_all used in other consumers, then a lock is * needed. This is because llist_del_first depends on list->first->next not * changing, but without lock protection, there's no way to be sure about that * if a preemption happens in the middle of the delete operation and on being * preempted back, the list->first is the same as before causing the cmpxchg in * llist_del_first to succeed. For example, while a llist_del_first operation * is in progress in one consumer, then a llist_del_first, llist_add, * llist_add (or llist_del_all, llist_add, llist_add) sequence in another * consumer may cause violations. * * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * * Where, a particular row's operation can happen concurrently with a column's * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list * entries can not be traversed safely before deleted from the list. * The order of deleted entries is from the newest to the oldest added * one. If you want to traverse from the oldest to the newest, you * must reverse the order by yourself before traversing. * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/atomic.h> #include <linux/kernel.h> struct llist_head { struct llist_node *first; }; struct llist_node { struct llist_node *next; }; #define LLIST_HEAD_INIT(name) { NULL } #define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) /** * init_llist_head - initialize lock-less list head * @head: the head for your lock-less list */ static inline void init_llist_head(struct llist_head *list) { list->first = NULL; } /** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. * @member: the name of the llist_node within the struct. */ #define llist_entry(ptr, type, member) \ container_of(ptr, type, member) /** * member_address_is_nonnull - check whether the member address is not NULL * @ptr: the object pointer (struct type * that contains the llist_node) * @member: the name of the llist_node within the struct. * * This macro is conceptually the same as * &ptr->member != NULL * but it works around the fact that compilers can decide that taking a member * address is never a NULL pointer. * * Real objects that start at a high address and have a member at NULL are * unlikely to exist, but such pointers may be returned e.g. by the * container_of() macro. */ #define member_address_is_nonnull(ptr, member) \ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) /** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each(pos, node) \ for ((pos) = (node); pos; (pos) = (pos)->next) /** * llist_for_each_safe - iterate over some deleted entries of a lock-less list * safe against removal of list entry * @pos: the &struct llist_node to use as a loop cursor * @n: another &struct llist_node to use as temporary storage * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_safe(pos, n, node) \ for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) /** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type * safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @node: the first entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * * Not guaranteed to be accurate or up to date. Just a quick way to * test whether the list is empty without deleting something from the * list. */ static inline bool llist_empty(const struct llist_head *head) { return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) { return node->next; } extern bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head); /** * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list * * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { return llist_add_batch(new, new, head); } /** * llist_del_all - delete all entries from lock-less list * @head: the head of lock-less list to delete all entries * * If list is empty, return NULL, otherwise, delete all entries and * return the pointer to the first entry. The order of entries * deleted is from the newest to the oldest added one. */ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } extern struct llist_node *llist_del_first(struct llist_head *head); struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BITOPS_H #define _ASM_X86_BITOPS_H /* * Copyright 1992, Linus Torvalds. * * Note: inlines with more than a single statement should be marked * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> #include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 #elif BITS_PER_LONG == 64 # define _BITOPS_LONG_SHIFT 6 #else # error "Unexpected BITS_PER_LONG" #endif #define BIT_64(n) (U64_C(1) << (n)) /* * These have to be done with inline assembly: that way the bit-setting * is guaranteed to be atomic. All bit operations return 0 if the bit * was cleared before the operation and != 0 if it was not. * * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ #define RLONG_ADDR(x) "m" (*(volatile long *) (x)) #define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) #define ADDR RLONG_ADDR(addr) /* * We do the locked ops that don't return the old value as * a mask operation on a byte. */ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "orb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr)) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch___set_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "andb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (~CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); arch_clear_bit(nr, addr); } static __always_inline void arch___clear_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) : CC_OUT(s) (negative), WBYTE_ADDR(addr) : "ir" ((char) ~(1 << nr)) : "memory"); return negative; } #define arch_clear_bit_unlock_is_negative_byte \ arch_clear_bit_unlock_is_negative_byte static __always_inline void arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { arch___clear_bit(nr, addr); } static __always_inline void arch___change_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "xorb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline bool arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } static __always_inline bool arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return arch_test_and_set_bit(nr, addr); } static __always_inline bool arch___test_and_set_bit(long nr, volatile unsigned long *addr) { bool oldbit; asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } /* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. * KVM relies on this behaviour on x86 for modifying memory that is also * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ static __always_inline bool arch___test_and_clear_bit(long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch___test_and_change_bit(long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } #define arch_test_bit(nr, addr) \ (__builtin_constant_p((nr)) \ ? constant_test_bit((nr), (addr)) \ : variable_test_bit((nr), (addr))) /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ static __always_inline unsigned long __ffs(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) : "rm" (word)); return word; } /** * ffz - find first zero bit in word * @word: The word to search * * Undefined if no zero exists, so code should check against ~0UL first. */ static __always_inline unsigned long ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) : "r" (~word)); return word; } /* * __fls: find last set bit in word * @word: The word to search * * Undefined if no set bit exists, so code should check against 0 first. */ static __always_inline unsigned long __fls(unsigned long word) { asm("bsr %1,%0" : "=r" (word) : "rm" (word)); return word; } #undef ADDR #ifdef __KERNEL__ /** * ffs - find first set bit in word * @x: the word to search * * This is defined the same way as the libc and compiler builtin ffs * routines, therefore differs in spirit from the other bitops. * * ffs(value) returns 0 if value is 0 or the position of the first * set bit if value is nonzero. The first (least significant) bit * is at position 1. */ static __always_inline int ffs(int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsfl %1,%0" : "=r" (r) : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "r" (-1)); #else asm("bsfl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls - find last set bit in word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffs, but returns the position of the most significant set bit. * * fls(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ static __always_inline int fls(unsigned int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsrl %1,%0" : "=r" (r) : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "rm" (-1)); #else asm("bsrl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls64 - find last set bit in a 64-bit word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffsll, but returns the position of the most significant set bit. * * fls64(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 64. */ #ifdef CONFIG_X86_64 static __always_inline int fls64(__u64 x) { int bitpos = -1; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ asm("bsrq %1,%q0" : "+r" (bitpos) : "rm" (x)); return bitpos + 1; } #else #include <asm-generic/bitops/fls64.h> #endif #include <asm-generic/bitops/find.h> #include <asm-generic/bitops/sched.h> #include <asm/arch_hweight.h> #include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-non-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_FORCE_MAX_ZONEORDER #define MAX_ORDER 11 #else #define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. What is important though * is that a range of pageblocks must be aligned to * MAX_ORDER_NR_PAGES should biggest page be bigger then * a single pageblock. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; static inline struct page *get_page_from_free_area(struct free_area *area, int migratetype) { return list_first_entry_or_null(&area->free_list[migratetype], struct page, lru); } static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } struct pglist_data; /* * zone->lock and the zone lru_lock are two of the hottest locks in the kernel. * So add a wild amount of padding here to ensure that they fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ #if defined(CONFIG_SMP) struct zone_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define ZONE_PADDING(name) struct zone_padding name; #else #define ZONE_PADDING(name) #endif #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_STAT_ITEMS }; #else #define NR_VM_NUMA_STAT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define ANON_AND_FILE 2 enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI */ }; struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif }; /* Isolate unmapped pages */ #define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, NR_WMARK }; #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[MIGRATE_PCPTYPES]; }; struct per_cpu_pageset { struct per_cpu_pages pcp; #ifdef CONFIG_NUMA s8 expire; u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif #ifdef CONFIG_SMP s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Memory offlining might * retry a long time. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NEED_MULTIPLE_NODES int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/end(). Any reader who can't tolerant drift of * present_pages should get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ ZONE_PADDING(_pad1_) /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ ZONE_PADDING(_pad2_) /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; #ifndef CONFIG_DISCONTIGMEM /* The array of struct pages - for discontigmem use pgdat->lmem_map */ extern struct page *mem_map; #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ ZONE_PADDING(_pad1_) spinlock_t lru_lock; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; ZONE_PADDING(_pad2_) /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #ifdef CONFIG_FLAT_NODE_MEM_MAP #define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) #else #define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } static inline bool pgdat_is_empty(pg_data_t *pgdat) { return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NEED_MULTIPLE_NODES static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; #ifdef CONFIG_HIGHMEM static inline int zone_movable_is_highmem(void) { #ifdef CONFIG_NEED_MULTIPLE_NODES return movable_zone == ZONE_HIGHMEM; #else return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; #endif } #endif static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && zone_movable_is_highmem())); #else return 0; #endif } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable */ static inline int is_highmem(struct zone *zone) { #ifdef CONFIG_HIGHMEM return is_highmem_idx(zone_idx(zone)); #else return 0; #endif } /* These two functions are used to setup the per zone pages min values */ struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NEED_MULTIPLE_NODES extern struct pglist_data contig_page_data; #define NODE_DATA(nid) (&contig_page_data) #define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NEED_MULTIPLE_NODES */ #include <asm/mmzone.h> #endif /* !CONFIG_NEED_MULTIPLE_NODES */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat - pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone - pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z - The cursor used as a starting point for the search * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone - The current zone in the iterator * @z - The current pointer within zonelist->_zonerefs being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * @nodemask - Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone - The current zone in the iterator * @z - The current pointer within zonelist->zones being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!z->zone) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * SECTION_SHIFT #bits space required to store a section # * * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern unsigned long __section_nr(struct mem_section *ms); extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available. */ #define SECTION_MARKED_PRESENT (1UL<<0) #define SECTION_HAS_MEM_MAP (1UL<<1) #define SECTION_IS_ONLINE (1UL<<2) #define SECTION_IS_EARLY (1UL<<3) #define SECTION_MAP_LAST_BIT (1UL<<4) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) #define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock(); if (!valid_section(ms)) { rcu_read_unlock(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ /* * During memory init memblocks map pfns to nids. The search is expensive and * this caches recent lookups. The implementation of __early_pfn_to_nid * may treat start/end as pfns or sections. */ struct mminit_pfnnid_cache { unsigned long last_start; unsigned long last_end; int last_nid; }; /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we * need to check pfn validity within that MAX_ORDER_NR_PAGES block. * pfn_valid_within() should be used in this case; we optimise this away * when we have no holes within a MAX_ORDER_NR_PAGES block. */ #ifdef CONFIG_HOLES_IN_ZONE #define pfn_valid_within(pfn) pfn_valid(pfn) #else #define pfn_valid_within(pfn) (1) #endif #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * Why is there no list_empty_rcu()? Because list_empty() serves this * purpose. The list_empty() function fetches the RCU-protected pointer * and compares it to the address of the list head, but neither dereferences * this pointer itself nor provides this pointer to the caller. Therefore, * it is not necessary to use rcu_dereference(), so that list_empty() can * be used anywhere you would want to use a list_empty_rcu(). */ /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * Implementing those functions following their counterparts list_empty() and * list_first_entry() is not advisable because they lead to subtle race * conditions as the following snippet shows: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list may not be empty when list_empty_rcu checks it, but it may be when * list_first_entry_rcu rereads the ->next pointer. * * Rereading the ->next pointer is not a problem for list_empty() and * list_first_entry() because they would be protected by a lock that blocks * writers. * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/filesystems.c * * Copyright (C) 1991, 1992 Linus Torvalds * * table of configured filesystems */ #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs_parser.h> /* * Handling of filesystem drivers list. * Rules: * Inclusion to/removals from/scanning of list are protected by spinlock. * During the unload module must call unregister_filesystem(). * We can access the fields of list element if: * 1) spinlock is held or * 2) we hold the reference to the module. * The latter can be guaranteed by call of try_module_get(); if it * returned 0 we must skip the element, otherwise we got the reference. * Once the reference is obtained we can drop the spinlock. */ static struct file_system_type *file_systems; static DEFINE_RWLOCK(file_systems_lock); /* WARNING: This can be used only if we _already_ own a reference */ struct file_system_type *get_filesystem(struct file_system_type *fs) { __module_get(fs->owner); return fs; } void put_filesystem(struct file_system_type *fs) { module_put(fs->owner); } static struct file_system_type **find_filesystem(const char *name, unsigned len) { struct file_system_type **p; for (p = &file_systems; *p; p = &(*p)->next) if (strncmp((*p)->name, name, len) == 0 && !(*p)->name[len]) break; return p; } /** * register_filesystem - register a new filesystem * @fs: the file system structure * * Adds the file system passed to the list of file systems the kernel * is aware of for mount and other syscalls. Returns 0 on success, * or a negative errno code on an error. * * The &struct file_system_type that is passed is linked into the kernel * structures and must not be freed until the file system has been * unregistered. */ int register_filesystem(struct file_system_type * fs) { int res = 0; struct file_system_type ** p; if (fs->parameters && !fs_validate_description(fs->name, fs->parameters)) return -EINVAL; BUG_ON(strchr(fs->name, '.')); if (fs->next) return -EBUSY; write_lock(&file_systems_lock); p = find_filesystem(fs->name, strlen(fs->name)); if (*p) res = -EBUSY; else *p = fs; write_unlock(&file_systems_lock); return res; } EXPORT_SYMBOL(register_filesystem); /** * unregister_filesystem - unregister a file system * @fs: filesystem to unregister * * Remove a file system that was previously successfully registered * with the kernel. An error is returned if the file system is not found. * Zero is returned on a success. * * Once this function has returned the &struct file_system_type structure * may be freed or reused. */ int unregister_filesystem(struct file_system_type * fs) { struct file_system_type ** tmp; write_lock(&file_systems_lock); tmp = &file_systems; while (*tmp) { if (fs == *tmp) { *tmp = fs->next; fs->next = NULL; write_unlock(&file_systems_lock); synchronize_rcu(); return 0; } tmp = &(*tmp)->next; } write_unlock(&file_systems_lock); return -EINVAL; } EXPORT_SYMBOL(unregister_filesystem); #ifdef CONFIG_SYSFS_SYSCALL static int fs_index(const char __user * __name) { struct file_system_type * tmp; struct filename *name; int err, index; name = getname(__name); err = PTR_ERR(name); if (IS_ERR(name)) return err; err = -EINVAL; read_lock(&file_systems_lock); for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) { if (strcmp(tmp->name, name->name) == 0) { err = index; break; } } read_unlock(&file_systems_lock); putname(name); return err; } static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; int len, res = -EINVAL; read_lock(&file_systems_lock); for (tmp = file_systems; tmp; tmp = tmp->next, index--) { if (index == 0) { if (try_module_get(tmp->owner)) res = 0; break; } } read_unlock(&file_systems_lock); if (res) return res; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; res = copy_to_user(buf, tmp->name, len) ? -EFAULT : 0; put_filesystem(tmp); return res; } static int fs_maxindex(void) { struct file_system_type * tmp; int index; read_lock(&file_systems_lock); for (tmp = file_systems, index = 0 ; tmp ; tmp = tmp->next, index++) ; read_unlock(&file_systems_lock); return index; } /* * Whee.. Weird sysv syscall. */ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) { int retval = -EINVAL; switch (option) { case 1: retval = fs_index((const char __user *) arg1); break; case 2: retval = fs_name(arg1, (char __user *) arg2); break; case 3: retval = fs_maxindex(); break; } return retval; } #endif int __init get_filesystem_list(char *buf) { int len = 0; struct file_system_type * tmp; read_lock(&file_systems_lock); tmp = file_systems; while (tmp && len < PAGE_SIZE - 80) { len += sprintf(buf+len, "%s\t%s\n", (tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev", tmp->name); tmp = tmp->next; } read_unlock(&file_systems_lock); return len; } #ifdef CONFIG_PROC_FS static int filesystems_proc_show(struct seq_file *m, void *v) { struct file_system_type * tmp; read_lock(&file_systems_lock); tmp = file_systems; while (tmp) { seq_printf(m, "%s\t%s\n", (tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev", tmp->name); tmp = tmp->next; } read_unlock(&file_systems_lock); return 0; } static int __init proc_filesystems_init(void) { proc_create_single("filesystems", 0, NULL, filesystems_proc_show); return 0; } module_init(proc_filesystems_init); #endif static struct file_system_type *__get_fs_type(const char *name, int len) { struct file_system_type *fs; read_lock(&file_systems_lock); fs = *(find_filesystem(name, len)); if (fs && !try_module_get(fs->owner)) fs = NULL; read_unlock(&file_systems_lock); return fs; } struct file_system_type *get_fs_type(const char *name) { struct file_system_type *fs; const char *dot = strchr(name, '.'); int len = dot ? dot - name : strlen(name); fs = __get_fs_type(name, len); if (!fs && (request_module("fs-%.*s", len, name) == 0)) { fs = __get_fs_type(name, len); if (!fs) pr_warn_once("request_module fs-%.*s succeeded, but still no fs?\n", len, name); } if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) { put_filesystem(fs); fs = NULL; } return fs; } EXPORT_SYMBOL(get_fs_type); |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <asm/page.h> #include "kstrtox.h" /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return 0; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return 0; return 1; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); /** * bitmap_cut() - remove bit region from bitmap and right shift remaining bits * @dst: destination bitmap, might overlap with src * @src: source bitmap * @first: start bit of region to be removed * @cut: number of bits to remove * @nbits: bitmap size, in bits * * Set the n-th bit of @dst iff the n-th bit of @src is set and * n is less than @first, or the m-th bit of @src is set for any * m such that @first <= n < nbits, and m = n + @cut. * * In pictures, example for a big-endian 32-bit architecture: * * The @src bitmap is:: * * 31 63 * | | * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101 * | | | | * 16 14 0 32 * * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:: * * 31 63 * | | * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010 * | | | * 14 (bit 17 0 32 * from @src) * * Note that @dst and @src might overlap partially or entirely. * * This is implemented in the obvious way, with a shift and carry * step for each moved bit. Optimisation is left as an exercise * for the compiler. */ void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits); unsigned long keep = 0, carry; int i; if (first % BITS_PER_LONG) { keep = src[first / BITS_PER_LONG] & (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG)); } memmove(dst, src, len * sizeof(*dst)); while (cut--) { for (i = first / BITS_PER_LONG; i < len; i++) { if (i < len - 1) carry = dst[i + 1] & 1UL; else carry = 0; dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1)); } } dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG); dst[first / BITS_PER_LONG] |= keep; } EXPORT_SYMBOL(bitmap_cut); int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(nbits); for (k = 0; k < nr; k++) dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); } EXPORT_SYMBOL(__bitmap_replace); int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return 1; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return 1; return 0; } EXPORT_SYMBOL(__bitmap_intersects); int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return 0; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return 0; return 1; } EXPORT_SYMBOL(__bitmap_subset); int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; int w = 0; for (k = 0; k < lim; k++) w += hweight_long(bitmap[k]); if (bits % BITS_PER_LONG) w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits)); return w; } EXPORT_SYMBOL(__bitmap_weight); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /* * Bitmap printing & parsing functions: first version by Nadia Yvette Chambers, * second version by Paul Jackson, third by Joe Korty. */ /** * bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap * * @ubuf: pointer to user buffer containing string. * @ulen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. */ int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *maskp, int nmaskbits) { char *buf; int ret; buf = memdup_user_nul(ubuf, ulen); if (IS_ERR(buf)) return PTR_ERR(buf); ret = bitmap_parse(buf, UINT_MAX, maskp, nmaskbits); kfree(buf); return ret; } EXPORT_SYMBOL(bitmap_parse_user); /** * bitmap_print_to_pagebuf - convert bitmap to list or hex format ASCII string * @list: indicates whether the bitmap must be list * @buf: page aligned buffer into which string is placed * @maskp: pointer to bitmap to convert * @nmaskbits: size of bitmap, in bits * * Output format is a comma-separated list of decimal numbers and * ranges if list is specified or hex digits grouped into comma-separated * sets of 8 digits/set. Returns the number of characters written to buf. * * It is assumed that @buf is a pointer into a PAGE_SIZE, page-aligned * area and that sufficient storage remains at @buf to accommodate the * bitmap_print_to_pagebuf() output. Returns the number of characters * actually printed to @buf, excluding terminating '\0'. */ int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits) { ptrdiff_t len = PAGE_SIZE - offset_in_page(buf); return list ? scnprintf(buf, len, "%*pbl\n", nmaskbits, maskp) : scnprintf(buf, len, "%*pb\n", nmaskbits, maskp); } EXPORT_SYMBOL(bitmap_print_to_pagebuf); /* * Region 9-38:4/10 describes the following bitmap structure: * 0 9 12 18 38 * .........****......****......****...... * ^ ^ ^ ^ * start off group_len end */ struct region { unsigned int start; unsigned int off; unsigned int group_len; unsigned int end; }; static int bitmap_set_region(const struct region *r, unsigned long *bitmap, int nbits) { unsigned int start; if (r->end >= nbits) return -ERANGE; for (start = r->start; start <= r->end; start += r->group_len) bitmap_set(bitmap, start, min(r->end - start + 1, r->off)); return 0; } static int bitmap_check_region(const struct region *r) { if (r->start > r->end || r->group_len == 0 || r->off > r->group_len) return -EINVAL; return 0; } static const char *bitmap_getnum(const char *str, unsigned int *num) { unsigned long long n; unsigned int len; len = _parse_integer(str, 10, &n); if (!len) return ERR_PTR(-EINVAL); if (len & KSTRTOX_OVERFLOW || n != (unsigned int)n) return ERR_PTR(-EOVERFLOW); *num = n; return str + len; } static inline bool end_of_str(char c) { return c == '\0' || c == '\n'; } static inline bool __end_of_region(char c) { return isspace(c) || c == ','; } static inline bool end_of_region(char c) { return __end_of_region(c) || end_of_str(c); } /* * The format allows commas and whitespaces at the beginning * of the region. */ static const char *bitmap_find_region(const char *str) { while (__end_of_region(*str)) str++; return end_of_str(*str) ? NULL : str; } static const char *bitmap_find_region_reverse(const char *start, const char *end) { while (start <= end && __end_of_region(*end)) end--; return end; } static const char *bitmap_parse_region(const char *str, struct region *r) { str = bitmap_getnum(str, &r->start); if (IS_ERR(str)) return str; if (end_of_region(*str)) goto no_end; if (*str != '-') return ERR_PTR(-EINVAL); str = bitmap_getnum(str + 1, &r->end); if (IS_ERR(str)) return str; if (end_of_region(*str)) goto no_pattern; if (*str != ':') return ERR_PTR(-EINVAL); str = bitmap_getnum(str + 1, &r->off); if (IS_ERR(str)) return str; if (*str != '/') return ERR_PTR(-EINVAL); return bitmap_getnum(str + 1, &r->group_len); no_end: r->end = r->start; no_pattern: r->off = r->end + 1; r->group_len = r->end + 1; return end_of_str(*str) ? NULL : str; } /** * bitmap_parselist - convert list format ASCII string to bitmap * @buf: read user string from this buffer; must be terminated * with a \0 or \n. * @maskp: write resulting mask here * @nmaskbits: number of bits in mask to be written * * Input format is a comma-separated list of decimal numbers and * ranges. Consecutively set bits are shown as two hyphen-separated * decimal numbers, the smallest and largest bit numbers set in * the range. * Optionally each range can be postfixed to denote that only parts of it * should be set. The range will divided to groups of specific size. * From each group will be used only defined amount of bits. * Syntax: range:used_size/group_size * Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769 * * Returns: 0 on success, -errno on invalid input strings. Error values: * * - ``-EINVAL``: wrong region format * - ``-EINVAL``: invalid character in string * - ``-ERANGE``: bit number specified too large for mask * - ``-EOVERFLOW``: integer overflow in the input parameters */ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits) { struct region r; long ret; bitmap_zero(maskp, nmaskbits); while (buf) { buf = bitmap_find_region(buf); if (buf == NULL) return 0; buf = bitmap_parse_region(buf, &r); if (IS_ERR(buf)) return PTR_ERR(buf); ret = bitmap_check_region(&r); if (ret) return ret; ret = bitmap_set_region(&r, maskp, nmaskbits); if (ret) return ret; } return 0; } EXPORT_SYMBOL(bitmap_parselist); /** * bitmap_parselist_user() * * @ubuf: pointer to user buffer containing string. * @ulen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. * * Wrapper for bitmap_parselist(), providing it with user buffer. */ int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *maskp, int nmaskbits) { char *buf; int ret; buf = memdup_user_nul(ubuf, ulen); if (IS_ERR(buf)) return PTR_ERR(buf); ret = bitmap_parselist(buf, maskp, nmaskbits); kfree(buf); return ret; } EXPORT_SYMBOL(bitmap_parselist_user); static const char *bitmap_get_x32_reverse(const char *start, const char *end, u32 *num) { u32 ret = 0; int c, i; for (i = 0; i < 32; i += 4) { c = hex_to_bin(*end--); if (c < 0) return ERR_PTR(-EINVAL); ret |= c << i; if (start > end || __end_of_region(*end)) goto out; } if (hex_to_bin(*end--) >= 0) return ERR_PTR(-EOVERFLOW); out: *num = ret; return end; } /** * bitmap_parse - convert an ASCII hex string into a bitmap. * @start: pointer to buffer containing string. * @buflen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0 or \n. In that case, * UINT_MAX may be provided instead of string length. * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. * * Commas group hex digits into chunks. Each chunk defines exactly 32 * bits of the resultant bitmask. No chunk may specify a value larger * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value * then leading 0-bits are prepended. %-EINVAL is returned for illegal * characters. Grouping such as "1,,5", ",44", "," or "" is allowed. * Leading, embedded and trailing whitespace accepted. */ int bitmap_parse(const char *start, unsigned int buflen, unsigned long *maskp, int nmaskbits) { const char *end = strnchrnul(start, buflen, '\n') - 1; int chunks = BITS_TO_U32(nmaskbits); u32 *bitmap = (u32 *)maskp; int unset_bit; int chunk; for (chunk = 0; ; chunk++) { end = bitmap_find_region_reverse(start, end); if (start > end) break; if (!chunks--) return -EOVERFLOW; #if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN) end = bitmap_get_x32_reverse(start, end, &bitmap[chunk ^ 1]); #else end = bitmap_get_x32_reverse(start, end, &bitmap[chunk]); #endif if (IS_ERR(end)) return PTR_ERR(end); } unset_bit = (BITS_TO_U32(nmaskbits) - chunks) * 32; if (unset_bit < nmaskbits) { bitmap_clear(maskp, unset_bit, nmaskbits - unset_bit); return 0; } if (find_next_bit(maskp, unset_bit, nmaskbits) != unset_bit) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(bitmap_parse); #ifdef CONFIG_NUMA /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return __bitmap_weight(buf, pos); } /** * bitmap_ord_to_pos - find position of n-th set bit in bitmap * @buf: pointer to bitmap * @ord: ordinal bit position (n-th set bit, n >= 0) * @nbits: number of valid bit positions in @buf * * Map the ordinal offset of bit @ord in @buf to its position in @buf. * Value of @ord should be in range 0 <= @ord < weight(buf). If @ord * >= weight(buf), returns @nbits. * * If for example, just bits 4 through 7 are set in @buf, then @ord * values 0 through 3 will get mapped to 4 through 7, respectively, * and all other @ord values returns @nbits. When @ord value 3 * gets mapped to (returns) @pos value 7 in this example, that means * that the 3rd set bit (starting with 0th) is at position 7 in @buf. * * The bit positions 0 through @nbits-1 are valid positions in @buf. */ unsigned int bitmap_ord_to_pos(const unsigned long *buf, unsigned int ord, unsigned int nbits) { unsigned int pos; for (pos = find_first_bit(buf, nbits); pos < nbits && ord; pos = find_next_bit(buf, nbits, pos + 1)) ord--; return pos; } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identify map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(bitmap_ord_to_pos(new, n % w, nbits), dst); } } /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identify map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return bitmap_ord_to_pos(new, n % w, bits); } /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated * @bits: number of bits in each of these bitmaps * * Set the n-th bit of @dst iff there exists some m such that the * n-th bit of @relmap is set, the m-th bit of @orig is set, and * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. * (If you understood the previous sentence the first time your * read it, you're overqualified for your current job.) * * In other words, @orig is mapped onto (surjectively) @dst, * using the map { <n, m> | the n-th bit of @relmap is the * m-th set bit of @relmap }. * * Any set bits in @orig above bit number W, where W is the * weight of (number of set bits in) @relmap are mapped nowhere. * In particular, if for all bits m set in @orig, m >= W, then * @dst will end up empty. In situations where the possibility * of such an empty result is not desired, one way to avoid it is * to use the bitmap_fold() operator, below, to first fold the * @orig bitmap over itself so that all its set bits x are in the * range 0 <= x < W. The bitmap_fold() operator does this by * setting the bit (m % W) in @dst, for each bit (m) set in @orig. * * Example [1] for bitmap_onto(): * Let's say @relmap has bits 30-39 set, and @orig has bits * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, * @dst will have bits 31, 33, 35, 37 and 39 set. * * When bit 0 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the first bit (if any) * that is turned on in @relmap. Since bit 0 was off in the * above example, we leave off that bit (bit 30) in @dst. * * When bit 1 is set in @orig (as in the above example), it * means turn on the bit in @dst corresponding to whatever * is the second bit that is turned on in @relmap. The second * bit in @relmap that was turned on in the above example was * bit 31, so we turned on bit 31 in @dst. * * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, * because they were the 4th, 6th, 8th and 10th set bits * set in @relmap, and the 4th, 6th, 8th and 10th bits of * @orig (i.e. bits 3, 5, 7 and 9) were also set. * * When bit 11 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the twelfth bit that is * turned on in @relmap. In the above example, there were * only ten bits turned on in @relmap (30..39), so that bit * 11 was set in @orig had no affect on @dst. * * Example [2] for bitmap_fold() + bitmap_onto(): * Let's say @relmap has these ten bits set:: * * 40 41 42 43 45 48 53 61 74 95 * * (for the curious, that's 40 plus the first ten terms of the * Fibonacci sequence.) * * Further lets say we use the following code, invoking * bitmap_fold() then bitmap_onto, as suggested above to * avoid the possibility of an empty @dst result:: * * unsigned long *tmp; // a temporary bitmap's bits * * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); * bitmap_onto(dst, tmp, relmap, bits); * * Then this table shows what various values of @dst would be, for * various @orig's. I list the zero-based positions of each set bit. * The tmp column shows the intermediate result, as computed by * using bitmap_fold() to fold the @orig bitmap modulo ten * (the weight of @relmap): * * =============== ============== ================= * @orig tmp @dst * 0 0 40 * 1 1 41 * 9 9 95 * 10 0 40 [#f1]_ * 1 3 5 7 1 3 5 7 41 43 48 61 * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 * 0 9 18 27 0 9 8 7 40 61 74 95 * 0 10 20 30 0 40 * 0 11 22 33 0 1 2 3 40 41 42 43 * 0 12 24 36 0 2 4 6 40 42 45 53 * 78 102 211 1 2 8 41 42 74 [#f1]_ * =============== ============== ================= * * .. [#f1] * * For these marked lines, if we hadn't first done bitmap_fold() * into tmp, then the @dst result would have been empty. * * If either of @orig or @relmap is empty (no set bits), then @dst * will be returned empty. * * If (as explained above) the only set bits in @orig are in positions * m where m >= W, (where W is the weight of @relmap) then @dst will * once again be returned empty. * * All bits in @dst not set by the above rule are cleared. */ void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits) { unsigned int n, m; /* same meaning as in above comment */ if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, bits); /* * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { * n = bitmap_ord_to_pos(orig, m, bits); * if (test_bit(m, orig)) * set_bit(n, dst); * } */ m = 0; for_each_set_bit(n, relmap, bits) { /* m == bitmap_pos_to_ord(relmap, n, bits) */ if (test_bit(m, orig)) set_bit(n, dst); m++; } } /** * bitmap_fold - fold larger bitmap into smaller, modulo specified size * @dst: resulting smaller bitmap * @orig: original larger bitmap * @sz: specified size * @nbits: number of bits in each of these bitmaps * * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. * Clear all other bits in @dst. See further the comment and * Example [2] for bitmap_onto() for why and how to use this. */ void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits) { unsigned int oldbit; if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, nbits); for_each_set_bit(oldbit, orig, nbits) set_bit(oldbit % sz, dst); } #endif /* CONFIG_NUMA */ /* * Common code for bitmap_*_region() routines. * bitmap: array of unsigned longs corresponding to the bitmap * pos: the beginning of the region * order: region size (log base 2 of number of bits) * reg_op: operation(s) to perform on that region of bitmap * * Can set, verify and/or release a region of bits in a bitmap, * depending on which combination of REG_OP_* flag bits is set. * * A region of a bitmap is a sequence of bits in the bitmap, of * some size '1 << order' (a power of two), aligned to that same * '1 << order' power of two. * * Returns 1 if REG_OP_ISFREE succeeds (region is all zero bits). * Returns 0 in all other cases and reg_ops. */ enum { REG_OP_ISFREE, /* true if region is all zero bits */ REG_OP_ALLOC, /* set all bits in region */ REG_OP_RELEASE, /* clear all bits in region */ }; static int __reg_op(unsigned long *bitmap, unsigned int pos, int order, int reg_op) { int nbits_reg; /* number of bits in region */ int index; /* index first long of region in bitmap */ int offset; /* bit offset region in bitmap[index] */ int nlongs_reg; /* num longs spanned by region in bitmap */ int nbitsinlong; /* num bits of region in each spanned long */ unsigned long mask; /* bitmask for one long of region */ int i; /* scans bitmap by longs */ int ret = 0; /* return value */ /* * Either nlongs_reg == 1 (for small orders that fit in one long) * or (offset == 0 && mask == ~0UL) (for larger multiword orders.) */ nbits_reg = 1 << order; index = pos / BITS_PER_LONG; offset = pos - (index * BITS_PER_LONG); nlongs_reg = BITS_TO_LONGS(nbits_reg); nbitsinlong = min(nbits_reg, BITS_PER_LONG); /* * Can't do "mask = (1UL << nbitsinlong) - 1", as that * overflows if nbitsinlong == BITS_PER_LONG. */ mask = (1UL << (nbitsinlong - 1)); mask += mask - 1; mask <<= offset; switch (reg_op) { case REG_OP_ISFREE: for (i = 0; i < nlongs_reg; i++) { if (bitmap[index + i] & mask) goto done; } ret = 1; /* all bits in region free (zero) */ break; case REG_OP_ALLOC: for (i = 0; i < nlongs_reg; i++) bitmap[index + i] |= mask; break; case REG_OP_RELEASE: for (i = 0; i < nlongs_reg; i++) bitmap[index + i] &= ~mask; break; } done: return ret; } /** * bitmap_find_free_region - find a contiguous aligned mem region * @bitmap: array of unsigned longs corresponding to the bitmap * @bits: number of bits in the bitmap * @order: region size (log base 2 of number of bits) to find * * Find a region of free (zero) bits in a @bitmap of @bits bits and * allocate them (set them to one). Only consider regions of length * a power (@order) of two, aligned to that power of two, which * makes the search algorithm much faster. * * Return the bit offset in bitmap of the allocated region, * or -errno on failure. */ int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) { unsigned int pos, end; /* scans bitmap by regions of size order */ for (pos = 0 ; (end = pos + (1U << order)) <= bits; pos = end) { if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE)) continue; __reg_op(bitmap, pos, order, REG_OP_ALLOC); return pos; } return -ENOMEM; } EXPORT_SYMBOL(bitmap_find_free_region); /** * bitmap_release_region - release allocated bitmap region * @bitmap: array of unsigned longs corresponding to the bitmap * @pos: beginning of bit region to release * @order: region size (log base 2 of number of bits) to release * * This is the complement to __bitmap_find_free_region() and releases * the found region (by clearing it in the bitmap). * * No return value. */ void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) { __reg_op(bitmap, pos, order, REG_OP_RELEASE); } EXPORT_SYMBOL(bitmap_release_region); /** * bitmap_allocate_region - allocate bitmap region * @bitmap: array of unsigned longs corresponding to the bitmap * @pos: beginning of bit region to allocate * @order: region size (log base 2 of number of bits) to allocate * * Allocate (set bits in) a specified region of a bitmap. * * Return 0 on success, or %-EBUSY if specified region wasn't * free (not all bits were zero). */ int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) { if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE)) return -EBUSY; return __reg_op(bitmap, pos, order, REG_OP_ALLOC); } EXPORT_SYMBOL(bitmap_allocate_region); /** * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order. * @dst: destination buffer * @src: bitmap to copy * @nbits: number of bits in the bitmap * * Require nbits % BITS_PER_LONG == 0. */ #ifdef __BIG_ENDIAN void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int i; for (i = 0; i < nbits/BITS_PER_LONG; i++) { if (BITS_PER_LONG == 64) dst[i] = cpu_to_le64(src[i]); else dst[i] = cpu_to_le32(src[i]); } } EXPORT_SYMBOL(bitmap_copy_le); #endif unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags) { return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags); } EXPORT_SYMBOL(bitmap_alloc); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) { return bitmap_alloc(nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL(bitmap_zalloc); void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); } EXPORT_SYMBOL(bitmap_free); static void devm_bitmap_free(void *data) { unsigned long *bitmap = data; bitmap_free(bitmap); } unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags) { unsigned long *bitmap; int ret; bitmap = bitmap_alloc(nbits, flags); if (!bitmap) return NULL; ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); if (ret) return NULL; return bitmap; } EXPORT_SYMBOL_GPL(devm_bitmap_alloc); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags) { return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { bitmap[i/2] = (unsigned long) buf[i]; if (++i < halfwords) bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } /* Clear tail bits in last word beyond nbits. */ if (nbits % BITS_PER_LONG) bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr32); /** * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits * @buf: array of u32 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { buf[i] = (u32) (bitmap[i/2] & UINT_MAX); if (++i < halfwords) buf[i] = (u32) (bitmap[i/2] >> 32); } /* Clear tail bits in last element of array beyond nbits. */ if (nbits % BITS_PER_LONG) buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } EXPORT_SYMBOL(bitmap_to_arr32); #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 | /* SPDX-License-Identifier: GPL-2.0 */ /* * net/dst.h Protocol independent destination cache definitions. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * */ #ifndef _NET_DST_H #define _NET_DST_H #include <net/dst_ops.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> #include <linux/bug.h> #include <linux/jiffies.h> #include <linux/refcount.h> #include <net/neighbour.h> #include <asm/processor.h> #include <linux/indirect_call_wrapper.h> struct sk_buff; struct dst_entry { struct net_device *dev; struct dst_ops *ops; unsigned long _metrics; unsigned long expires; #ifdef CONFIG_XFRM struct xfrm_state *xfrm; #else void *__pad1; #endif int (*input)(struct sk_buff *); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); unsigned short flags; #define DST_NOXFRM 0x0002 #define DST_NOPOLICY 0x0004 #define DST_NOCOUNT 0x0008 #define DST_FAKE_RTABLE 0x0010 #define DST_XFRM_TUNNEL 0x0020 #define DST_XFRM_QUEUE 0x0040 #define DST_METADATA 0x0080 /* A non-zero value of dst->obsolete forces by-hand validation * of the route entry. Positive values are set by the generic * dst layer to indicate that the entry has been forcefully * destroyed. * * Negative values are used by the implementation layer code to * force invocation of the dst_ops->check() method. */ short obsolete; #define DST_OBSOLETE_NONE 0 #define DST_OBSOLETE_DEAD 2 #define DST_OBSOLETE_FORCE_CHK -1 #define DST_OBSOLETE_KILL -2 unsigned short header_len; /* more space at head required */ unsigned short trailer_len; /* space to reserve at tail */ /* * __refcnt wants to be on a different cache line from * input/output/ops or performance tanks badly */ #ifdef CONFIG_64BIT atomic_t __refcnt; /* 64-bit offset 64 */ #endif int __use; unsigned long lastuse; struct lwtunnel_state *lwtstate; struct rcu_head rcu_head; short error; short __pad; __u32 tclassid; #ifndef CONFIG_64BIT atomic_t __refcnt; /* 32-bit offset 64 */ #endif }; struct dst_metrics { u32 metrics[RTAX_MAX]; refcount_t refcnt; } __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ extern const struct dst_metrics dst_default_metrics; u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); #define DST_METRICS_READ_ONLY 0x1UL #define DST_METRICS_REFCOUNTED 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) #define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) static inline bool dst_metrics_read_only(const struct dst_entry *dst) { return dst->_metrics & DST_METRICS_READ_ONLY; } void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); static inline void dst_destroy_metrics_generic(struct dst_entry *dst) { unsigned long val = dst->_metrics; if (!(val & DST_METRICS_READ_ONLY)) __dst_destroy_metrics_generic(dst, val); } static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) { unsigned long p = dst->_metrics; BUG_ON(!p); if (p & DST_METRICS_READ_ONLY) return dst->ops->cow_metrics(dst, p); return __DST_METRICS_PTR(p); } /* This may only be invoked before the entry has reached global * visibility. */ static inline void dst_init_metrics(struct dst_entry *dst, const u32 *src_metrics, bool read_only) { dst->_metrics = ((unsigned long) src_metrics) | (read_only ? DST_METRICS_READ_ONLY : 0); } static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) { u32 *dst_metrics = dst_metrics_write_ptr(dest); if (dst_metrics) { u32 *src_metrics = DST_METRICS_PTR(src); memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); } } static inline u32 *dst_metrics_ptr(struct dst_entry *dst) { return DST_METRICS_PTR(dst); } static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { u32 *p = DST_METRICS_PTR(dst); return p[metric-1]; } static inline u32 dst_metric(const struct dst_entry *dst, const int metric) { WARN_ON_ONCE(metric == RTAX_HOPLIMIT || metric == RTAX_ADVMSS || metric == RTAX_MTU); return dst_metric_raw(dst, metric); } static inline u32 dst_metric_advmss(const struct dst_entry *dst) { u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS); if (!advmss) advmss = dst->ops->default_advmss(dst); return advmss; } static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { u32 *p = dst_metrics_write_ptr(dst); if (p) p[metric-1] = val; } /* Kernel-internal feature bits that are unallocated in user space. */ #define DST_FEATURE_ECN_CA (1U << 31) #define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) #define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) static inline u32 dst_feature(const struct dst_entry *dst, u32 feature) { return dst_metric(dst, RTAX_FEATURES) & feature; } static inline u32 dst_mtu(const struct dst_entry *dst) { return dst->ops->mtu(dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric) { return msecs_to_jiffies(dst_metric(dst, metric)); } static inline u32 dst_allfrag(const struct dst_entry *dst) { int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); return ret; } static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) { /* * If your kernel compilation stops here, please check * the placement of __refcnt in struct dst_entry */ BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63); WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); } static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) { if (unlikely(time != dst->lastuse)) { dst->__use++; dst->lastuse = time; } } static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) dst_hold(dst); return dst; } void dst_release(struct dst_entry *dst); void dst_release_immediate(struct dst_entry *dst); static inline void refdst_drop(unsigned long refdst) { if (!(refdst & SKB_DST_NOREF)) dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK)); } /** * skb_dst_drop - drops skb dst * @skb: buffer * * Drops dst reference count if a reference was taken. */ static inline void skb_dst_drop(struct sk_buff *skb) { if (skb->_skb_refdst) { refdst_drop(skb->_skb_refdst); skb->_skb_refdst = 0UL; } } static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); } static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb) { __skb_dst_copy(nskb, oskb->_skb_refdst); } /** * dst_hold_safe - Take a reference on a dst if possible * @dst: pointer to dst entry * * This helper returns false if it could not safely * take a reference on a dst. */ static inline bool dst_hold_safe(struct dst_entry *dst) { return atomic_inc_not_zero(&dst->__refcnt); } /** * skb_dst_force - makes sure skb dst is refcounted * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. * Returns true if dst is refcounted. */ static inline bool skb_dst_force(struct sk_buff *skb) { if (skb_dst_is_noref(skb)) { struct dst_entry *dst = skb_dst(skb); WARN_ON(!rcu_read_lock_held()); if (!dst_hold_safe(dst)) dst = NULL; skb->_skb_refdst = (unsigned long)dst; } return skb->_skb_refdst != 0UL; } /** * __skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups. (no accounting done) */ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { skb->dev = dev; /* * Clear hash so that we can recalulate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ skb_clear_hash_if_not_l4(skb); skb_set_queue_mapping(skb, 0); skb_scrub_packet(skb, !net_eq(net, dev_net(dev))); } /** * skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups, and perform accounting. * Note: this accounting is not SMP safe. */ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { DEV_STATS_INC(dev, rx_packets); DEV_STATS_ADD(dev, rx_bytes, skb->len); __skb_tunnel_rx(skb, dev, net); } static inline u32 dst_tclassid(const struct sk_buff *skb) { #ifdef CONFIG_IP_ROUTE_CLASSID const struct dst_entry *dst; dst = skb_dst(skb); if (dst) return dst->tclassid; #endif return 0; } int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { return dst_discard_out(&init_net, skb->sk, skb); } void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags); void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags); struct dst_entry *dst_destroy(struct dst_entry *dst); void dst_dev_put(struct dst_entry *dst); static inline void dst_confirm(struct dst_entry *dst) { } static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) { struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr); return IS_ERR(n) ? NULL : n; } static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { struct neighbour *n = NULL; /* The packets from tunnel devices (eg bareudp) may have only * metadata in the dst pointer of skb. Hence a pointer check of * neigh_lookup is needed. */ if (dst->ops->neigh_lookup) n = dst->ops->neigh_lookup(dst, skb, NULL); return IS_ERR(n) ? NULL : n; } static inline void dst_confirm_neigh(const struct dst_entry *dst, const void *daddr) { if (dst->ops->confirm_neigh) dst->ops->confirm_neigh(dst, daddr); } static inline void dst_link_failure(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops && dst->ops->link_failure) dst->ops->link_failure(skb); } static inline void dst_set_expires(struct dst_entry *dst, int timeout) { unsigned long expires = jiffies + timeout; if (expires == 0) expires = 1; if (dst->expires == 0 || time_before(expires, dst->expires)) dst->expires = expires; } static inline unsigned int dst_dev_overhead(struct dst_entry *dst, struct sk_buff *skb) { if (likely(dst)) return LL_RESERVED_SPACE(dst->dev); return skb->mac_len; } INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, struct sk_buff *)); /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return INDIRECT_CALL_INET(skb_dst(skb)->output, ip6_output, ip_output, net, sk, skb); } INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { return INDIRECT_CALL_INET(skb_dst(skb)->input, ip6_input, ip_local_deliver, skb); } static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) { if (dst->obsolete) dst = dst->ops->check(dst, cookie); return dst; } /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, XFRM_LOOKUP_QUEUE = 1 << 1, XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, }; struct flowi; #ifndef CONFIG_XFRM static inline struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return dst_orig; } static inline struct dst_entry * xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { return dst_orig; } static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return dst_orig; } static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { return NULL; } #else struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id); struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); /* skb attached with this dst needs transformation if dst->xfrm is valid */ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { return dst->xfrm; } #endif static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, true); } /* update dst pmtu but not do neighbor confirm */ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); unsigned int dst_blackhole_mtu(const struct dst_entry *dst); #endif /* _NET_DST_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Integer base 2 logarithm calculation * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_LOG2_H #define _LINUX_LOG2_H #include <linux/types.h> #include <linux/bitops.h> /* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() * - the arch is not required to handle n==0 if implementing the fallback */ #ifndef CONFIG_ARCH_HAS_ILOG2_U32 static inline __attribute__((const)) int __ilog2_u32(u32 n) { return fls(n) - 1; } #endif #ifndef CONFIG_ARCH_HAS_ILOG2_U64 static inline __attribute__((const)) int __ilog2_u64(u64 n) { return fls64(n) - 1; } #endif /** * is_power_of_2() - check if a value is a power of two * @n: the value to check * * Determine whether some value is a power of two, where zero is * *not* considered a power of two. * Return: true if @n is a power of 2, otherwise false. */ static inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); } /** * __roundup_pow_of_two() - round up to nearest power of two * @n: value to round up */ static inline __attribute__((const)) unsigned long __roundup_pow_of_two(unsigned long n) { return 1UL << fls_long(n - 1); } /** * __rounddown_pow_of_two() - round down to nearest power of two * @n: value to round down */ static inline __attribute__((const)) unsigned long __rounddown_pow_of_two(unsigned long n) { return 1UL << (fls_long(n) - 1); } /** * const_ilog2 - log base 2 of 32-bit or a 64-bit constant unsigned value * @n: parameter * * Use this where sparse expects a true constant expression, e.g. for array * indices. */ #define const_ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ (n) & (1ULL << 60) ? 60 : \ (n) & (1ULL << 59) ? 59 : \ (n) & (1ULL << 58) ? 58 : \ (n) & (1ULL << 57) ? 57 : \ (n) & (1ULL << 56) ? 56 : \ (n) & (1ULL << 55) ? 55 : \ (n) & (1ULL << 54) ? 54 : \ (n) & (1ULL << 53) ? 53 : \ (n) & (1ULL << 52) ? 52 : \ (n) & (1ULL << 51) ? 51 : \ (n) & (1ULL << 50) ? 50 : \ (n) & (1ULL << 49) ? 49 : \ (n) & (1ULL << 48) ? 48 : \ (n) & (1ULL << 47) ? 47 : \ (n) & (1ULL << 46) ? 46 : \ (n) & (1ULL << 45) ? 45 : \ (n) & (1ULL << 44) ? 44 : \ (n) & (1ULL << 43) ? 43 : \ (n) & (1ULL << 42) ? 42 : \ (n) & (1ULL << 41) ? 41 : \ (n) & (1ULL << 40) ? 40 : \ (n) & (1ULL << 39) ? 39 : \ (n) & (1ULL << 38) ? 38 : \ (n) & (1ULL << 37) ? 37 : \ (n) & (1ULL << 36) ? 36 : \ (n) & (1ULL << 35) ? 35 : \ (n) & (1ULL << 34) ? 34 : \ (n) & (1ULL << 33) ? 33 : \ (n) & (1ULL << 32) ? 32 : \ (n) & (1ULL << 31) ? 31 : \ (n) & (1ULL << 30) ? 30 : \ (n) & (1ULL << 29) ? 29 : \ (n) & (1ULL << 28) ? 28 : \ (n) & (1ULL << 27) ? 27 : \ (n) & (1ULL << 26) ? 26 : \ (n) & (1ULL << 25) ? 25 : \ (n) & (1ULL << 24) ? 24 : \ (n) & (1ULL << 23) ? 23 : \ (n) & (1ULL << 22) ? 22 : \ (n) & (1ULL << 21) ? 21 : \ (n) & (1ULL << 20) ? 20 : \ (n) & (1ULL << 19) ? 19 : \ (n) & (1ULL << 18) ? 18 : \ (n) & (1ULL << 17) ? 17 : \ (n) & (1ULL << 16) ? 16 : \ (n) & (1ULL << 15) ? 15 : \ (n) & (1ULL << 14) ? 14 : \ (n) & (1ULL << 13) ? 13 : \ (n) & (1ULL << 12) ? 12 : \ (n) & (1ULL << 11) ? 11 : \ (n) & (1ULL << 10) ? 10 : \ (n) & (1ULL << 9) ? 9 : \ (n) & (1ULL << 8) ? 8 : \ (n) & (1ULL << 7) ? 7 : \ (n) & (1ULL << 6) ? 6 : \ (n) & (1ULL << 5) ? 5 : \ (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ 1) : \ -1) /** * ilog2 - log base 2 of 32-bit or a 64-bit unsigned value * @n: parameter * * constant-capable log of base 2 calculation * - this can be used to initialise global variables from constant data, hence * the massive ternary operator construction * * selects the appropriately-sized optimised version depending on sizeof(n) */ #define ilog2(n) \ ( \ __builtin_constant_p(n) ? \ const_ilog2(n) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ ) /** * roundup_pow_of_two - round the given value up to nearest power of two * @n: parameter * * round the given value up to the nearest power of two * - the result is undefined when n == 0 * - this can be used to initialise global variables from constant data */ #define roundup_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 1) ? 1 : \ (1UL << (ilog2((n) - 1) + 1)) \ ) : \ __roundup_pow_of_two(n) \ ) /** * rounddown_pow_of_two - round the given value down to nearest power of two * @n: parameter * * round the given value down to the nearest power of two * - the result is undefined when n == 0 * - this can be used to initialise global variables from constant data */ #define rounddown_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ (1UL << ilog2(n))) : \ __rounddown_pow_of_two(n) \ ) static inline __attribute_const__ int __order_base_2(unsigned long n) { return n > 1 ? ilog2(n - 1) + 1 : 0; } /** * order_base_2 - calculate the (rounded up) base 2 order of the argument * @n: parameter * * The first few values calculated by this routine: * ob2(0) = 0 * ob2(1) = 0 * ob2(2) = 1 * ob2(3) = 2 * ob2(4) = 2 * ob2(5) = 3 * ... and so on. */ #define order_base_2(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 0 || (n) == 1) ? 0 : \ ilog2((n) - 1) + 1) : \ __order_base_2(n) \ ) static inline __attribute__((const)) int __bits_per(unsigned long n) { if (n < 2) return 1; if (is_power_of_2(n)) return order_base_2(n) + 1; return order_base_2(n); } /** * bits_per - calculate the number of bits required for the argument * @n: parameter * * This is constant-capable and can be used for compile time * initializations, e.g bitfields. * * The first few values calculated by this routine: * bf(0) = 1 * bf(1) = 1 * bf(2) = 2 * bf(3) = 2 * bf(4) = 3 * ... and so on. */ #define bits_per(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 0 || (n) == 1) \ ? 1 : ilog2(n) + 1 \ ) : \ __bits_per(n) \ ) #endif /* _LINUX_LOG2_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/drivers/char/serial_core.h * * Copyright (C) 2000 Deep Blue Solutions Ltd. */ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> #include <linux/circ_buf.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/sysrq.h> #include <uapi/linux/serial_core.h> #ifdef CONFIG_SERIAL_CORE_CONSOLE #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else #define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; struct serial_struct; struct device; struct gpio_desc; /* * This structure describes all the operations that can be done on the * physical hardware. See Documentation/driver-api/serial/driver.rst for details. */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int mctrl); unsigned int (*get_mctrl)(struct uart_port *); void (*stop_tx)(struct uart_port *); void (*start_tx)(struct uart_port *); void (*throttle)(struct uart_port *); void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); /* * Return a string describing the type of the port */ const char *(*type)(struct uart_port *); /* * Release IO and memory resources used by the port. * This includes iounmap if necessary. */ void (*release_port)(struct uart_port *); /* * Request IO and memory resources used by the port. * This includes iomapping the port if necessary. */ int (*request_port)(struct uart_port *); void (*config_port)(struct uart_port *, int); int (*verify_port)(struct uart_port *, struct serial_struct *); int (*ioctl)(struct uart_port *, unsigned int, unsigned long); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct uart_port *); void (*poll_put_char)(struct uart_port *, unsigned char); int (*poll_get_char)(struct uart_port *); #endif }; #define NO_POLL_CHAR 0x00ff0000 #define UART_CONFIG_TYPE (1 << 0) #define UART_CONFIG_IRQ (1 << 1) struct uart_icount { __u32 cts; __u32 dsr; __u32 rng; __u32 dcd; __u32 rx; __u32 tx; __u32 frame; __u32 overrun; __u32 parity; __u32 brk; __u32 buf_overrun; }; typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t; struct uart_port { spinlock_t lock; /* port lock */ unsigned long iobase; /* in/out[bwl] */ unsigned char __iomem *membase; /* read/write[bwl] */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); unsigned int (*get_divisor)(struct uart_port *, unsigned int baud, unsigned int *frac); void (*set_divisor)(struct uart_port *, unsigned int baud, unsigned int quot, unsigned int quot_frac); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); void (*unthrottle)(struct uart_port *port); int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int old); void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct serial_rs485 *rs485); int (*iso7816_config)(struct uart_port *, struct serial_iso7816 *iso7816); unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ unsigned int fifosize; /* tx fifo size */ unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char iotype; /* io access style */ unsigned char quirks; /* internal quirks */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ #define UPIO_MEM (SERIAL_IO_MEM) /* driver-specific */ #define UPIO_MEM32 (SERIAL_IO_MEM32) /* 32b little endian */ #define UPIO_AU (SERIAL_IO_AU) /* Au1x00 and RT288x type IO */ #define UPIO_TSI (SERIAL_IO_TSI) /* Tsi108/109 type IO */ #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ /* quirks must be updated while holding port mutex */ #define UPQ_NO_TXEN_TEST BIT(0) unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ /* flags must be updated while holding port mutex */ upf_t flags; /* * These flags must be equivalent to the flags defined in * include/uapi/linux/tty_flags.h which are the userspace definitions * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ #define UPF_FOURPORT ((__force upf_t) ASYNC_FOURPORT /* 1 */ ) #define UPF_SAK ((__force upf_t) ASYNC_SAK /* 2 */ ) #define UPF_SPD_HI ((__force upf_t) ASYNC_SPD_HI /* 4 */ ) #define UPF_SPD_VHI ((__force upf_t) ASYNC_SPD_VHI /* 5 */ ) #define UPF_SPD_CUST ((__force upf_t) ASYNC_SPD_CUST /* 0x0030 */ ) #define UPF_SPD_WARP ((__force upf_t) ASYNC_SPD_WARP /* 0x1010 */ ) #define UPF_SPD_MASK ((__force upf_t) ASYNC_SPD_MASK /* 0x1030 */ ) #define UPF_SKIP_TEST ((__force upf_t) ASYNC_SKIP_TEST /* 6 */ ) #define UPF_AUTO_IRQ ((__force upf_t) ASYNC_AUTO_IRQ /* 7 */ ) #define UPF_HARDPPS_CD ((__force upf_t) ASYNC_HARDPPS_CD /* 11 */ ) #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) #define UPF_NO_THRE_TEST ((__force upf_t) (1 << 19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) (1 << 20)) #define UPF_AUTO_RTS ((__force upf_t) (1 << 21)) #define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ #define UPF_SOFT_FLOW ((__force upf_t) (1 << 22)) #define UPF_CONS_FLOW ((__force upf_t) (1 << 23)) #define UPF_SHARE_IRQ ((__force upf_t) (1 << 24)) #define UPF_EXAR_EFR ((__force upf_t) (1 << 25)) #define UPF_BUG_THRE ((__force upf_t) (1 << 26)) /* The exact UART type is known and should not be probed. */ #define UPF_FIXED_TYPE ((__force upf_t) (1 << 27)) #define UPF_BOOT_AUTOCONF ((__force upf_t) (1 << 28)) #define UPF_FIXED_PORT ((__force upf_t) (1 << 29)) #define UPF_DEAD ((__force upf_t) (1 << 30)) #define UPF_IOREMAP ((__force upf_t) (1 << 31)) #define UPF_FULL_PROBE ((__force upf_t) (1ULL << 32)) #define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK) #define UPF_USR_MASK ((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY)) #if __UPF_CHANGE_MASK > ASYNC_FLAGS #error Change mask not equivalent to userspace-visible bit defines #endif /* * Must hold termios_rwsem, port mutex and port lock to change; * can hold any one lock to read. */ upstat_t status; #define UPSTAT_CTS_ENABLE ((__force upstat_t) (1 << 0)) #define UPSTAT_DCD_ENABLE ((__force upstat_t) (1 << 1)) #define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) #define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) int hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int timeout; /* character-based timeout */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; unsigned int line; /* port index */ unsigned int minor; resource_size_t mapbase; /* for ioremap */ resource_size_t mapsize; struct device *dev; /* parent device */ unsigned long sysrq; /* sysrq timeout */ unsigned int sysrq_ch; /* char for sysrq */ unsigned char has_sysrq; unsigned char sysrq_seq; /* index in sysrq_toggle_seq */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; const struct serial_rs485 *rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); } /** * uart_port_lock_irq - Lock the UART port and disable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); } /** * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage */ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); } /** * uart_port_trylock - Try to lock the UART port * @up: Pointer to UART port structure * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock(struct uart_port *up) { return spin_trylock(&up->lock); } /** * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { return spin_trylock_irqsave(&up->lock, *flags); } /** * uart_port_unlock - Unlock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_unlock(struct uart_port *up) { spin_unlock(&up->lock); } /** * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_unlock_irq(struct uart_port *up) { spin_unlock_irq(&up->lock); } /** * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts * @up: Pointer to UART port structure * @flags: The saved interrupt flags for restore */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { spin_unlock_irqrestore(&up->lock, flags); } static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); } static inline void serial_port_out(struct uart_port *up, int offset, int value) { up->serial_out(up, offset, value); } /** * enum uart_pm_state - power states for UARTs * @UART_PM_STATE_ON: UART is powered, up and operational * @UART_PM_STATE_OFF: UART is powered off * @UART_PM_STATE_UNDEFINED: sentinel */ enum uart_pm_state { UART_PM_STATE_ON = 0, UART_PM_STATE_OFF = 3, /* number taken from ACPI */ UART_PM_STATE_UNDEFINED, }; /* * This is the state information which is persistent across opens. */ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; struct circ_buf xmit; atomic_t refcount; wait_queue_head_t remove_wait; struct uart_port *uart_port; }; #define UART_XMIT_SIZE PAGE_SIZE /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 /** * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars * @up: uart_port structure describing the port * @chars: number of characters sent * * This function advances the tail of circular xmit buffer by the number of * @chars transmitted and handles accounting of transmitted bytes (into * @up's icount.tx). */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { struct circ_buf *xmit = &up->state->xmit; xmit->tail = (xmit->tail + chars) & (UART_XMIT_SIZE - 1); up->icount.tx += chars; } struct module; struct tty_driver; struct uart_driver { struct module *owner; const char *driver_name; const char *dev_name; int major; int minor; int nr; struct console *cons; /* * these are private; the low level driver should not * touch these; they should be initialised to NULL */ struct uart_state *state; struct tty_driver *tty_driver; }; void uart_write_wakeup(struct uart_port *port); /* * Baud rate helpers. */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); /* Base timer interval for polling */ static inline int uart_poll_timeout(struct uart_port *port) { int timeout = port->timeout; return timeout > 6 ? (timeout / 2 - 2) : 1; } /* * Console helpers. */ struct earlycon_device { struct console *con; struct uart_port port; char options[16]; /* e.g., 115200n8 */ unsigned int baud; }; struct earlycon_id { char name[15]; char name_term; /* In case compiler didn't '\0' term name */ char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); }; extern const struct earlycon_id *__earlycon_table[]; extern const struct earlycon_id *__earlycon_table_end[]; #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) #define EARLYCON_USED_OR_UNUSED __used #else #define EARLYCON_USED_OR_UNUSED __maybe_unused #endif #define _OF_EARLYCON_DECLARE(_name, compat, fn, unique_id) \ static const struct earlycon_id unique_id \ EARLYCON_USED_OR_UNUSED __initconst \ = { .name = __stringify(_name), \ .compatible = compat, \ .setup = fn }; \ static const struct earlycon_id EARLYCON_USED_OR_UNUSED \ __section("__earlycon_table") \ * const __PASTE(__p, unique_id) = &unique_id #define OF_EARLYCON_DECLARE(_name, compat, fn) \ _OF_EARLYCON_DECLARE(_name, compat, fn, \ __UNIQUE_ID(__earlycon_##_name)) #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) extern int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; int setup_earlycon(char *buf); #else static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif static inline bool uart_console_enabled(struct uart_port *port) { return uart_console(port) && (port->cons->flags & CON_ENABLED); } struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options); void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow); int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow); struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, int)); /* * Port/driver registration/removal */ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); int uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); int uart_match_port(struct uart_port *port1, struct uart_port *port2); /* * Power Management */ int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); #define uart_circ_empty(circ) ((circ)->head == (circ)->tail) #define uart_circ_clear(circ) ((circ)->head = (circ)->tail = 0) #define uart_circ_chars_pending(circ) \ (CIRC_CNT((circ)->head, (circ)->tail, UART_XMIT_SIZE)) #define uart_circ_chars_free(circ) \ (CIRC_SPACE((circ)->head, (circ)->tail, UART_XMIT_SIZE)) static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; if ((tty && tty->stopped) || port->hw_stopped) return 1; return 0; } static inline bool uart_cts_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_CTS_ENABLE); } static inline bool uart_softcts_mode(struct uart_port *uport) { upstat_t mask = UPSTAT_CTS_ENABLE | UPSTAT_AUTOCTS; return ((uport->status & mask) == UPSTAT_CTS_ENABLE); } /* * The following are helper functions for the low level drivers. */ extern void uart_handle_dcd_change(struct uart_port *uport, unsigned int status); extern void uart_handle_cts_change(struct uart_port *uport, unsigned int status); extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); void uart_xchar_out(struct uart_port *uport, int offset); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch); static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { handle_sysrq(ch); port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { port->sysrq_ch = ch; port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) { int sysrq_ch; if (!port->has_sysrq) { spin_unlock_irqrestore(&port->lock, irqflags); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; spin_unlock_irqrestore(&port->lock, irqflags); if (sysrq_ch) handle_sysrq(sysrq_ch); } #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) { return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) { spin_unlock_irqrestore(&port->lock, irqflags); } #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* * We do the SysRQ and SAK checking like this... */ static inline int uart_handle_break(struct uart_port *port) { struct uart_state *state = port->state; if (port->handle_break) port->handle_break(port); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL if (port->has_sysrq && uart_console(port)) { if (!port->sysrq) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return 1; } port->sysrq = 0; } #endif if (port->flags & UPF_SAK) do_SAK(state->port.tty); return 0; } /* * UART_ENABLE_MS - determine if port should enable modem status irqs */ #define UART_ENABLE_MS(port,cflag) ((port)->flags & UPF_HARDPPS_CD || \ (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/lcm.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* the slots are sorted by free bytes left, 1-31 bytes share the same slot */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; EXPORT_SYMBOL_GPL(pcpu_base_addr); static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* chunks which need their map areas extended, protected by pcpu_lock */ static LIST_HEAD(pcpu_map_extend_chunks); /* * The number of empty populated pages by chunk type, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES]; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_nr_slots - 1; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->index = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->index; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { struct list_head *pcpu_slot; pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); if (move_front) list_move(&chunk->list, &pcpu_slot[slot]); else list_move_tail(&chunk->list, &pcpu_slot[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk) pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int rs, re, start; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ bitmap_for_each_clear_region(alloc_map, rs, re, start, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, rs, re); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int page_start, page_end, rs, re; page_start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); page_end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); rs = page_start; bitmap_next_clear_region(chunk->populated, &rs, &re, page_end); if (rs >= page_end) return true; *next_off = re * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * Check to see if the allocation can fit in the chunk's contig hint. * This is an optimization to prevent scanning by assuming if it * cannot fit in the global hint, there is memory pressure and creating * a new chunk would happen soon. */ bit_off = ALIGN(chunk_md->contig_hint_start, align) - chunk_md->contig_hint_start; if (bit_off + alloc_bits > chunk_md->contig_hint) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr, lcm_align; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; /* * Align the end of the region with the LCM of PAGE_SIZE and * PCPU_BITMAP_BLOCK_SIZE. One of these constants is a multiple of * the other. */ lcm_align = lcm(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE); region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->alloc_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->bound_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->md_blocks) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); #ifdef CONFIG_MEMCG_KMEM /* first chunk isn't memcg-aware */ chunk->obj_cgroups = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef CONFIG_MEMCG_KMEM if (pcpu_is_memcg_chunk(type)) { chunk->obj_cgroups = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct obj_cgroup *), gfp); if (!chunk->obj_cgroups) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef CONFIG_MEMCG_KMEM objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef CONFIG_MEMCG_KMEM pcpu_mem_free(chunk->obj_cgroups); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. * * If this is @for_alloc, do not increment pcpu_nr_empty_pop_pages because it * is to serve an allocation in that area. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG_KMEM static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT)) return PCPU_CHUNK_ROOT; objcg = get_obj_cgroup_from_current(); if (!objcg) return PCPU_CHUNK_ROOT; if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) { obj_cgroup_put(objcg); return PCPU_FAIL_ALLOC; } *objcgp = objcg; return PCPU_CHUNK_MEMCG; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (chunk) { chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, size * num_possible_cpus()); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, size * num_possible_cpus()); obj_cgroup_put(objcg); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))) return; objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; obj_cgroup_uncharge(objcg, size * num_possible_cpus()); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -(size * num_possible_cpus())); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG_KMEM */ static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return PCPU_CHUNK_ROOT; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG_KMEM */ /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; enum pcpu_chunk_type type; struct list_head *pcpu_slot; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg); if (unlikely(type == PCPU_FAIL_ALLOC)) return NULL; pcpu_slot = pcpu_chunk_list(type); if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; } } spin_unlock_irqrestore(&pcpu_lock, flags); /* * No space left. Create a new chunk. We don't want multiple * tasks to create chunks simultaneously. Serialize and create iff * there's still no empty chunk after grabbing the mutex. */ if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { chunk = pcpu_create_chunk(type, pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_start, page_end, rs, re; page_start = PFN_DOWN(off); page_end = PFN_UP(off + size); bitmap_for_each_clear_region(chunk->populated, rs, re, page_start, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(reserved, is_atomic, size, align, chunk->base_addr, off, ptr); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (!is_atomic && do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n"); } if (is_atomic) { /* see the flag handling in pcpu_blance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } /** * __alloc_percpu_gfp - allocate dynamic percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @gfp: allocation flags * * Allocate zero-filled percpu area of @size bytes aligned at @align. If * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can * be called from any context but is a lot more likely to fail. If @gfp * has __GFP_NOWARN then no warning will be triggered on invalid or failed * allocation requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) { return pcpu_alloc(size, align, false, gfp); } EXPORT_SYMBOL_GPL(__alloc_percpu_gfp); /** * __alloc_percpu - allocate dynamic percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL). */ void __percpu *__alloc_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, false, GFP_KERNEL); } EXPORT_SYMBOL_GPL(__alloc_percpu); /** * __alloc_reserved_percpu - allocate reserved percpu area * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * * Allocate zero-filled percpu area of @size bytes aligned at @align * from reserved percpu area if arch has set it up; otherwise, * allocation is served from the same dynamic area. Might sleep. * Might trigger writeouts. * * CONTEXT: * Does GFP_KERNEL allocation. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, true, GFP_KERNEL); } /** * __pcpu_balance_workfn - manage the amount of free chunks and populated pages * @type: chunk type * * Reclaim all fully free chunks except for the first one. This is also * responsible for maintaining the pool of empty populated pages. However, * it is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. */ static void __pcpu_balance_workfn(enum pcpu_chunk_type type) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; LIST_HEAD(to_free); struct list_head *pcpu_slot = pcpu_chunk_list(type); struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1]; struct pcpu_chunk *chunk, *next; int slot, nr_to_pop, ret; /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; list_move(&chunk->list, &to_free); } spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; bitmap_for_each_set_region(chunk->populated, rs, re, 0, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages[type], 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; spin_lock_irq(&pcpu_lock); list_for_each_entry(chunk, &pcpu_slot[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } spin_unlock_irq(&pcpu_lock); if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ bitmap_for_each_clear_region(chunk->populated, rs, re, 0, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); if (!ret) { nr_to_pop -= nr; spin_lock_irq(&pcpu_lock); pcpu_chunk_populated(chunk, rs, rs + nr); spin_unlock_irq(&pcpu_lock); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ chunk = pcpu_create_chunk(type, gfp); if (chunk) { spin_lock_irq(&pcpu_lock); pcpu_chunk_relocate(chunk, -1); spin_unlock_irq(&pcpu_lock); goto retry_pop; } } mutex_unlock(&pcpu_alloc_mutex); } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * Call __pcpu_balance_workfn() for each chunk type. */ static void pcpu_balance_workfn(struct work_struct *work) { enum pcpu_chunk_type type; for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) __pcpu_balance_workfn(type); } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; struct list_head *pcpu_slot; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); spin_lock_irqsave(&pcpu_lock, flags); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; size = pcpu_free_area(chunk, off); pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); pcpu_memcg_free_hook(chunk, off, size); /* if there are more than one fully free chunks, wake up grim reaper */ if (chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) if (pos != chunk) { need_balance = true; break; } } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free_early(__pa(ai), ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; struct pcpu_chunk *chunk; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; int map_size; unsigned long tmp_addr; size_t alloc_size; enum pcpu_chunk_type type; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!ai->dyn_size); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_offsets) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_sizes) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_off) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size(chunk, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The additional last slot is for * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * PCPU_NR_CHUNK_TYPES, SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * PCPU_NR_CHUNK_TYPES); for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk. * If the reserved_size is non-zero, this initializes the reserved * chunk. If the reserved_size is zero, the reserved chunk is NULL * and the dynamic region is initialized here. The first chunk, * pcpu_first_chunk, will always point to the chunk that serves * the dynamic region. */ tmp_addr = (unsigned long)base_addr + static_size; map_size = ai->reserved_size ?: dyn_size; chunk = pcpu_alloc_first_chunk(tmp_addr, map_size); /* init dynamic chunk if necessary */ if (ai->reserved_size) { pcpu_reserved_chunk = chunk; tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; map_size = dyn_size; chunk = pcpu_alloc_first_chunk(tmp_addr, map_size); } /* link the first chunk in */ pcpu_first_chunk = chunk; pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; /* group cpus according to their proximity */ for_each_possible_cpu(cpu) { group = 0; next_group: for_each_possible_cpu(tcpu) { if (cpu == tcpu) break; if (group_map[tcpu] == group && cpu_distance_fn && (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE || cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) { group++; nr_groups = max(nr_groups, group + 1); goto next_group; } } group_map[cpu] = group; group_cnt[group]++; } /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @alloc_fn: function to allocate percpu page * @free_fn: function to free percpu page * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling @alloc_fn and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using @free_fn. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_free(ptr); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ free_fn(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); free_fn(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) free_fn(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free_early(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE * @free_fn: function to free percpu page, always called with PAGE_SIZE * @populate_pte_fn: function to populate pte * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); if (!pages) panic("%s: Failed to allocate %zu bytes\n", __func__, pages_size); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_free(ptr); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); /* * FIXME: Archs with virtual cache should flush local * cache for the linear mapping here - something * equivalent to flush_cache_vmap() on the local cpu. * flush_cache_vmap() can't be used as most supporting * data structures are not set up yet. */ /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free_early(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align) { return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS)); } static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { memblock_free_early(__pa(ptr), size); } void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_free(fc); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return pcpu_nr_populated * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/types.h> struct page; /** * struct bio_vec - a contiguous range of physical memory addresses * @bv_page: First page associated with the address range. * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: * * nth_page(@bv_page, n) == @bv_page + n * * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { unsigned int idx = iter->bi_idx; if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } iter->bi_size -= bytes; bytes += iter->bi_bvec_done; while (bytes && bytes >= bv[idx].bv_len) { bytes -= bv[idx].bv_len; idx++; } iter->bi_idx = idx; iter->bi_bvec_done = bytes; return true; } static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) { iter->bi_bvec_done = 0; iter->bi_idx++; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } #endif /* __LINUX_BVEC_ITER_H */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path = &file->f_path; /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } /* Simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { int ret; __u32 fsnotify_mask = 0; if (!(mask & (MAY_READ | MAY_OPEN))) return 0; if (mask & MAY_OPEN) { fsnotify_mask = FS_OPEN_PERM; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } } else if (mask & MAY_READ) { fsnotify_mask = FS_ACCESS_PERM; } return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * No idle tick implementation for low and high resolution timers * * Started by: Thomas Gleixner and Ingo Molnar */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/percpu.h> #include <linux/nmi.h> #include <linux/profile.h> #include <linux/sched/signal.h> #include <linux/sched/clock.h> #include <linux/sched/stat.h> #include <linux/sched/nohz.h> #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> #include <linux/context_tracking.h> #include <linux/mm.h> #include <asm/irq_regs.h> #include "tick-internal.h" #include <trace/events/timer.h> /* * Per-CPU nohz control structure */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) /* * The time, when the last jiffy update happened. Protected by jiffies_lock. */ static ktime_t last_jiffies_update; /* * Must be called with interrupts disabled ! */ static void tick_do_update_jiffies64(ktime_t now) { unsigned long ticks = 1; ktime_t delta; /* * Do a quick check without holding jiffies_lock. The READ_ONCE() * pairs with the update done later in this function. * * This is also an intentional data race which is even safe on * 32bit in theory. If there is a concurrent update then the check * might give a random answer. It does not matter because if it * returns then the concurrent update is already taking care, if it * falls through then it will pointlessly contend on jiffies_lock. * * Though there is one nasty case on 32bit due to store tearing of * the 64bit value. If the first 32bit store makes the quick check * return on all other CPUs and the writing CPU context gets * delayed to complete the second store (scheduled out on virt) * then jiffies can become stale for up to ~2^32 nanoseconds * without noticing. After that point all CPUs will wait for * jiffies lock. * * OTOH, this is not any different than the situation with NOHZ=off * where one CPU is responsible for updating jiffies and * timekeeping. If that CPU goes out for lunch then all other CPUs * will operate on stale jiffies until it decides to come back. */ if (ktime_before(now, READ_ONCE(tick_next_period))) return; /* Reevaluate with jiffies_lock held */ raw_spin_lock(&jiffies_lock); if (ktime_before(now, tick_next_period)) { raw_spin_unlock(&jiffies_lock); return; } write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, tick_next_period); if (unlikely(delta >= TICK_NSEC)) { /* Slow path for long idle sleep times */ s64 incr = TICK_NSEC; ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); } else { last_jiffies_update = ktime_add_ns(last_jiffies_update, TICK_NSEC); } do_timer(ticks); /* * Keep the tick_next_period variable up to date. WRITE_ONCE() * pairs with the READ_ONCE() in the lockless quick check above. */ WRITE_ONCE(tick_next_period, ktime_add_ns(last_jiffies_update, TICK_NSEC)); write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); update_wall_time(); } /* * Initialize and return retrieve the jiffies update. */ static ktime_t tick_init_jiffy_update(void) { ktime_t period; raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Did we start the jiffies update yet ? */ if (last_jiffies_update == 0) { u32 rem; /* * Ensure that the tick is aligned to a multiple of * TICK_NSEC. */ div_u64_rem(tick_next_period, TICK_NSEC, &rem); if (rem) tick_next_period += TICK_NSEC - rem; last_jiffies_update = tick_next_period; } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); return period; } #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int cpu = smp_processor_id(); #ifdef CONFIG_NO_HZ_COMMON /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * jiffies_lock. * * If nohz_full is enabled, this should not happen because the * tick_do_timer_cpu never relinquishes. */ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } #endif /* Check, if the jiffies need an update */ if (tick_do_timer_cpu == cpu) tick_do_update_jiffies64(now); /* * If jiffies update stalled for too long (timekeeper in stop_machine() * or VMEXIT'ed for several msecs), force an update. */ if (ts->last_tick_jiffies != jiffies) { ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } else { if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) { tick_do_update_jiffies64(now); ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } } if (ts->inidle) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { #ifdef CONFIG_NO_HZ_COMMON /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long * time. This happens on complete idle SMP systems while * waiting on the login prompt. We also increment the "start of * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too much ticks. */ if (ts->tick_stopped) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; /* * In case the current tick fired too early past its expected * expiration, make sure we don't bypass the next clock reprogramming * to the same deadline. */ ts->next_tick = 0; } #endif update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } #endif #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; bool tick_nohz_full_running; EXPORT_SYMBOL_GPL(tick_nohz_full_running); static atomic_t tick_dep_mask; static bool check_tick_dependency(atomic_t *dep) { int val = atomic_read(dep); if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); return true; } if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); return true; } if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); return true; } if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); return true; } if (val & TICK_DEP_MASK_RCU) { trace_tick_stop(0, TICK_DEP_MASK_RCU); return true; } if (val & TICK_DEP_MASK_RCU_EXP) { trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP); return true; } return false; } static bool can_stop_full_tick(int cpu, struct tick_sched *ts) { lockdep_assert_irqs_disabled(); if (unlikely(!cpu_online(cpu))) return false; if (check_tick_dependency(&tick_dep_mask)) return false; if (check_tick_dependency(&ts->tick_dep_mask)) return false; if (check_tick_dependency(¤t->tick_dep_mask)) return false; if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; return true; } static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { .func = nohz_full_kick_func, .flags = ATOMIC_INIT(IRQ_WORK_HARD_IRQ), }; /* * Kick this CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; irq_work_queue(this_cpu_ptr(&nohz_full_kick_work)); } /* * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ void tick_nohz_full_kick_cpu(int cpu) { if (!tick_nohz_full_cpu(cpu)) return; irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ static void tick_nohz_full_kick_all(void) { int cpu; if (!tick_nohz_full_running) return; preempt_disable(); for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { int prev; prev = atomic_fetch_or(BIT(bit), dep); if (!prev) tick_nohz_full_kick_all(); } /* * Set a global tick dependency. Used by perf events that rely on freq and * by unstable clock. */ void tick_nohz_dep_set(enum tick_dep_bits bit) { tick_nohz_dep_set_all(&tick_dep_mask, bit); } void tick_nohz_dep_clear(enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tick_dep_mask); } /* * Set per-CPU tick dependency. Used by scheduler and perf events in order to * manage events throttling. */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ if (cpu == smp_processor_id()) { tick_nohz_full_kick(); } else { /* Remote irq work not NMI-safe */ if (!WARN_ON_ONCE(in_nmi())) tick_nohz_full_kick_cpu(cpu); } preempt_enable(); } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); atomic_andnot(BIT(bit), &ts->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. RCU need this. Also posix CPU timers * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) { if (tsk == current) { preempt_disable(); tick_nohz_full_kick(); preempt_enable(); } else { /* * Some future tick_nohz_full_kick_task() * should optimize this. */ tick_nohz_full_kick_all(); } } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task); /* * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse * per process timers. */ void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit) { tick_nohz_dep_set_all(&sig->tick_dep_mask, bit); } void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: * perf events, posix CPU timers, ... */ void __tick_nohz_task_switch(void) { unsigned long flags; struct tick_sched *ts; local_irq_save(flags); if (!tick_nohz_full_cpu(smp_processor_id())) goto out; ts = this_cpu_ptr(&tick_cpu_sched); if (ts->tick_stopped) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } out: local_irq_restore(flags); } /* Get the boot-time nohz CPU list from the kernel parameters. */ void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; } bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The tick_do_timer_cpu CPU handles housekeeping duty (unbound * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) return false; return true; } static int tick_nohz_cpu_down(unsigned int cpu) { return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) { int cpu, ret; if (!tick_nohz_full_running) return; /* * Full dynticks uses irq work to drive the tick rescheduling on safe * locking contexts. But then we need irq work to raise its own * interrupts to avoid circular dependency on the tick */ if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); tick_nohz_full_running = false; return; } if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { pr_warn("NO_HZ: Clearing %d from nohz_full range " "for timekeeping\n", cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } } for_each_cpu(cpu, tick_nohz_full_mask) context_tracking_cpu_set(cpu); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "kernel/nohz:predown", NULL, tick_nohz_cpu_down); WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } #endif /* * NOHZ - aka dynamic tick functionality */ #ifdef CONFIG_NO_HZ_COMMON /* * NO HZ enabled ? */ bool tick_nohz_enabled __read_mostly = true; unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return ts->tick_stopped; } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); return ts->tick_stopped; } /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * * Called from interrupt entry when the CPU was idle * * In case the sched_tick was stopped on this CPU, we have to check if jiffies * must be updated. Otherwise an interrupt handler could use a stale jiffy * value. We do this unconditionally on any CPU, as we don't know whether the * CPU, which has the update task assigned is in a long sleep. */ static void tick_nohz_update_jiffies(ktime_t now) { unsigned long flags; __this_cpu_write(tick_cpu_sched.idle_waketime, now); local_irq_save(flags); tick_do_update_jiffies64(now); local_irq_restore(flags); touch_softlockup_watchdog_sched(); } /* * Updates the per-CPU time idle statistics counters */ static void update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time) { ktime_t delta; if (ts->idle_active) { delta = ktime_sub(now, ts->idle_entrytime); if (nr_iowait_cpu(cpu) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); else ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; } if (last_update_time) *last_update_time = ktime_to_us(now); } static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { update_ts_time_stats(smp_processor_id(), ts, now, NULL); ts->idle_active = 0; sched_clock_idle_wakeup_event(); } static void tick_nohz_start_idle(struct tick_sched *ts) { ts->idle_entrytime = ktime_get(); ts->idle_active = 1; sched_clock_idle_sleep_event(); } /** * get_cpu_idle_time_us - get the total idle time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative idle time (since boot) for a given * CPU, in microseconds. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * This function returns -1 if NOHZ is not enabled. */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t now, idle; if (!tick_nohz_active) return -1; now = ktime_get(); if (last_update_time) { update_ts_time_stats(cpu, ts, now, last_update_time); idle = ts->idle_sleeptime; } else { if (ts->idle_active && !nr_iowait_cpu(cpu)) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(ts->idle_sleeptime, delta); } else { idle = ts->idle_sleeptime; } } return ktime_to_us(idle); } EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); /** * get_cpu_iowait_time_us - get the total iowait time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative iowait time (since boot) for a given * CPU, in microseconds. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * This function returns -1 if NOHZ is not enabled. */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t now, iowait; if (!tick_nohz_active) return -1; now = ktime_get(); if (last_update_time) { update_ts_time_stats(cpu, ts, now, last_update_time); iowait = ts->iowait_sleeptime; } else { if (ts->idle_active && nr_iowait_cpu(cpu) > 0) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); iowait = ktime_add(ts->iowait_sleeptime, delta); } else { iowait = ts->iowait_sleeptime; } } return ktime_to_us(iowait); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); hrtimer_set_expires(&ts->sched_timer, ts->last_tick); /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); } else { tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } /* * Reset to make sure next tick stop doesn't get fooled by past * cached clock deadline. */ ts->next_tick = 0; } static inline bool local_timer_softirq_pending(void) { return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; unsigned long basejiff; unsigned int seq; /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work * requests it. * Aside of that check whether the local timer softirq is * pending. If so its a bad idea to call get_next_timer_interrupt() * because there is an already expired timer, so it will request * immeditate expiry, which rearms the hardware timer with a * minimal delta which brings us back to this place * immediately. Lather, rinse and repeat... */ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() || irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* * Get the next pending timer. If high resolution * timers are enabled this only takes the timer wheel * timers into account. If high resolution timers are * disabled this also looks at the next expiring * hrtimer. */ next_tmr = get_next_timer_interrupt(basejiff, basemono); ts->next_timer = next_tmr; /* Take the next rcu event into account */ next_tick = next_rcu < next_tmr ? next_rcu : next_tmr; } /* * If the tick is due in the next period, keep it ticking or * force prod the timer. */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* * Tell the timer code that the base is not idle, i.e. undo * the effect of get_next_timer_interrupt(): */ timer_clear_idle(); /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ if (!ts->tick_stopped) { ts->timer_expires = 0; goto out; } } /* * If this CPU is the one which had the do_timer() duty last, we limit * the sleep time to the timekeeping max_deferment value. * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); if (cpu != tick_do_timer_cpu && (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last)) delta = KTIME_MAX; /* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta; else expires = KTIME_MAX; ts->timer_expires = min_t(u64, expires, next_tick); out: return ts->timer_expires; } static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); u64 basemono = ts->timer_expires_base; u64 expires = ts->timer_expires; ktime_t tick = expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we * don't drop this here the jiffies might be stale and * do_timer() never invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ if (cpu == tick_do_timer_cpu) { tick_do_timer_cpu = TICK_DO_TIMER_NONE; ts->do_timer_last = 1; } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { ts->do_timer_last = 0; } /* Skip reprogram of event if its not changed */ if (ts->tick_stopped && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; WARN_ON_ONCE(1); printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick, dev->next_event, hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); } /* * nohz_stop_sched_tick can be called several times before * the nohz_restart_sched_tick is called. This happens when * interrupts arrive which do not cause a reschedule. In the * first call we save the current tick time, so we can restart * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; trace_tick_stop(1, TICK_DEP_MASK_NONE); } ts->next_tick = tick; /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); else tick_program_event(KTIME_MAX, 1); return; } if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, tick); tick_program_event(tick, 1); } } static void tick_nohz_retain_tick(struct tick_sched *ts) { ts->timer_expires_base = 0; } #ifdef CONFIG_NO_HZ_FULL static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); else tick_nohz_retain_tick(ts); } #endif /* CONFIG_NO_HZ_FULL */ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); /* * Clear the timer idle flag, so we avoid IPIs on remote queueing and * the clock forward checks in the enqueue path: */ timer_clear_idle(); calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* * Cancel the scheduled timer and restore the tick */ ts->tick_stopped = 0; ts->idle_exittime = now; tick_nohz_restart(ts, now); } static void tick_nohz_full_update_tick(struct tick_sched *ts) { #ifdef CONFIG_NO_HZ_FULL int cpu = smp_processor_id(); if (!tick_nohz_full_cpu(cpu)) return; if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) return; if (can_stop_full_tick(cpu, ts)) tick_nohz_stop_sched_tick(ts, cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, ktime_get()); #endif } static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { /* * If this CPU is offline and it is the one which updates * jiffies, then give up the assignment and let it be taken by * the CPU which runs the tick timer next. If we don't drop * this here the jiffies might be stale and do_timer() never * invoked. */ if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) tick_do_timer_cpu = TICK_DO_TIMER_NONE; /* * Make sure the CPU doesn't get fooled by obsolete tick * deadline if it comes back online later. */ ts->next_tick = 0; return false; } if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) return false; if (need_resched()) return false; if (unlikely(local_softirq_pending())) { static int ratelimit; if (ratelimit < 10 && (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n", (unsigned int) local_softirq_pending()); ratelimit++; } return false; } if (tick_nohz_full_enabled()) { /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ if (tick_do_timer_cpu == cpu) return false; /* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) return false; } return true; } static void __tick_nohz_idle_stop_tick(struct tick_sched *ts) { ktime_t expires; int cpu = smp_processor_id(); /* * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the * tick timer expiration time is known already. */ if (ts->timer_expires_base) expires = ts->timer_expires; else if (can_stop_idle_tick(cpu, ts)) expires = tick_nohz_next_event(ts, cpu); else return; ts->idle_calls++; if (expires > 0LL) { int was_stopped = ts->tick_stopped; tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; if (!was_stopped && ts->tick_stopped) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } } else { tick_nohz_retain_tick(ts); } } /** * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick */ void tick_nohz_idle_stop_tick(void) { __tick_nohz_idle_stop_tick(this_cpu_ptr(&tick_cpu_sched)); } void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); /* * Undo the effect of get_next_timer_interrupt() called from * tick_nohz_next_event(). */ timer_clear_idle(); } /** * tick_nohz_idle_enter - prepare for entering idle on the current CPU * * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { struct tick_sched *ts; lockdep_assert_irqs_enabled(); local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); WARN_ON_ONCE(ts->timer_expires_base); ts->inidle = 1; tick_nohz_start_idle(ts); local_irq_enable(); } /** * tick_nohz_irq_exit - update next tick event from interrupt exit * * When an interrupt fires while we are idle and it doesn't cause * a reschedule, it may still add, modify or delete a timer, enqueue * an RCU callback, etc... * So we need to re-calculate and reprogram the next tick event. */ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->inidle) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run */ bool tick_nohz_idle_got_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->got_idle_tick) { ts->got_idle_tick = 0; return true; } return false; } /** * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer * or the tick, whatever that expires first. Note that, if the tick has been * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled */ ktime_t tick_nohz_get_next_hrtimer(void) { return __this_cpu_read(tick_cpu_device.evtdev)->next_event; } /** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); /* * The idle entry time is expected to be a sufficient approximation of * the current time at this point. */ ktime_t now = ts->idle_entrytime; ktime_t next_event; WARN_ON_ONCE(!ts->inidle); *delta_next = ktime_sub(dev->next_event, now); if (!can_stop_idle_tick(cpu, ts)) return *delta_next; next_event = tick_nohz_next_event(ts, cpu); if (!next_event) return *delta_next; /* * If the next highres timer to expire is earlier than next_event, the * idle governor needs to know that. */ next_event = min_t(u64, next_event, hrtimer_next_event_without(&ts->sched_timer)); return ktime_sub(next_event, now); } /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. * * Called from the schedutil frequency scaling governor in scheduler context. */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { struct tick_sched *ts = tick_get_tick_sched(cpu); return ts->idle_calls; } /** * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. */ unsigned long tick_nohz_get_idle_calls(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return ts->idle_calls; } static void tick_nohz_account_idle_ticks(struct tick_sched *ts) { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE unsigned long ticks; if (vtime_accounting_enabled_this_cpu()) return; /* * We stopped the tick in idle. Update process times would miss the * time we slept as update_process_times does only a 1 tick * accounting. Enforce that this is accounted to idle ! */ ticks = jiffies - ts->idle_jiffies; /* * We might be one off. Do not randomly account a huge number of ticks! */ if (ticks && ticks < LONG_MAX) account_idle_ticks(ticks); #endif } static void __tick_nohz_idle_restart_tick(struct tick_sched *ts, ktime_t now) { tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_ticks(ts); } void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->tick_stopped) __tick_nohz_idle_restart_tick(ts, ktime_get()); } /** * tick_nohz_idle_exit - restart the idle tick from the idle task * * Restart the idle tick when the CPU is woken up from idle * This also exit the RCU extended quiescent state. The CPU * can use RCU again after this function is called. */ void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); WARN_ON_ONCE(!ts->inidle); WARN_ON_ONCE(ts->timer_expires_base); ts->inidle = 0; idle_active = ts->idle_active; tick_stopped = ts->tick_stopped; if (idle_active || tick_stopped) now = ktime_get(); if (idle_active) tick_nohz_stop_idle(ts, now); if (tick_stopped) __tick_nohz_idle_restart_tick(ts, now); local_irq_enable(); } /* * The nohz low res interrupt handler */ static void tick_nohz_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); dev->next_event = KTIME_MAX; tick_sched_do_timer(ts, now); tick_sched_handle(ts, regs); if (unlikely(ts->tick_stopped)) { /* * The clockevent device is not reprogrammed, so change the * clock event device to ONESHOT_STOPPED to avoid spurious * interrupts on devices which might not be truly one shot. */ tick_program_event(KTIME_MAX, 1); return; } hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { if (!tick_nohz_enabled) return; ts->nohz_mode = mode; /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); } /** * tick_nohz_switch_to_nohz - switch to nohz mode */ static void tick_nohz_switch_to_nohz(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t next; if (!tick_nohz_enabled) return; if (tick_switch_to_oneshot(tick_nohz_handler)) return; /* * Recycle the hrtimer in ts, so we can share the * hrtimer_forward with the highres code. */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); /* Get the next period */ next = tick_init_jiffy_update(); hrtimer_set_expires(&ts->sched_timer, next); hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } static inline void tick_nohz_irq_enter(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; if (!ts->idle_active && !ts->tick_stopped) return; now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); if (ts->tick_stopped) tick_nohz_update_jiffies(now); } #else static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { } #endif /* CONFIG_NO_HZ_COMMON */ /* * Called from irq_enter to notify about the possible interruption of idle() */ void tick_irq_enter(void) { tick_check_oneshot_broadcast_this_cpu(); tick_nohz_irq_enter(); } /* * High resolution timer specific code */ #ifdef CONFIG_HIGH_RES_TIMERS /* * We rearm the timer until we get disabled by the idle code. * Called with interrupts disabled. */ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) { struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); tick_sched_do_timer(ts, now); /* * Do not call, when we are not in irq context and have * no valid regs pointer */ if (regs) tick_sched_handle(ts, regs); else ts->next_tick = 0; /* No need to reprogram if we are in idle or full dynticks mode */ if (unlikely(ts->tick_stopped)) return HRTIMER_NORESTART; hrtimer_forward(timer, now, TICK_NSEC); return HRTIMER_RESTART; } static int sched_skew_tick; static int __init skew_tick(char *str) { get_option(&str, &sched_skew_tick); return 0; } early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer */ void tick_setup_sched_timer(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now = ktime_get(); /* * Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ts->sched_timer.function = tick_sched_timer; /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); /* Offset the tick to avert jiffies_lock contention. */ if (sched_skew_tick) { u64 offset = TICK_NSEC >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); hrtimer_add_expires_ns(&ts->sched_timer, offset); } hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); } #endif /* HIGH_RES_TIMERS */ #if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; # ifdef CONFIG_HIGH_RES_TIMERS if (ts->sched_timer.base) hrtimer_cancel(&ts->sched_timer); # endif idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; idle_calls = ts->idle_calls; idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); ts->idle_sleeptime = idle_sleeptime; ts->iowait_sleeptime = iowait_sleeptime; ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } #endif /** * Async notification about clocksource changes */ void tick_clock_notify(void) { int cpu; for_each_possible_cpu(cpu) set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks); } /* * Async notification about clock event changes */ void tick_oneshot_notify(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); set_bit(0, &ts->check_clocks); } /** * Check, if a change happened, which makes oneshot possible. * * Called cyclic from the hrtimer softirq (driven by the timer * softirq) allow_nohz signals, that we can switch into low-res nohz * mode, because high resolution timers are disabled (either compile * or runtime). Called with interrupts disabled. */ int tick_check_oneshot_change(int allow_nohz) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; if (ts->nohz_mode != NOHZ_MODE_INACTIVE) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) return 0; if (!allow_nohz) return 1; tick_nohz_switch_to_nohz(); return 0; } |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H #include <linux/atomic.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/rculist_bl.h> #include <linux/spinlock.h> #include <linux/seqlock.h> #include <linux/cache.h> #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> #include <linux/wait.h> struct path; struct vfsmount; /* * linux/include/linux/dcache.h * * Dirent cache data structures * * (C) Copyright 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ #define IS_ROOT(x) ((x) == (x)->d_parent) /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { union { struct { HASH_LEN_DECLARE; }; u64 hash_len; }; const unsigned char *name; }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } extern const struct qstr empty_name; extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the * large memory footprint increase). */ #ifdef CONFIG_64BIT # define DNAME_INLINE_LEN 32 /* 192 bytes */ #else # ifdef CONFIG_SMP # define DNAME_INLINE_LEN 36 /* 128 bytes */ # else # define DNAME_INLINE_LEN 40 /* 128 bytes */ # endif #endif #define d_lock d_lockref.lock struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ /* Ref lookup also touches following */ struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ union { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; struct list_head d_child; /* child of parent list */ struct list_head d_subdirs; /* our children */ /* * d_alias and d_rcu can share memory */ union { struct hlist_node d_alias; /* inode alias list */ struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; } __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: * * 0: normal * 1: nested */ enum dentry_d_lock_class { DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */ DENTRY_D_LOCK_NESTED }; struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *); } ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/locking.rst. Keep it updated! * * FUrther descriptions are found in Documentation/filesystems/vfs.rst. * Keep it updated too! */ /* d_flags entries */ #define DCACHE_OP_HASH 0x00000001 #define DCACHE_OP_COMPARE 0x00000002 #define DCACHE_OP_REVALIDATE 0x00000004 #define DCACHE_OP_DELETE 0x00000008 #define DCACHE_OP_PRUNE 0x00000010 #define DCACHE_DISCONNECTED 0x00000020 /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first * endeavour to clear the bit either by discovering that it is connected, * or by performing lookup operations. Any filesystem which supports * nfsd_operations MUST have a lookup function which, if it finds a * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ #define DCACHE_REFERENCED 0x00000040 /* Recently used, don't discard. */ #define DCACHE_DONTCACHE 0x00000080 /* Purge from memory on final dput() */ #define DCACHE_CANT_MOUNT 0x00000100 #define DCACHE_GENOCIDE 0x00000200 #define DCACHE_SHRINK_LIST 0x00000400 #define DCACHE_OP_WEAK_REVALIDATE 0x00000800 #define DCACHE_NFSFS_RENAMED 0x00001000 /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ #define DCACHE_COOKIE 0x00002000 /* For use by dcookie subsystem */ #define DCACHE_FSNOTIFY_PARENT_WATCHED 0x00004000 /* Parent inode is watched by some fsnotify listener */ #define DCACHE_DENTRY_KILLED 0x00008000 #define DCACHE_MOUNTED 0x00010000 /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT 0x00020000 /* handle automount on this dir */ #define DCACHE_MANAGE_TRANSIT 0x00040000 /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) #define DCACHE_LRU_LIST 0x00080000 #define DCACHE_ENTRY_TYPE 0x00700000 #define DCACHE_MISS_TYPE 0x00000000 /* Negative dentry (maybe fallthru to nowhere) */ #define DCACHE_WHITEOUT_TYPE 0x00100000 /* Whiteout dentry (stop pathwalk) */ #define DCACHE_DIRECTORY_TYPE 0x00200000 /* Normal directory */ #define DCACHE_AUTODIR_TYPE 0x00300000 /* Lookupless directory (presumed automount) */ #define DCACHE_REGULAR_TYPE 0x00400000 /* Regular file type (or fallthru to such) */ #define DCACHE_SPECIAL_TYPE 0x00500000 /* Other file type (or fallthru to such) */ #define DCACHE_SYMLINK_TYPE 0x00600000 /* Symlink (or fallthru to such) */ #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ #define DCACHE_NOKEY_NAME 0x02000000 /* Encrypted name encoded without key */ #define DCACHE_OP_REAL 0x04000000 #define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ #define DCACHE_DENTRY_CURSOR 0x20000000 #define DCACHE_NORCU 0x40000000 /* No RCU delay for freeing */ extern seqlock_t rename_lock; /* * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void shrink_dcache_for_umount(struct super_block *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); /* <clickety>-<click> the ramfs-type tree */ extern void d_genocide(struct dentry *); extern void d_tmpfile(struct dentry *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); /* appendix may either be NULL or be used for transname suffixes */ extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; } /* * helper function for dentry_operations.d_dname() members */ extern __printf(4, 5) char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); extern char *dentry_path_raw(struct dentry *, char *, int); extern char *dentry_path(struct dentry *, char *, int); /* Allocation counts.. */ /** * dget, dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be * destroyed when it has references. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { if (dentry) dentry->d_lockref.count++; return dentry; } static inline struct dentry *dget(struct dentry *dentry) { if (dentry) lockref_get(&dentry->d_lockref); return dentry; } extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed * @dentry: entry to check * * Returns true if the dentry passed is not currently hashed. */ static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } static inline void dont_mount(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_CANT_MOUNT; spin_unlock(&dentry->d_lock); } extern void __d_lookup_done(struct dentry *); static inline int d_in_lookup(const struct dentry *dentry) { return dentry->d_flags & DCACHE_PAR_LOOKUP; } static inline void d_lookup_done(struct dentry *dentry) { if (unlikely(d_in_lookup(dentry))) { spin_lock(&dentry->d_lock); __d_lookup_done(dentry); spin_unlock(&dentry->d_lock); } } extern void dput(struct dentry *); static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } /* * Directory cache entry type accessor functions. */ static inline unsigned __d_entry_type(const struct dentry *dentry) { return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_MISS_TYPE; } static inline bool d_is_whiteout(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; } static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } static inline bool d_is_autodir(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } static inline bool d_is_dir(const struct dentry *dentry) { return d_can_lookup(dentry) || d_is_autodir(dentry); } static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } static inline bool d_is_reg(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; } static inline bool d_is_special(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; } static inline bool d_is_file(const struct dentry *dentry) { return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) { // TODO: check d_is_whiteout(dentry) also. return d_is_miss(dentry); } static inline bool d_flags_negative(unsigned flags) { return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; } static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); } /** * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents either an absent name or a name that * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent * a true miss, a whiteout that isn't represented by a 0,0 chardev or a * fallthrough marker in an opaque directory. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. (3) The dentry may have something attached to ->d_lower and the * type field of the flags may be set to something other than miss or whiteout. */ static inline bool d_really_is_negative(const struct dentry *dentry) { return dentry->d_inode == NULL; } /** * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents a name that maps to an inode * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if * that is represented on medium as a 0,0 chardev. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. */ static inline bool d_really_is_positive(const struct dentry *dentry) { return dentry->d_inode != NULL; } static inline int simple_positive(const struct dentry *dentry) { return d_really_is_positive(dentry) && !d_unhashed(dentry); } extern void d_set_fallthru(struct dentry *dentry); static inline bool d_is_fallthru(const struct dentry *dentry) { return dentry->d_flags & DCACHE_FALLTHRU; } extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, 100); } /** * d_inode - Get the actual inode of this dentry * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode(const struct dentry *dentry) { return dentry->d_inode; } /** * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { return READ_ONCE(dentry->d_inode); } /** * d_backing_inode - Get upper or lower inode we should be using * @upper: The upper layer * * This is the helper that should be used to get at the inode that will be used * if this dentry were to be opened as a file. The inode may be on the upper * dentry or it may be on a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own inodes. */ static inline struct inode *d_backing_inode(const struct dentry *upper) { struct inode *inode = upper->d_inode; return inode; } /** * d_backing_dentry - Get upper or lower dentry we should be using * @upper: The upper layer * * This is the helper that should be used to get the dentry of the inode that * will be used if this dentry were opened as a file. It may be the upper * dentry or it may be a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own dentries. */ static inline struct dentry *d_backing_dentry(struct dentry *upper) { return upper; } /** * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ static inline struct dentry *d_real(struct dentry *dentry, const struct inode *inode) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, inode); else return dentry; } /** * d_real_inode - Return the real inode * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ return d_backing_inode(d_real((struct dentry *) dentry, NULL)); } struct name_snapshot { struct qstr name; unsigned char inline_name[DNAME_INLINE_LEN]; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); #endif /* __LINUX_DCACHE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/numa.h> typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mis-match error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) static inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); } #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) static inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) static inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) unsigned int __next_node_in(int node, const nodemask_t *srcp); static inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node >= 0) && (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static inline int node_state(int node, enum node_states state) { return node == 0; } static inline void node_set_state(int node, enum node_states state) { } static inline void node_clear_state(int node, enum node_states state) { } static inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) extern int node_random(const nodemask_t *maskp); #else static inline int node_random(const nodemask_t *mask) { return 0; } #endif #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* * For nodemask scrach area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* A example struture for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/pagevec.h * * In many places it is efficient to batch an operation up against multiple * pages. A pagevec is a multipage container which is used for that. */ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H #include <linux/xarray.h> /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 struct page; struct address_space; struct pagevec { unsigned char nr; bool percpu_pvec_drained; struct page *pages[PAGEVEC_SIZE]; }; void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); static inline unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start) { return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); } unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } static inline void pagevec_init(struct pagevec *pvec) { pvec->nr = 0; pvec->percpu_pvec_drained = false; } static inline void pagevec_reinit(struct pagevec *pvec) { pvec->nr = 0; } static inline unsigned pagevec_count(struct pagevec *pvec) { return pvec->nr; } static inline unsigned pagevec_space(struct pagevec *pvec) { return PAGEVEC_SIZE - pvec->nr; } /* * Add a page to a pagevec. Returns the number of slots still available. */ static inline unsigned pagevec_add(struct pagevec *pvec, struct page *page) { pvec->pages[pvec->nr++] = page; return pagevec_space(pvec); } static inline void pagevec_release(struct pagevec *pvec) { if (pagevec_count(pvec)) __pagevec_release(pvec); } #endif /* _LINUX_PAGEVEC_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> /* * Initially, a percpu refcount is just a set of percpu counters. Initially, we * don't try to detect the ref hitting 0 - which means that get/put can just * increment or decrement the local counter. Note that the counter on a * particular cpu can (and will) wrap - this is fine, when we go to shutdown the * percpu counters will all sum to the correct value * * (More precisely: because modular arithmetic is commutative the sum of all the * percpu_count vars will be equal to what it would have been if all the gets * and puts were done to a single integer, even if some of the percpu integers * overflow or underflow). * * The real trick to implementing percpu refcounts is shutdown. We can't detect * the ref hitting 0 on every put - this would require global synchronization * and defeat the whole purpose of using percpu refs. * * What we do is require the user to keep track of the initial refcount; we know * the ref can't hit 0 before the user drops the initial ref, so as long as we * convert to non percpu mode before the initial ref is dropped everything * works. * * Converting to non percpu mode is done with some RCUish stuff in * percpu_ref_kill. Additionally, we need a bias value so that the * atomic_long_t can't hit 0 before we've added up all the percpu refs. */ #define PERCPU_COUNT_BIAS (1LU << (BITS_PER_LONG - 1)) static DEFINE_SPINLOCK(percpu_ref_switch_lock); static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq); static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref) { return (unsigned long __percpu *) (ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD); } /** * percpu_ref_init - initialize a percpu refcount * @ref: percpu_ref to initialize * @release: function which will be called when refcount hits 0 * @flags: PERCPU_REF_INIT_* flags * @gfp: allocation mask to use * * Initializes @ref. @ref starts out in percpu mode with a refcount of 1 unless * @flags contains PERCPU_REF_INIT_ATOMIC or PERCPU_REF_INIT_DEAD. These flags * change the start state to atomic with the latter setting the initial refcount * to 0. See the definitions of PERCPU_REF_INIT_* flags for flag behaviors. * * Note that @release must not sleep - it may potentially be called from RCU * callback context by percpu_ref_kill(). */ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp) { size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS, __alignof__(unsigned long)); unsigned long start_count = 0; struct percpu_ref_data *data; ref->percpu_count_ptr = (unsigned long) __alloc_percpu_gfp(sizeof(unsigned long), align, gfp); if (!ref->percpu_count_ptr) return -ENOMEM; data = kzalloc(sizeof(*ref->data), gfp); if (!data) { free_percpu((void __percpu *)ref->percpu_count_ptr); ref->percpu_count_ptr = 0; return -ENOMEM; } data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) { ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; data->allow_reinit = true; } else { start_count += PERCPU_COUNT_BIAS; } if (flags & PERCPU_REF_INIT_DEAD) ref->percpu_count_ptr |= __PERCPU_REF_DEAD; else start_count++; atomic_long_set(&data->count, start_count); data->release = release; data->confirm_switch = NULL; data->ref = ref; ref->data = data; return 0; } EXPORT_SYMBOL_GPL(percpu_ref_init); static void __percpu_ref_exit(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); if (percpu_count) { /* non-NULL confirm_switch indicates switching in progress */ WARN_ON_ONCE(ref->data && ref->data->confirm_switch); free_percpu(percpu_count); ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD; } } /** * percpu_ref_exit - undo percpu_ref_init() * @ref: percpu_ref to exit * * This function exits @ref. The caller is responsible for ensuring that * @ref is no longer in active use. The usual places to invoke this * function from are the @ref->release() callback or in init failure path * where percpu_ref_init() succeeded but other parts of the initialization * of the embedding object failed. */ void percpu_ref_exit(struct percpu_ref *ref) { struct percpu_ref_data *data = ref->data; unsigned long flags; __percpu_ref_exit(ref); if (!data) return; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) << __PERCPU_REF_FLAG_BITS; ref->data = NULL; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); kfree(data); } EXPORT_SYMBOL_GPL(percpu_ref_exit); static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; data->confirm_switch(ref); data->confirm_switch = NULL; wake_up_all(&percpu_ref_switch_waitq); if (!data->allow_reinit) __percpu_ref_exit(ref); /* drop ref from percpu_ref_switch_to_atomic() */ percpu_ref_put(ref); } static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); unsigned long count = 0; int cpu; for_each_possible_cpu(cpu) count += *per_cpu_ptr(percpu_count, cpu); pr_debug("global %lu percpu %lu\n", atomic_long_read(&data->count), count); /* * It's crucial that we sum the percpu counters _before_ adding the sum * to &ref->count; since gets could be happening on one cpu while puts * happen on another, adding a single cpu's count could cause * @ref->count to hit 0 before we've got a consistent value - but the * sum of all the counts will be consistent and correct. * * Subtracting the bias value then has to happen _after_ adding count to * &ref->count; we need the bias value to prevent &ref->count from * reaching 0 before we add the percpu counts. But doing it at the same * time is equivalent and saves us atomic operations: */ atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); WARN_ONCE(atomic_long_read(&data->count) <= 0, "percpu ref (%ps) <= 0 (%ld) after switching to atomic", data->release, atomic_long_read(&data->count)); /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); } static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref) { } static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { if (ref->percpu_count_ptr & __PERCPU_REF_ATOMIC) { if (confirm_switch) confirm_switch(ref); return; } /* switching from percpu to atomic */ ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; /* * Non-NULL ->confirm_switch is used to indicate that switching is * in progress. Use noop one if unspecified. */ ref->data->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch; percpu_ref_get(ref); /* put after confirmation */ call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu); } static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); int cpu; BUG_ON(!percpu_count); if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) return; if (WARN_ON_ONCE(!ref->data->allow_reinit)) return; atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count); /* * Restore per-cpu operation. smp_store_release() is paired * with READ_ONCE() in __ref_is_percpu() and guarantees that the * zeroing is visible to all percpu accesses which can see the * following __PERCPU_REF_ATOMIC clearing. */ for_each_possible_cpu(cpu) *per_cpu_ptr(percpu_count, cpu) = 0; smp_store_release(&ref->percpu_count_ptr, ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC); } static void __percpu_ref_switch_mode(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { struct percpu_ref_data *data = ref->data; lockdep_assert_held(&percpu_ref_switch_lock); /* * If the previous ATOMIC switching hasn't finished yet, wait for * its completion. If the caller ensures that ATOMIC switching * isn't in progress, this function can be called from any context. */ wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); } /** * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * @confirm_switch: optional confirmation callback * * There's no reason to use this function for the usual reference counting. * Use percpu_ref_kill[_and_confirm](). * * Schedule switching of @ref to atomic mode. All its percpu counts will * be collected to the main atomic counter. On completion, when all CPUs * are guaraneed to be in atomic mode, @confirm_switch, which may not * block, is invoked. This function may be invoked concurrently with all * the get/put operations and can safely be mixed with kill and reinit * operations. Note that @ref will stay in atomic mode across kill/reinit * cycles until percpu_ref_switch_to_percpu() is called. * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = true; __percpu_ref_switch_mode(ref, confirm_switch); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic); /** * percpu_ref_switch_to_atomic_sync - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * * Schedule switching the ref to atomic mode, and wait for the * switch to complete. Caller must ensure that no other thread * will switch back to percpu mode. */ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref) { percpu_ref_switch_to_atomic(ref, NULL); wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync); /** * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode * @ref: percpu_ref to switch to percpu mode * * There's no reason to use this function for the usual reference counting. * To re-use an expired ref, use percpu_ref_reinit(). * * Switch @ref to percpu mode. This function may be invoked concurrently * with all the get/put operations and can safely be mixed with kill and * reinit operations. This function reverses the sticky atomic state set * by PERCPU_REF_INIT_ATOMIC or percpu_ref_switch_to_atomic(). If @ref is * dying or dead, the actual switching takes place on the following * percpu_ref_reinit(). * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = false; __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); /** * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation * @ref: percpu_ref to kill * @confirm_kill: optional confirmation callback * * Equivalent to percpu_ref_kill() but also schedules kill confirmation if * @confirm_kill is not NULL. @confirm_kill, which may not block, will be * called after @ref is seen as dead from all CPUs at which point all * further invocations of percpu_ref_tryget_live() will fail. See * percpu_ref_tryget_live() for details. * * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). * * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD, "%s called more than once on %ps!", __func__, ref->data->release); ref->percpu_count_ptr |= __PERCPU_REF_DEAD; __percpu_ref_switch_mode(ref, confirm_kill); percpu_ref_put(ref); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test * * Returns %true if @ref reached zero. * * This function is safe to call as long as @ref is between init and exit. */ bool percpu_ref_is_zero(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long count, flags; if (__ref_is_percpu(ref, &percpu_count)) return false; /* protect us from being destroyed */ spin_lock_irqsave(&percpu_ref_switch_lock, flags); if (ref->data) count = atomic_long_read(&ref->data->count); else count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); return count == 0; } EXPORT_SYMBOL_GPL(percpu_ref_is_zero); /** * percpu_ref_reinit - re-initialize a percpu refcount * @ref: perpcu_ref to re-initialize * * Re-initialize @ref so that it's in the same state as when it finished * percpu_ref_init() ignoring %PERCPU_REF_INIT_DEAD. @ref must have been * initialized successfully and reached 0 but not exited. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_reinit(struct percpu_ref *ref) { WARN_ON_ONCE(!percpu_ref_is_zero(ref)); percpu_ref_resurrect(ref); } EXPORT_SYMBOL_GPL(percpu_ref_reinit); /** * percpu_ref_resurrect - modify a percpu refcount from dead to live * @ref: perpcu_ref to resurrect * * Modify @ref so that it's in the same state as before percpu_ref_kill() was * called. @ref must be dead but must not yet have exited. * * If @ref->release() frees @ref then the caller is responsible for * guaranteeing that @ref->release() does not get called while this * function is in progress. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_resurrect(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ON_ONCE(!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)); WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count)); ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD; percpu_ref_get(ref); __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_resurrect); |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 | // SPDX-License-Identifier: GPL-2.0 /* * Tag allocation using scalable bitmaps. Uses active queue tracking to support * fairer distribution of tags between multiple submitters when a shared tag map * is used. * * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blk-mq.h> #include <linux/delay.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-tag.h" /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail * to get tag when first time, the other shared-tag users could reserve * budget for it. */ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) atomic_inc(&set->active_queues_shared_sbitmap); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) atomic_inc(&hctx->tags->active_queues); } return true; } /* * Wakeup all potentially sleeping on tags */ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) { sbitmap_queue_wake_all(tags->bitmap_tags); if (include_reserve) sbitmap_queue_wake_all(tags->breserved_tags); } /* * If a previously busy queue goes inactive, potential waiters could now * be allowed to queue. Wake them up and check. */ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (blk_mq_is_sbitmap_shared(hctx->flags)) { if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; atomic_dec(&set->active_queues_shared_sbitmap); } else { if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; atomic_dec(&tags->active_queues); } blk_mq_tag_wakeup_all(tags, false); } static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { if (!data->q->elevator && !(data->flags & BLK_MQ_REQ_RESERVED) && !hctx_may_queue(data->hctx, bt)) return BLK_MQ_NO_TAG; if (data->shallow_depth) return __sbitmap_queue_get_shallow(bt, data->shallow_depth); else return __sbitmap_queue_get(bt); } unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt; struct sbq_wait_state *ws; DEFINE_SBQ_WAIT(wait); unsigned int tag_offset; int tag; if (data->flags & BLK_MQ_REQ_RESERVED) { if (unlikely(!tags->nr_reserved_tags)) { WARN_ON_ONCE(1); return BLK_MQ_NO_TAG; } bt = tags->breserved_tags; tag_offset = 0; } else { bt = tags->bitmap_tags; tag_offset = tags->nr_reserved_tags; } tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) goto found_tag; if (data->flags & BLK_MQ_REQ_NOWAIT) return BLK_MQ_NO_TAG; ws = bt_wait_ptr(bt, data->hctx); do { struct sbitmap_queue *bt_prev; /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for * some to complete. */ blk_mq_run_hw_queue(data->hctx, false); /* * Retry tag allocation after running the hardware queue, * as running the queue may also have found completions. */ tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE); tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; bt_prev = bt; io_schedule(); sbitmap_finish_wait(bt, ws, &wait); data->ctx = blk_mq_get_ctx(data->q); data->hctx = blk_mq_map_queue(data->q, data->cmd_flags, data->ctx); tags = blk_mq_tags_from_data(data); if (data->flags & BLK_MQ_REQ_RESERVED) bt = tags->breserved_tags; else bt = tags->bitmap_tags; /* * If destination hw queue is changed, fake wake up on * previous queue for compensating the wake up miss, so * other allocations on previous queue won't be starved. */ if (bt != bt_prev) sbitmap_queue_wake_up(bt_prev); ws = bt_wait_ptr(bt, data->hctx); } while (1); sbitmap_finish_wait(bt, ws, &wait); found_tag: /* * Give up this allocation if the hctx is inactive. The caller will * retry on an active hctx. */ if (unlikely(test_bit(BLK_MQ_S_INACTIVE, &data->hctx->state))) { blk_mq_put_tag(tags, data->ctx, tag + tag_offset); return BLK_MQ_NO_TAG; } return tag + tag_offset; } void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag) { if (!blk_mq_tag_is_reserved(tags, tag)) { const int real_tag = tag - tags->nr_reserved_tags; BUG_ON(real_tag >= tags->nr_tags); sbitmap_queue_clear(tags->bitmap_tags, real_tag, ctx->cpu); } else { BUG_ON(tag >= tags->nr_reserved_tags); sbitmap_queue_clear(tags->breserved_tags, tag, ctx->cpu); } } struct bt_iter_data { struct blk_mq_hw_ctx *hctx; busy_iter_fn *fn; void *data; bool reserved; }; static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, unsigned int bitnr) { struct request *rq; unsigned long flags; spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; } static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; struct blk_mq_hw_ctx *hctx = iter_data->hctx; struct blk_mq_tags *tags = hctx->tags; bool reserved = iter_data->reserved; struct request *rq; bool ret = true; if (!reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (rq->q == hctx->queue && rq->mq_hctx == hctx) ret = iter_data->fn(hctx, rq, iter_data->data, reserved); blk_mq_put_rq_ref(rq); return ret; } /** * bt_for_each - iterate over the requests associated with a hardware queue * @hctx: Hardware queue to examine. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each request * associated with @hctx that has been assigned a driver tag. * @fn will be called as follows: @fn(@hctx, rq, @data, @reserved) * where rq is a pointer to a request. Return true to continue * iterating tags, false to stop. * @data: Will be passed as third argument to @fn. * @reserved: Indicates whether @bt is the breserved_tags member or the * bitmap_tags member of struct blk_mq_tags. */ static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt, busy_iter_fn *fn, void *data, bool reserved) { struct bt_iter_data iter_data = { .hctx = hctx, .fn = fn, .data = data, .reserved = reserved, }; sbitmap_for_each_set(&bt->sb, bt_iter, &iter_data); } struct bt_tags_iter_data { struct blk_mq_tags *tags; busy_tag_iter_fn *fn; void *data; unsigned int flags; }; #define BT_TAG_ITER_RESERVED (1 << 0) #define BT_TAG_ITER_STARTED (1 << 1) #define BT_TAG_ITER_STATIC_RQS (1 << 2) static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_tags_iter_data *iter_data = data; struct blk_mq_tags *tags = iter_data->tags; bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; bool ret = true; bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (!(iter_data->flags & BT_TAG_ITER_STARTED) || blk_mq_request_started(rq)) ret = iter_data->fn(rq, iter_data->data, reserved); if (!iter_static_rqs) blk_mq_put_rq_ref(rq); return ret; } /** * bt_tags_for_each - iterate over the requests in a tag map * @tags: Tag map to iterate over. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @data, * @reserved) where rq is a pointer to a request. Return true * to continue iterating tags, false to stop. * @data: Will be passed as second argument to @fn. * @flags: BT_TAG_ITER_* */ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt, busy_tag_iter_fn *fn, void *data, unsigned int flags) { struct bt_tags_iter_data iter_data = { .tags = tags, .fn = fn, .data = data, .flags = flags, }; if (tags->rqs) sbitmap_for_each_set(&bt->sb, bt_tags_iter, &iter_data); } static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv, unsigned int flags) { WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED); if (tags->nr_reserved_tags) bt_tags_for_each(tags, tags->breserved_tags, fn, priv, flags | BT_TAG_ITER_RESERVED); bt_tags_for_each(tags, tags->bitmap_tags, fn, priv, flags); } /** * blk_mq_all_tag_iter - iterate over all requests in a tag map * @tags: Tag map to iterate over. * @fn: Pointer to the function that will be called for each * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * Caller has to pass the tag map from which requests are allocated. */ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv) { __blk_mq_all_tag_iter(tags, fn, priv, BT_TAG_ITER_STATIC_RQS); } /** * blk_mq_tagset_busy_iter - iterate over all started requests in a tag set * @tagset: Tag set to iterate over. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * We grab one request reference before calling @fn and release it after * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) { int i; for (i = 0; i < tagset->nr_hw_queues; i++) { if (tagset->tags && tagset->tags[i]) __blk_mq_all_tag_iter(tagset->tags[i], fn, priv, BT_TAG_ITER_STARTED); } } EXPORT_SYMBOL(blk_mq_tagset_busy_iter); static bool blk_mq_tagset_count_completed_rqs(struct request *rq, void *data, bool reserved) { unsigned *count = data; if (blk_mq_request_completed(rq)) (*count)++; return true; } /** * blk_mq_tagset_wait_completed_request - wait until all completed req's * complete funtion is run * @tagset: Tag set to drain completed request * * Note: This function has to be run after all IO queues are shutdown */ void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset) { while (true) { unsigned count = 0; blk_mq_tagset_busy_iter(tagset, blk_mq_tagset_count_completed_rqs, &count); if (!count) break; msleep(5); } } EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request); /** * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag * @q: Request queue to examine. * @fn: Pointer to the function that will be called for each request * on @q. @fn will be called as follows: @fn(hctx, rq, @priv, * reserved) where rq is a pointer to a request and hctx points * to the hardware queue associated with the request. 'reserved' * indicates whether or not @rq is a reserved request. * @priv: Will be passed as third argument to @fn. * * Note: if @q->tag_set is shared with other request queues then @fn will be * called for all requests on all queues that share that tag set and not only * for requests associated with @q. */ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv) { struct blk_mq_hw_ctx *hctx; int i; /* * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx * while the queue is frozen. So we can use q_usage_counter to avoid * racing with it. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; queue_for_each_hw_ctx(q, hctx, i) { struct blk_mq_tags *tags = hctx->tags; /* * If no software queues are currently mapped to this * hardware queue, there's nothing to check */ if (!blk_mq_hw_queue_mapped(hctx)) continue; if (tags->nr_reserved_tags) bt_for_each(hctx, tags->breserved_tags, fn, priv, true); bt_for_each(hctx, tags->bitmap_tags, fn, priv, false); } blk_queue_exit(q); } static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, bool round_robin, int node) { return sbitmap_queue_init_node(bt, depth, -1, round_robin, GFP_KERNEL, node); } static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, int node, int alloc_policy) { unsigned int depth = tags->nr_tags - tags->nr_reserved_tags; bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; if (bt_alloc(&tags->__bitmap_tags, depth, round_robin, node)) return -ENOMEM; if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags, round_robin, node)) goto free_bitmap_tags; tags->bitmap_tags = &tags->__bitmap_tags; tags->breserved_tags = &tags->__breserved_tags; return 0; free_bitmap_tags: sbitmap_queue_free(&tags->__bitmap_tags); return -ENOMEM; } int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) { unsigned int depth = set->queue_depth - set->reserved_tags; int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; int i, node = set->numa_node; if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node)) return -ENOMEM; if (bt_alloc(&set->__breserved_tags, set->reserved_tags, round_robin, node)) goto free_bitmap_tags; for (i = 0; i < set->nr_hw_queues; i++) { struct blk_mq_tags *tags = set->tags[i]; tags->bitmap_tags = &set->__bitmap_tags; tags->breserved_tags = &set->__breserved_tags; } return 0; free_bitmap_tags: sbitmap_queue_free(&set->__bitmap_tags); return -ENOMEM; } void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) { sbitmap_queue_free(&set->__bitmap_tags); sbitmap_queue_free(&set->__breserved_tags); } struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, int node, unsigned int flags) { int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags); struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { pr_err("blk-mq: tag depth too large\n"); return NULL; } tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node); if (!tags) return NULL; tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; spin_lock_init(&tags->lock); if (flags & BLK_MQ_F_TAG_HCTX_SHARED) return tags; if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) { kfree(tags); return NULL; } return tags; } void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags) { if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) { sbitmap_queue_free(tags->bitmap_tags); sbitmap_queue_free(tags->breserved_tags); } kfree(tags); } int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tagsptr, unsigned int tdepth, bool can_grow) { struct blk_mq_tags *tags = *tagsptr; if (tdepth <= tags->nr_reserved_tags) return -EINVAL; /* * If we are allowed to grow beyond the original size, allocate * a new set of tags before freeing the old one. */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; /* Only sched tags can grow, so clear HCTX_SHARED flag */ unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; struct blk_mq_tags *new; bool ret; if (!can_grow) return -EINVAL; /* * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ if (tdepth > 16 * BLKDEV_MAX_RQ) return -EINVAL; new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, tags->nr_reserved_tags, flags); if (!new) return -ENOMEM; ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth); if (ret) { blk_mq_free_rq_map(new, flags); return -ENOMEM; } blk_mq_free_rqs(set, *tagsptr, hctx->queue_num); blk_mq_free_rq_map(*tagsptr, flags); *tagsptr = new; } else { /* * Don't need (or can't) update reserved tags here, they * remain static and should never need resizing. */ sbitmap_queue_resize(tags->bitmap_tags, tdepth - tags->nr_reserved_tags); } return 0; } void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) { sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags); } /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag * * The tag field in struct request is unique per hardware queue but not over * all hardware queues. Hence this function that returns a tag with the * hardware context index in the upper bits and the per hardware queue tag in * the lower bits. * * Note: When called for a request that is queued on a non-multiqueue request * queue, the hardware context index is set to zero. */ u32 blk_mq_unique_tag(struct request *rq) { return (rq->mq_hctx->queue_num << BLK_MQ_UNIQUE_TAG_BITS) | (rq->tag & BLK_MQ_UNIQUE_TAG_MASK); } EXPORT_SYMBOL(blk_mq_unique_tag); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_advance(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); /* Move the radix tree node cache here */ extern struct kmem_cache *radix_tree_node_cachep; extern void radix_tree_node_rcu_free(struct rcu_head *head); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * This function is now internal-only. */ static void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_all(child, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: New entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: New entry order. * * The value in the entry is copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_advance(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_advance(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; int order = 0; rcu_read_lock(); entry = xas_load(&xas); if (!entry) goto unlock; if (!xas.xa_node) goto unlock; for (;;) { unsigned int slot = xas.xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xas.xa_node->slots[slot])) break; order++; } order += xas.xa_node->shift; unlock: rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ #include <stdarg.h> #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); extern void *memdup_user(const void __user *, size_t); extern void *vmemdup_user(const void __user *, size_t); extern void *memdup_user_nul(const void __user *, size_t); /* * Include machine specific inline routines */ #include <asm/string.h> #ifndef __HAVE_ARCH_STRCPY extern char * strcpy(char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCPY extern char * strncpy(char *,const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCPY size_t strlcpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRSCPY ssize_t strscpy(char *, const char *, size_t); #endif /* Wraps calls to strscpy()/memset(), no arch specific code required */ ssize_t strscpy_pad(char *dest, const char *src, size_t count); #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif #ifndef __HAVE_ARCH_STRNCAT extern char * strncat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCAT extern size_t strlcat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCMP extern int strcmp(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCMP extern int strncmp(const char *,const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCASECMP extern int strcasecmp(const char *s1, const char *s2); #endif #ifndef __HAVE_ARCH_STRNCASECMP extern int strncasecmp(const char *s1, const char *s2, size_t n); #endif #ifndef __HAVE_ARCH_STRCHR extern char * strchr(const char *,int); #endif #ifndef __HAVE_ARCH_STRCHRNUL extern char * strchrnul(const char *,int); #endif extern char * strnchrnul(const char *, size_t, int); #ifndef __HAVE_ARCH_STRNCHR extern char * strnchr(const char *, size_t, int); #endif #ifndef __HAVE_ARCH_STRRCHR extern char * strrchr(const char *,int); #endif extern char * __must_check skip_spaces(const char *); extern char *strim(char *); static inline __must_check char *strstrip(char *str) { return strim(str); } #ifndef __HAVE_ARCH_STRSTR extern char * strstr(const char *, const char *); #endif #ifndef __HAVE_ARCH_STRNSTR extern char * strnstr(const char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRLEN extern __kernel_size_t strlen(const char *); #endif #ifndef __HAVE_ARCH_STRNLEN extern __kernel_size_t strnlen(const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRPBRK extern char * strpbrk(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRSEP extern char * strsep(char **,const char *); #endif #ifndef __HAVE_ARCH_STRSPN extern __kernel_size_t strspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRCSPN extern __kernel_size_t strcspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET16 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET32 extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET64 extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); #endif static inline void *memset_l(unsigned long *p, unsigned long v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, v, n); else return memset64((uint64_t *)p, v, n); } static inline void *memset_p(void **p, void *v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, (uintptr_t)v, n); else return memset64((uint64_t *)p, (uintptr_t)v, n); } extern void **__memcat_p(void **a, void **b); #define memcat_p(a, b) ({ \ BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ "type mismatch in memcat_p()"); \ (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ }) #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMMOVE extern void * memmove(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSCAN extern void * memscan(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_BCMP extern int bcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); } #endif void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); /** * sysfs_match_string - matches given string in an array * @_a: array of strings * @_s: string to match with * * Helper for __sysfs_match_string(). Calculates the size of @a automatically. */ #define sysfs_match_string(_a, _s) __sysfs_match_string(_a, ARRAY_SIZE(_a), _s) #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); int ptr_to_hashval(const void *ptr, unsigned long *hashval_out); /** * strstarts - does @str start with @prefix? * @str: string to examine * @prefix: prefix to look for. */ static inline bool strstarts(const char *str, const char *prefix) { return strncmp(str, prefix, strlen(prefix)) == 0; } size_t memweight(const void *ptr, size_t bytes); /** * memzero_explicit - Fill a region of memory (e.g. sensitive * keying data) with 0s. * @s: Pointer to the start of the area. * @count: The size of the area. * * Note: usually using memset() is just fine (!), but in cases * where clearing out _local_ data at the end of a scope is * necessary, memzero_explicit() should be used instead in * order to prevent the compiler from optimising away zeroing. * * memzero_explicit() doesn't need an arch-specific version as * it just invokes the one of memset() implicitly. */ static inline void memzero_explicit(void *s, size_t count) { memset(s, 0, count); barrier_data(s); } /** * kbasename - return the last part of a pathname. * * @path: path to extract the filename from. */ static inline const char *kbasename(const char *path) { const char *tail = strrchr(path, '/'); return tail ? tail + 1 : path; } #define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #ifdef CONFIG_KASAN extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else #define __underlying_memchr __builtin_memchr #define __underlying_memcmp __builtin_memcmp #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy #endif __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_strncpy(p, q, size); } __FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; } __FORTIFY_INLINE __kernel_size_t strlen(const char *p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 0); /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); return ret; } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 0); __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(__func__); return ret; } /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) { size_t ret; size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __real_strlcpy(p, q, size); ret = strlen(q); if (size) { size_t len = (ret >= size) ? size - 1 : ret; if (__builtin_constant_p(len) && len >= p_size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; } /* defined after fortified strlen and strnlen to reuse them */ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_memset(p, c, size); } __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __write_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memcpy(p, q, size); } __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __write_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memmove(p, q, size); } extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memscan(p, c, size); } __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __read_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memchr_inv(p, c, size); } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_kmemdup(p, size, gfp); } /* defined after fortified strlen and memcpy to reuse them */ __FORTIFY_INLINE char *strcpy(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp #undef __underlying_memcpy #undef __underlying_memmove #undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy #endif /** * memcpy_and_pad - Copy one buffer to another with padding * @dest: Where to copy to * @dest_len: The destination buffer size * @src: Where to copy from * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ static inline void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad) { if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); } else memcpy(dest, src, dest_len); } /** * str_has_prefix - Test if a string has a given prefix * @str: The string to test * @prefix: The string to see if @str starts with * * A common way to test a prefix of a string is to do: * strncmp(str, prefix, sizeof(prefix) - 1) * * But this can lead to bugs due to typos, or if prefix is a pointer * and not a constant. Instead use str_has_prefix(). * * Returns: * * strlen(@prefix) if @str starts with @prefix * * 0 if @str does not start with @prefix */ static __always_inline size_t str_has_prefix(const char *str, const char *prefix) { size_t len = strlen(prefix); return strncmp(str, prefix, len) == 0 ? len : 0; } #endif /* _LINUX_STRING_H_ */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to io context handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/sched/task.h> #include "blk.h" /* * For io context allocations */ static struct kmem_cache *iocontext_cachep; /** * get_io_context - increment reference count to io_context * @ioc: io_context to get * * Increment reference count to @ioc. */ void get_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); atomic_long_inc(&ioc->refcount); } static void icq_free_icq_rcu(struct rcu_head *head) { struct io_cq *icq = container_of(head, struct io_cq, __rcu_head); kmem_cache_free(icq->__rcu_icq_cache, icq); } /* * Exit an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_exit_icq(struct io_cq *icq) { struct elevator_type *et = icq->q->elevator->type; if (icq->flags & ICQ_EXITED) return; if (et->ops.exit_icq) et->ops.exit_icq(icq); icq->flags |= ICQ_EXITED; } /* * Release an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_destroy_icq(struct io_cq *icq) { struct io_context *ioc = icq->ioc; struct request_queue *q = icq->q; struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); list_del_init(&icq->q_node); /* * Both setting lookup hint to and clearing it from @icq are done * under queue_lock. If it's not pointing to @icq now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(ioc->icq_hint) == icq) rcu_assign_pointer(ioc->icq_hint, NULL); ioc_exit_icq(icq); /* * @icq->q might have gone away by the time RCU callback runs * making it impossible to determine icq_cache. Record it in @icq. */ icq->__rcu_icq_cache = et->icq_cache; icq->flags |= ICQ_DESTROYED; call_rcu(&icq->__rcu_head, icq_free_icq_rcu); } /* * Slow path for ioc release in put_io_context(). Performs double-lock * dancing to unlink all icq's and then frees ioc. */ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); spin_lock_irq(&ioc->lock); while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, struct io_cq, ioc_node); struct request_queue *q = icq->q; if (spin_trylock(&q->queue_lock)) { ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); } else { /* Make sure q and icq cannot be freed. */ rcu_read_lock(); /* Re-acquire the locks in the correct order. */ spin_unlock(&ioc->lock); spin_lock(&q->queue_lock); spin_lock(&ioc->lock); /* * The icq may have been destroyed when the ioc lock * was released. */ if (!(icq->flags & ICQ_DESTROYED)) ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); } } spin_unlock_irq(&ioc->lock); kmem_cache_free(iocontext_cachep, ioc); } /** * put_io_context - put a reference of io_context * @ioc: io_context to put * * Decrement reference count of @ioc and release it if the count reaches * zero. */ void put_io_context(struct io_context *ioc) { unsigned long flags; bool free_ioc = false; if (ioc == NULL) return; BUG_ON(atomic_long_read(&ioc->refcount) <= 0); /* * Releasing ioc requires reverse order double locking and we may * already be holding a queue_lock. Do it asynchronously from wq. */ if (atomic_long_dec_and_test(&ioc->refcount)) { spin_lock_irqsave(&ioc->lock, flags); if (!hlist_empty(&ioc->icq_list)) queue_work(system_power_efficient_wq, &ioc->release_work); else free_ioc = true; spin_unlock_irqrestore(&ioc->lock, flags); } if (free_ioc) kmem_cache_free(iocontext_cachep, ioc); } /** * put_io_context_active - put active reference on ioc * @ioc: ioc of interest * * Undo get_io_context_active(). If active reference reaches zero after * put, @ioc can never issue further IOs and ioscheds are notified. */ void put_io_context_active(struct io_context *ioc) { struct io_cq *icq; if (!atomic_dec_and_test(&ioc->active_ref)) { put_io_context(ioc); return; } spin_lock_irq(&ioc->lock); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; ioc_exit_icq(icq); } spin_unlock_irq(&ioc->lock); put_io_context(ioc); } /* Called by the exiting task */ void exit_io_context(struct task_struct *task) { struct io_context *ioc; task_lock(task); ioc = task->io_context; task->io_context = NULL; task_unlock(task); atomic_dec(&ioc->nr_tasks); put_io_context_active(ioc); } static void __ioc_clear_queue(struct list_head *icq_list) { unsigned long flags; rcu_read_lock(); while (!list_empty(icq_list)) { struct io_cq *icq = list_entry(icq_list->next, struct io_cq, q_node); struct io_context *ioc = icq->ioc; spin_lock_irqsave(&ioc->lock, flags); if (icq->flags & ICQ_DESTROYED) { spin_unlock_irqrestore(&ioc->lock, flags); continue; } ioc_destroy_icq(icq); spin_unlock_irqrestore(&ioc->lock, flags); } rcu_read_unlock(); } /** * ioc_clear_queue - break any ioc association with the specified queue * @q: request_queue being cleared * * Walk @q->icq_list and exit all io_cq's. */ void ioc_clear_queue(struct request_queue *q) { LIST_HEAD(icq_list); spin_lock_irq(&q->queue_lock); list_splice_init(&q->icq_list, &icq_list); spin_unlock_irq(&q->queue_lock); __ioc_clear_queue(&icq_list); } int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) { struct io_context *ioc; int ret; ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO, node); if (unlikely(!ioc)) return -ENOMEM; /* initialize */ atomic_long_set(&ioc->refcount, 1); atomic_set(&ioc->nr_tasks, 1); atomic_set(&ioc->active_ref, 1); spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); /* * Try to install. ioc shouldn't be installed if someone else * already did or @task, which isn't %current, is exiting. Note * that we need to allow ioc creation on exiting %current as exit * path may issue IOs from e.g. exit_files(). The exit path is * responsible for not issuing IO after exit_io_context(). */ task_lock(task); if (!task->io_context && (task == current || !(task->flags & PF_EXITING))) task->io_context = ioc; else kmem_cache_free(iocontext_cachep, ioc); ret = task->io_context ? 0 : -EBUSY; task_unlock(task); return ret; } /** * get_task_io_context - get io_context of a task * @task: task of interest * @gfp_flags: allocation flags, used if allocation is necessary * @node: allocation node, used if allocation is necessary * * Return io_context of @task. If it doesn't exist, it is created with * @gfp_flags and @node. The returned io_context has its reference count * incremented. * * This function always goes through task_lock() and it's better to use * %current->io_context + get_io_context() for %current. */ struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) { struct io_context *ioc; might_sleep_if(gfpflags_allow_blocking(gfp_flags)); do { task_lock(task); ioc = task->io_context; if (likely(ioc)) { get_io_context(ioc); task_unlock(task); return ioc; } task_unlock(task); } while (!create_task_io_context(task, gfp_flags, node)); return NULL; } /** * ioc_lookup_icq - lookup io_cq from ioc * @ioc: the associated io_context * @q: the associated request_queue * * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called * with @q->queue_lock held. */ struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q) { struct io_cq *icq; lockdep_assert_held(&q->queue_lock); /* * icq's are indexed from @ioc using radix tree and hint pointer, * both of which are protected with RCU. All removals are done * holding both q and ioc locks, and we're holding q lock - if we * find a icq which points to us, it's guaranteed to be valid. */ rcu_read_lock(); icq = rcu_dereference(ioc->icq_hint); if (icq && icq->q == q) goto out; icq = radix_tree_lookup(&ioc->icq_tree, q->id); if (icq && icq->q == q) rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */ else icq = NULL; out: rcu_read_unlock(); return icq; } EXPORT_SYMBOL(ioc_lookup_icq); /** * ioc_create_icq - create and link io_cq * @ioc: io_context of interest * @q: request_queue of interest * @gfp_mask: allocation mask * * Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they * will be created using @gfp_mask. * * The caller is responsible for ensuring @ioc won't go away and @q is * alive and will stay alive until this function returns. */ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, gfp_t gfp_mask) { struct elevator_type *et = q->elevator->type; struct io_cq *icq; /* allocate stuff */ icq = kmem_cache_alloc_node(et->icq_cache, gfp_mask | __GFP_ZERO, q->node); if (!icq) return NULL; if (radix_tree_maybe_preload(gfp_mask) < 0) { kmem_cache_free(et->icq_cache, icq); return NULL; } icq->ioc = ioc; icq->q = q; INIT_LIST_HEAD(&icq->q_node); INIT_HLIST_NODE(&icq->ioc_node); /* lock both q and ioc and try to link @icq */ spin_lock_irq(&q->queue_lock); spin_lock(&ioc->lock); if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { hlist_add_head(&icq->ioc_node, &ioc->icq_list); list_add(&icq->q_node, &q->icq_list); if (et->ops.init_icq) et->ops.init_icq(icq); } else { kmem_cache_free(et->icq_cache, icq); icq = ioc_lookup_icq(ioc, q); if (!icq) printk(KERN_ERR "cfq: icq link failed!\n"); } spin_unlock(&ioc->lock); spin_unlock_irq(&q->queue_lock); radix_tree_preload_end(); return icq; } static int __init blk_ioc_init(void) { iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL); return 0; } subsys_initcall(blk_ioc_init); |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/bitops.h> #include <asm/word-at-a-time.h> /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the * address space maximum. * * Return 0 for exceptions (which includes hitting the address * space maximum), or 'count+1' if hitting the user-supplied * maximum count. * * NOTE! We can sometimes overshoot the user-supplied maximum * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; unsigned long c; /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align; unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { unsigned long data; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); /* We already handled 'unsigned long' bytes. Did we do it all ? */ if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, return the marker for "too long". */ if (res >= count) return count+1; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ efault: return 0; } /** * strnlen_user: - Get the size of a user string INCLUDING final NUL. * @str: The string to measure. * @count: Maximum count (including NUL character) * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * NOTE! You should basically never use this function. There is * almost never any valid case for using the length of a user space * string, since the string can be changed at any time by other * threads. Use "strncpy_from_user()" instead to get a stable copy * of the string. */ long strnlen_user(const char __user *str, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_read_access_end(); return retval; } } return 0; } EXPORT_SYMBOL(strnlen_user); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Filesystem parameter description and parser * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_FS_PARSER_H #define _LINUX_FS_PARSER_H #include <linux/fs_context.h> struct path; struct constant_table { const char *name; int value; }; struct fs_parameter_spec; struct fs_parse_result; typedef int fs_param_type(struct p_log *, const struct fs_parameter_spec *, struct fs_parameter *, struct fs_parse_result *); /* * The type of parameter expected. */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, fs_param_is_path, fs_param_is_fd; /* * Specification of the type of value a parameter wants. * * Note that the fsparam_flag(), fsparam_string(), fsparam_u32(), ... macros * should be used to generate elements of this type. */ struct fs_parameter_spec { const char *name; fs_param_type *type; /* The desired parameter type */ u8 opt; /* Option number (returned by fs_parse()) */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ const void *data; }; /* * Result of parse. */ struct fs_parse_result { bool negated; /* T if param was "noxxx" */ union { bool boolean; /* For spec_bool */ int int_32; /* For spec_s32/spec_enum */ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */ u64 uint_64; /* For spec_u64 */ }; }; extern int __fs_parse(struct p_log *log, const struct fs_parameter_spec *desc, struct fs_parameter *value, struct fs_parse_result *result); static inline int fs_parse(struct fs_context *fc, const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { return __fs_parse(&fc->log, desc, param, result); } extern int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, struct path *_path); extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); extern bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc); #else static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { return true; } static inline bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { return true; } #endif /* * Parameter type, name, index and flags element constructors. Use as: * * fsparam_xxxx("foo", Opt_foo) * * If existing helpers are not enough, direct use of __fsparam() would * work, but any such case is probably a sign that new helper is needed. * Helpers will remain stable; low-level implementation may change. */ #define __fsparam(TYPE, NAME, OPT, FLAGS, DATA) \ { \ .name = NAME, \ .opt = OPT, \ .type = TYPE, \ .flags = FLAGS, \ .data = DATA \ } #define fsparam_flag(NAME, OPT) __fsparam(NULL, NAME, OPT, 0, NULL) #define fsparam_flag_no(NAME, OPT) \ __fsparam(NULL, NAME, OPT, fs_param_neg_with_no, NULL) #define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0, NULL) #define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) #define fsparam_string(NAME, OPT) \ __fsparam(fs_param_is_string, NAME, OPT, 0, NULL) #define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0, NULL) #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) #endif /* _LINUX_FS_PARSER_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 */ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/set_memory.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/llist.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> #include <linux/overflow.h> #include <linux/uaccess.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> #include "internal.h" #include "pgalloc-track.h" bool is_vmalloc_addr(const void *x) { unsigned long addr = (unsigned long)x; return addr >= VMALLOC_START && addr < VMALLOC_END; } EXPORT_SYMBOL(is_vmalloc_addr); struct vfree_deferred { struct llist_head list; struct work_struct wq; }; static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); static void __vunmap(const void *, int); static void free_work(struct work_struct *w) { struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); struct llist_node *t, *llnode; llist_for_each_safe(llnode, t, llist_del_all(&p->list)) __vunmap((void *)llnode, 1); } /*** Page table manipulation functions ***/ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; pte = pte_offset_kernel(pmd, addr); do { pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; } static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); cleared = pmd_clear_huge(pmd); if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; if (cleared) continue; if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); cond_resched(); } while (pmd++, addr = next, addr != end); } static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); cleared = pud_clear_huge(pud); if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; if (cleared) continue; if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int cleared; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); cleared = p4d_clear_huge(p4d); if (cleared || p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; if (cleared) continue; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /** * unmap_kernel_range_noflush - unmap kernel VM area * @start: start of the VM area to unmap * @size: size of the VM area to unmap * * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size specify * should have been allocated using get_vm_area() and its friends. * * NOTE: * This function does NOT do any cache flushing. The caller is responsible * for calling flush_cache_vunmap() on to-be-mapped areas before calling this * function and flush_tlb_kernel_range() after. */ void unmap_kernel_range_noflush(unsigned long start, unsigned long size) { unsigned long end = start + size; unsigned long next; pgd_t *pgd; unsigned long addr = start; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); } static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { int err = 0; pte_t *pte; /* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { struct page *page = pages[*nr]; if (WARN_ON(!pte_none(*pte))) { err = -EBUSY; break; } if (WARN_ON(!page)) { err = -ENOMEM; break; } set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; return err; } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; } /** * map_kernel_range_noflush - map kernel VM area with the specified pages * @addr: start of the VM area to map * @size: size of the VM area to map * @prot: page protection flags to use * @pages: pages to map * * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size specify should * have been allocated using get_vm_area() and its friends. * * NOTE: * This function does NOT do any cache flushing. The caller is responsible for * calling flush_cache_vmap() on to-be-mapped areas before calling this * function. * * RETURNS: * 0 on success, -errno on failure. */ int map_kernel_range_noflush(unsigned long addr, unsigned long size, pgprot_t prot, struct page **pages) { unsigned long start = addr; unsigned long end = addr + size; unsigned long next; pgd_t *pgd; int err = 0; int nr = 0; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) return err; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return 0; } int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages) { int ret; ret = map_kernel_range_noflush(start, size, prot, pages); flush_cache_vmap(start, start + size); return ret; } int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_MODULES) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)x; if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } /* * Walk a vmap address to the struct page it maps. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (pgd_none(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; pud = pud_offset(p4d, addr); /* * Don't dereference bad PUD or PMD (below) entries. This will also * identify huge mappings, which we may encounter on architectures * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be * identified as vmalloc addresses by is_vmalloc_addr(), but are * not [unambiguously] associated with a struct page, so there is * no correct value to return for them. */ WARN_ON_ONCE(pud_bad(*pud)); if (pud_none(*pud) || pud_bad(*pud)) return NULL; pmd = pmd_offset(pud, addr); WARN_ON_ONCE(pmd_bad(*pmd)); if (pmd_none(*pmd) || pmd_bad(*pmd)) return NULL; ptep = pte_offset_map(pmd, addr); pte = *ptep; if (pte_present(pte)) page = pte_page(pte); pte_unmap(ptep); return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ unsigned long vmalloc_to_pfn(const void *vmalloc_addr) { return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ #define DEBUG_AUGMENT_PROPAGATE_CHECK 0 #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 static DEFINE_SPINLOCK(vmap_area_lock); static DEFINE_SPINLOCK(free_vmap_area_lock); /* Export for kexec only */ LIST_HEAD(vmap_area_list); static LLIST_HEAD(vmap_purge_list); static struct rb_root vmap_area_root = RB_ROOT; static bool vmap_initialized __read_mostly; /* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to * make things faster. Especially in "no edge" splitting of * free block. */ static struct kmem_cache *vmap_area_cachep; /* * This linked list is used in pair with free_vmap_area_root. * It gives O(1) access to prev/next to perform fast coalescing. */ static LIST_HEAD(free_vmap_area_list); /* * This augment red-black tree represents the free vmap space. * All vmap_area objects in this tree are sorted by va->va_start * address. It is used for allocation and merging when a vmap * object is released. * * Each vmap_area node contains a maximum available free block * of its sub-tree, right or left. Therefore it is possible to * find a lowest match of free area. */ static struct rb_root free_vmap_area_root = RB_ROOT; /* * Preload a CPU with one object for "no edge" split case. The * aim is to get rid of allocations from the atomic context, thus * to use more permissive allocation masks. */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); static __always_inline unsigned long va_size(struct vmap_area *va) { return (va->va_end - va->va_start); } static __always_inline unsigned long get_subtree_max_size(struct rb_node *node) { struct vmap_area *va; va = rb_entry_safe(node, struct vmap_area, rb_node); return va ? va->subtree_max_size : 0; } /* * Gets called when remove the node and rotate. */ static __always_inline unsigned long compute_subtree_max_size(struct vmap_area *va) { return max3(va_size(va), get_subtree_max_size(va->rb_node.rb_left), get_subtree_max_size(va->rb_node.rb_right)); } RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void purge_vmap_area_lazy(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static unsigned long lazy_max_pages(void); static atomic_long_t nr_vmalloc_pages; unsigned long vmalloc_nr_pages(void) { return atomic_long_read(&nr_vmalloc_pages); } static struct vmap_area *__find_vmap_area(unsigned long addr) { struct rb_node *n = vmap_area_root.rb_node; while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr >= va->va_end) n = n->rb_right; else return va; } return NULL; } /* * This function returns back addresses of parent node * and its left or right link for further processing. * * Otherwise NULL is returned. In that case all further * steps regarding inserting of conflicting overlap range * have to be declined and actually considered as a bug. */ static __always_inline struct rb_node ** find_va_links(struct vmap_area *va, struct rb_root *root, struct rb_node *from, struct rb_node **parent) { struct vmap_area *tmp_va; struct rb_node **link; if (root) { link = &root->rb_node; if (unlikely(!*link)) { *parent = NULL; return link; } } else { link = &from; } /* * Go to the bottom of the tree. When we hit the last point * we end up with parent rb_node and correct direction, i name * it link, where the new va->rb_node will be attached to. */ do { tmp_va = rb_entry(*link, struct vmap_area, rb_node); /* * During the traversal we also do some sanity check. * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ if (va->va_start < tmp_va->va_end && va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; else if (va->va_end > tmp_va->va_start && va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; else { WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); return NULL; } } while (*link); *parent = &tmp_va->rb_node; return link; } static __always_inline struct list_head * get_va_next_sibling(struct rb_node *parent, struct rb_node **link) { struct list_head *list; if (unlikely(!parent)) /* * The red-black tree where we try to find VA neighbors * before merging or inserting is empty, i.e. it means * there is no free vmap space. Normally it does not * happen but we handle this case anyway. */ return NULL; list = &rb_entry(parent, struct vmap_area, rb_node)->list; return (&parent->rb_right == link ? list->next : list); } static __always_inline void link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { /* * VA is still not in the list, but we can * identify its future previous list_head node. */ if (likely(parent)) { head = &rb_entry(parent, struct vmap_area, rb_node)->list; if (&parent->rb_right != link) head = head->prev; } /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); if (root == &free_vmap_area_root) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). * It is because of we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, * to let __augment_tree_propagate_from() puts everything to * the correct order later on. */ rb_insert_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); va->subtree_max_size = 0; } else { rb_insert_color(&va->rb_node, root); } /* Address-sort this list */ list_add(&va->list, head); } static __always_inline void unlink_va(struct vmap_area *va, struct rb_root *root) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; if (root == &free_vmap_area_root) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); list_del(&va->list); RB_CLEAR_NODE(&va->rb_node); } #if DEBUG_AUGMENT_PROPAGATE_CHECK static void augment_tree_propagate_check(void) { struct vmap_area *va; unsigned long computed_size; list_for_each_entry(va, &free_vmap_area_list, list) { computed_size = compute_subtree_max_size(va); if (computed_size != va->subtree_max_size) pr_emerg("tree is corrupted: %lu, %lu\n", va_size(va), va->subtree_max_size); } } #endif /* * This function populates subtree_max_size from bottom to upper * levels starting from VA point. The propagation must be done * when VA size is modified by changing its va_start/va_end. Or * in case of newly inserting of VA to the tree. * * It means that __augment_tree_propagate_from() must be called: * - After VA has been inserted to the tree(free path); * - After VA has been shrunk(allocation path); * - After VA has been increased(merging path). * * Please note that, it does not mean that upper parent nodes * and their subtree_max_size are recalculated all the time up * to the root node. * * 4--8 * /\ * / \ * / \ * 2--2 8--8 * * For example if we modify the node 4, shrinking it to 2, then * no any modification is required. If we shrink the node 2 to 1 * its subtree_max_size is updated only, and set to 1. If we shrink * the node 8 to 6, then its subtree_max_size is set to 6 and parent * node becomes 4--6. */ static __always_inline void augment_tree_propagate_from(struct vmap_area *va) { /* * Populate the tree from bottom towards the root until * the calculated maximum available size of checked node * is equal to its current one. */ free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); #if DEBUG_AUGMENT_PROPAGATE_CHECK augment_tree_propagate_check(); #endif } static void insert_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; link = find_va_links(va, root, NULL, &parent); if (link) link_va(va, root, parent, link, head); } static void insert_vmap_area_augment(struct vmap_area *va, struct rb_node *from, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; if (from) link = find_va_links(va, NULL, from, &parent); else link = find_va_links(va, root, NULL, &parent); if (link) { link_va(va, root, parent, link, head); augment_tree_propagate_from(va); } } /* * Merge de-allocated chunk of VA memory with previous * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. * * Please note, it can return NULL in case of overlap * ranges, followed by WARN() report. Despite it is a * buggy behaviour, a system can be alive and keep * ongoing. */ static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { struct vmap_area *sibling; struct list_head *next; struct rb_node **link; struct rb_node *parent; bool merged = false; /* * Find a place in the tree where VA potentially will be * inserted, unless it is merged with its sibling/siblings. */ link = find_va_links(va, root, NULL, &parent); if (!link) return NULL; /* * Get next node of VA to check if merging can be done. */ next = get_va_next_sibling(parent, link); if (unlikely(next == NULL)) goto insert; /* * start end * | | * |<------VA------>|<-----Next----->| * | | * start end */ if (next != head) { sibling = list_entry(next, struct vmap_area, list); if (sibling->va_start == va->va_end) { sibling->va_start = va->va_start; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } /* * start end * | | * |<-----Prev----->|<------VA------>| * | | * start end */ if (next->prev != head) { sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { /* * If both neighbors are coalesced, it is important * to unlink the "next" node first, followed by merging * with "previous" one. Otherwise the tree might not be * fully populated if a sibling's augmented value is * "normalized" because of rotation operations. */ if (merged) unlink_va(va, root); sibling->va_end = va->va_end; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } insert: if (!merged) link_va(va, root, parent, link, head); /* * Last step is to check and update the tree. */ augment_tree_propagate_from(va); return va; } static __always_inline bool is_within_this_va(struct vmap_area *va, unsigned long size, unsigned long align, unsigned long vstart) { unsigned long nva_start_addr; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Can be overflowed due to big size or alignment. */ if (nva_start_addr + size < nva_start_addr || nva_start_addr < vstart) return false; return (nva_start_addr + size <= va->va_end); } /* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing * parameters. */ static __always_inline struct vmap_area * find_vmap_lowest_match(unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ node = free_vmap_area_root.rb_node; /* Adjust the search size for alignment overhead. */ length = size + align - 1; while (node) { va = rb_entry(node, struct vmap_area, rb_node); if (get_subtree_max_size(node->rb_left) >= length && vstart < va->va_start) { node = node->rb_left; } else { if (is_within_this_va(va, size, align, vstart)) return va; /* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is * equal or bigger to the requested search length. */ if (get_subtree_max_size(node->rb_right) >= length) { node = node->rb_right; continue; } /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen * only once due to "vstart" restriction. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va; if (get_subtree_max_size(node->rb_right) >= length && vstart <= va->va_start) { node = node->rb_right; break; } } } } return NULL; } #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK #include <linux/random.h> static struct vmap_area * find_vmap_lowest_linear_match(unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; list_for_each_entry(va, &free_vmap_area_list, list) { if (!is_within_this_va(va, size, align, vstart)) continue; return va; } return NULL; } static void find_vmap_lowest_match_check(unsigned long size) { struct vmap_area *va_1, *va_2; unsigned long vstart; unsigned int rnd; get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; va_1 = find_vmap_lowest_match(size, 1, vstart); va_2 = find_vmap_lowest_linear_match(size, 1, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", va_1, va_2, vstart); } #endif enum fit_type { NOTHING_FIT = 0, FL_FIT_TYPE = 1, /* full fit */ LE_FIT_TYPE = 2, /* left edge fit */ RE_FIT_TYPE = 3, /* right edge fit */ NE_FIT_TYPE = 4 /* no edge fit */ }; static __always_inline enum fit_type classify_va_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { enum fit_type type; /* Check if it is within VA. */ if (nva_start_addr < va->va_start || nva_start_addr + size > va->va_end) return NOTHING_FIT; /* Now classify. */ if (va->va_start == nva_start_addr) { if (va->va_end == nva_start_addr + size) type = FL_FIT_TYPE; else type = LE_FIT_TYPE; } else if (va->va_end == nva_start_addr + size) { type = RE_FIT_TYPE; } else { type = NE_FIT_TYPE; } return type; } static __always_inline int adjust_va_to_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size, enum fit_type type) { struct vmap_area *lva = NULL; if (type == FL_FIT_TYPE) { /* * No need to split VA, it fully fits. * * | | * V NVA V * |---------------| */ unlink_va(va, &free_vmap_area_root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* * Split left edge of fit VA. * * | | * V NVA V R * |-------|-------| */ va->va_start += size; } else if (type == RE_FIT_TYPE) { /* * Split right edge of fit VA. * * | | * L V NVA V * |-------|-------| */ va->va_end = nva_start_addr; } else if (type == NE_FIT_TYPE) { /* * Split no edge of fit VA. * * | | * L V NVA V R * |---|-------|---| */ lva = __this_cpu_xchg(ne_fit_preload_node, NULL); if (unlikely(!lva)) { /* * For percpu allocator we do not do any pre-allocation * and leave it as it is. The reason is it most likely * never ends up with NE_FIT_TYPE splitting. In case of * percpu allocations offsets and sizes are aligned to * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE * are its main fitting cases. * * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. * * Also we can hit this path in case of regular "vmap" * allocations, if "this" current CPU was not preloaded. * See the comment in alloc_vmap_area() why. If so, then * GFP_NOWAIT is used instead to get an extra object for * split purpose. That is rare and most time does not * occur. * * What happens if an allocation gets failed. Basically, * an "overflow" path is triggered to purge lazily freed * areas to free some memory, then, the "retry" path is * triggered to repeat one more time. See more details * in alloc_vmap_area() function. */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) return -1; } /* * Build the remainder. */ lva->va_start = va->va_start; lva->va_end = nva_start_addr; /* * Shrink this VA to remaining size. */ va->va_start = nva_start_addr + size; } else { return -1; } if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, &free_vmap_area_root, &free_vmap_area_list); } return 0; } /* * Returns a start address of the newly allocated area, if success. * Otherwise a vend is returned that indicates failure. */ static __always_inline unsigned long __alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; struct vmap_area *va; enum fit_type type; int ret; va = find_vmap_lowest_match(size, align, vstart); if (unlikely(!va)) return vend; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) return vend; /* Classify what we have found. */ type = classify_va_fit_type(va, nva_start_addr, size); if (WARN_ON_ONCE(type == NOTHING_FIT)) return vend; /* Update the free vmap_area. */ ret = adjust_va_to_fit_type(va, nva_start_addr, size, type); if (ret) return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK find_vmap_lowest_match_check(size); #endif return nva_start_addr; } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { /* * Remove from the busy tree/list. */ spin_lock(&vmap_area_lock); unlink_va(va, &vmap_area_root); spin_unlock(&vmap_area_lock); /* * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask) { struct vmap_area *va, *pva; unsigned long addr; int purged = 0; int ret; BUG_ON(!size); BUG_ON(offset_in_page(size)); BUG_ON(!is_power_of_2(align)); if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); might_sleep(); gfp_mask = gfp_mask & GFP_RECLAIM_MASK; va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); /* * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); retry: /* * Preload this CPU with one extra vmap_area object. It is used * when fit type of free area is NE_FIT_TYPE. Please note, it * does not guarantee that an allocation occurs on a CPU that * is preloaded, instead we minimize the case when it is not. * It can happen because of cpu migration, because there is a * race until the below spinlock is taken. * * The preload is done in non-atomic context, thus it allows us * to use more permissive allocation masks to be more stable under * low memory condition and high memory pressure. In rare case, * if not preloaded, GFP_NOWAIT is used. * * Set "pva" to NULL here, because of "retry" path. */ pva = NULL; if (!this_cpu_read(ne_fit_preload_node)) /* * Even if it fails we do not really care about that. * Just proceed as it is. If needed "overflow" path * will refill the cache we allocate from. */ pva = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); spin_lock(&free_vmap_area_lock); if (pva && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) kmem_cache_free(vmap_area_cachep, pva); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ addr = __alloc_vmap_area(size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); if (unlikely(addr == vend)) goto overflow; va->va_start = addr; va->va_end = addr + size; va->vm = NULL; spin_lock(&vmap_area_lock); insert_vmap_area(va, &vmap_area_root, &vmap_area_list); spin_unlock(&vmap_area_lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); ret = kasan_populate_vmalloc(addr, size); if (ret) { free_vmap_area(va); return ERR_PTR(ret); } return va; overflow: if (!purged) { purge_vmap_area_lazy(); purged = 1; goto retry; } if (gfpflags_allow_blocking(gfp_mask)) { unsigned long freed = 0; blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); if (freed > 0) { purged = 0; goto retry; } } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n", size); kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } int register_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); int unregister_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* * Serialize vmap purging. There is no actual criticial section protected * by this look, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); /* * called before a call to iounmap() if the caller wants vm_area_struct's * immediately freed. */ void set_iounmap_nonlazy(void) { atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); } /* * Purges all lazily-freed vmap areas. */ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) { unsigned long resched_threshold; struct llist_node *valist; struct vmap_area *va; struct vmap_area *n_va; lockdep_assert_held(&vmap_purge_lock); valist = llist_del_all(&vmap_purge_list); if (unlikely(valist == NULL)) return false; /* * TODO: to calculate a flush range without looping. * The list can be up to lazy_max_pages() elements. */ llist_for_each_entry(va, valist, purge_list) { if (va->va_start < start) start = va->va_start; if (va->va_end > end) end = va->va_end; } flush_tlb_kernel_range(start, end); resched_threshold = lazy_max_pages() << 1; spin_lock(&free_vmap_area_lock); llist_for_each_entry_safe(va, n_va, valist, purge_list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; unsigned long orig_start = va->va_start; unsigned long orig_end = va->va_end; /* * Finally insert or merge lazily-freed area. It is * detached and there is no need to "unlink" it from * anything. */ va = merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); if (!va) continue; if (is_vmalloc_or_module_addr((void *)orig_start)) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); atomic_long_sub(nr, &vmap_lazy_nr); if (atomic_long_read(&vmap_lazy_nr) < resched_threshold) cond_resched_lock(&free_vmap_area_lock); } spin_unlock(&free_vmap_area_lock); return true; } /* * Kick off a purge of the outstanding lazy areas. Don't bother if somebody * is already purging. */ static void try_purge_vmap_area_lazy(void) { if (mutex_trylock(&vmap_purge_lock)) { __purge_vmap_area_lazy(ULONG_MAX, 0); mutex_unlock(&vmap_purge_lock); } } /* * Kick off a purge of the outstanding lazy areas. */ static void purge_vmap_area_lazy(void) { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); __purge_vmap_area_lazy(ULONG_MAX, 0); mutex_unlock(&vmap_purge_lock); } /* * Free a vmap area, caller ensuring that the area has been unmapped * and flush_cache_vunmap had been called for the correct range * previously. */ static void free_vmap_area_noflush(struct vmap_area *va) { unsigned long nr_lazy; spin_lock(&vmap_area_lock); unlink_va(va, &vmap_area_root); spin_unlock(&vmap_area_lock); nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); /* After this point, we may free va at any time */ llist_add(&va->purge_list, &vmap_purge_list); if (unlikely(nr_lazy > lazy_max_pages())) try_purge_vmap_area_lazy(); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); unmap_kernel_range_noflush(va->va_start, va->va_end - va->va_start); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); } static struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_area *va; spin_lock(&vmap_area_lock); va = __find_vmap_area(addr); spin_unlock(&vmap_area_lock); return va; } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS \ VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) struct vmap_block_queue { spinlock_t lock; struct list_head free; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * XArray of vmap blocks, indexed by address, to quickly find a vmap block * in the free path. Could get rid of this if we change the API to return a * "cookie" from alloc, to be passed to free. But no big deal yet. */ static DEFINE_XARRAY(vmap_blocks); /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) { unsigned long addr; addr = va_start + (pages_off << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); return (void *)addr; } /** * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this * block. Of course pages number can't exceed VMAP_BBMAP_BITS * @order: how many 2^order pages should be occupied in newly allocated block * @gfp_mask: flags for the page level allocator * * Return: virtual address in a newly allocated block or ERR_PTR(-errno) */ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; int node, err; void *vaddr; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; /* At least something should be left free */ BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; INIT_LIST_HEAD(&vb->free_list); vb_idx = addr_to_vb_idx(va->va_start); err = xa_insert(&vmap_blocks, vb_idx, vb, gfp_mask); if (err) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } vbq = &get_cpu_var(vmap_block_queue); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); put_cpu_var(vmap_block_queue); return vaddr; } static void free_vmap_block(struct vmap_block *vb) { struct vmap_block *tmp; tmp = xa_erase(&vmap_blocks, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); } static void purge_fragmented_blocks(int cpu) { LIST_HEAD(purge); struct vmap_block *vb; struct vmap_block *n_vb; struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS)) continue; spin_lock(&vb->lock); if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { vb->free = 0; /* prevent further allocs after releasing lock */ vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ vb->dirty_min = 0; vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); spin_unlock(&vb->lock); list_add_tail(&vb->purge, &purge); } else spin_unlock(&vb->lock); } rcu_read_unlock(); list_for_each_entry_safe(vb, n_vb, &purge, purge) { list_del(&vb->purge); free_vmap_block(vb); } } static void purge_fragmented_blocks_allcpus(void) { int cpu; for_each_possible_cpu(cpu) purge_fragmented_blocks(cpu); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; void *vaddr = NULL; unsigned int order; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); if (WARN_ON(size == 0)) { /* * Allocating 0 bytes isn't what caller wants since * get_order(0) returns funny result. Just warn and terminate * early. */ return NULL; } order = get_order(size); rcu_read_lock(); vbq = &get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; spin_lock(&vb->lock); if (vb->free < (1UL << order)) { spin_unlock(&vb->lock); continue; } pages_off = VMAP_BBMAP_BITS - vb->free; vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); vb->free -= 1UL << order; if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } put_cpu_var(vmap_block_queue); rcu_read_unlock(); /* Allocate new block if nothing was found */ if (!vaddr) vaddr = new_vmap_block(order, gfp_mask); return vaddr; } static void vb_free(unsigned long addr, unsigned long size) { unsigned long offset; unsigned int order; struct vmap_block *vb; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); flush_cache_vunmap(addr, addr + size); order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; vb = xa_load(&vmap_blocks, addr_to_vb_idx(addr)); unmap_kernel_range_noflush(addr, size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); spin_lock(&vb->lock); /* Expand dirty range */ vb->dirty_min = min(vb->dirty_min, offset); vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { int cpu; if (unlikely(!vmap_initialized)) return; might_sleep(); for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { spin_lock(&vb->lock); if (vb->dirty) { unsigned long va_start = vb->va->va_start; unsigned long s, e; s = va_start + (vb->dirty_min << PAGE_SHIFT); e = va_start + (vb->dirty_max << PAGE_SHIFT); start = min(s, start); end = max(e, end); flush = 1; } spin_unlock(&vb->lock); } rcu_read_unlock(); } mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); if (!__purge_vmap_area_lazy(start, end) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { unsigned long start = ULONG_MAX, end = 0; int flush = 0; _vm_unmap_aliases(start, end, flush); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr = (unsigned long)mem; struct vmap_area *va; might_sleep(); BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); kasan_poison_vmalloc(mem, size); if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(addr, size); return; } va = find_vmap_area(addr); BUG_ON(!va); debug_check_no_locks_freed((void *)va->va_start, (va->va_end - va->va_start)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life * objects with vm_map_ram(), it could consume lots of address space through * fragmentation (especially on a 32bit machine). You could see failures in * the end. Please use this function for short-lived objects. * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } kasan_unpoison_vmalloc(mem, size); if (map_kernel_range(addr, size, PAGE_KERNEL, pages) < 0) { vm_unmap_ram(mem, count); return NULL; } return mem; } EXPORT_SYMBOL(vm_map_ram); static struct vm_struct *vmlist __initdata; /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add * * This function is used to add fixed kernel vm area to vmlist before * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags * should contain proper values and the other fields should be zero. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_add_early(struct vm_struct *vm) { struct vm_struct *tmp, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) { BUG_ON(tmp->addr < vm->addr + vm->size); break; } else BUG_ON(tmp->addr + tmp->size > vm->addr); } vm->next = *p; *p = vm; } /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { static size_t vm_init_off __initdata; unsigned long addr; addr = ALIGN(VMALLOC_START + vm_init_off, align); vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; vm->addr = (void *)addr; vm_area_add_early(vm); } static void vmap_init_free_space(void) { unsigned long vmap_start = 1; const unsigned long vmap_end = ULONG_MAX; struct vmap_area *busy, *free; /* * B F B B B F * -|-----|.....|-----|-----|-----|.....|- * | The KVA space | * |<--------------------------------->| */ list_for_each_entry(busy, &vmap_area_list, list) { if (busy->va_start - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = busy->va_start; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } vmap_start = busy->va_end; } if (vmap_end - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = vmap_end; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } } void __init vmalloc_init(void) { struct vmap_area *va; struct vm_struct *tmp; int i; /* * Create the cache for vmap_area objects. */ vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); for_each_possible_cpu(i) { struct vmap_block_queue *vbq; struct vfree_deferred *p; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); p = &per_cpu(vfree_deferred, i); init_llist_head(&p->list); INIT_WORK(&p->wq, free_work); } /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (WARN_ON_ONCE(!va)) continue; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; va->vm = tmp; insert_vmap_area(va, &vmap_area_root, &vmap_area_list); } /* * Now we can initialize a free vmap space. */ vmap_init_free_space(); vmap_initialized = true; } /** * unmap_kernel_range - unmap kernel VM area and flush cache and TLB * @addr: start of the VM area to unmap * @size: size of the VM area to unmap * * Similar to unmap_kernel_range_noflush() but flushes vcache before * the unmapping and tlb after. */ void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; flush_cache_vunmap(addr, end); unmap_kernel_range_noflush(addr, size); flush_tlb_kernel_range(addr, end); } static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->vm = vm; } static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { spin_lock(&vmap_area_lock); setup_vmalloc_vm_locked(vm, va, flags, caller); spin_unlock(&vmap_area_lock); } static void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. * Pair with smp_rmb() in show_numa_info(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); size = PAGE_ALIGN(size); if (unlikely(!size)) return NULL; if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; va = alloc_vmap_area(size, align, start, end, node, gfp_mask); if (IS_ERR(va)) { kfree(area); return NULL; } kasan_unpoison_vmalloc((void *)va->va_start, requested_size); setup_vmalloc_vm(area, va, flags, caller); return area; } struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * find_vm_area - find a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and return it. * It is up to the caller to do all required locking to keep the returned * pointer valid. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (!va) return NULL; return va->vm; } /** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; might_sleep(); spin_lock(&vmap_area_lock); va = __find_vmap_area((unsigned long)addr); if (va && va->vm) { struct vm_struct *vm = va->vm; va->vm = NULL; spin_unlock(&vmap_area_lock); kasan_free_shadow(vm); free_unmap_vmap_area(va); return vm; } spin_unlock(&vmap_area_lock); return NULL; } static inline void set_area_direct_map(const struct vm_struct *area, int (*set_direct_map)(struct page *page)) { int i; for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i])) set_direct_map(area->pages[i]); } /* Handle removing and resetting vm mappings related to the vm_struct. */ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) { unsigned long start = ULONG_MAX, end = 0; int flush_reset = area->flags & VM_FLUSH_RESET_PERMS; int flush_dmap = 0; int i; remove_vm_area(area->addr); /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */ if (!flush_reset) return; /* * If not deallocating pages, just do the flush of the VM area and * return. */ if (!deallocate_pages) { vm_unmap_aliases(); return; } /* * If execution gets here, flush the vm mapping and reset the direct * map. Find the start and end range of the direct mappings to make sure * the vm_unmap_aliases() flush includes the direct map. */ for (i = 0; i < area->nr_pages; i++) { unsigned long addr = (unsigned long)page_address(area->pages[i]); if (addr) { start = min(addr, start); end = max(addr + PAGE_SIZE, end); flush_dmap = 1; } } /* * Set direct map to something invalid so that it won't be cached if * there are any accesses after the TLB flush, then flush the TLB and * reset the direct map permissions to the default. */ set_area_direct_map(area, set_direct_map_invalid_noflush); _vm_unmap_aliases(start, end, flush_dmap); set_area_direct_map(area, set_direct_map_default_noflush); } static void __vunmap(const void *addr, int deallocate_pages) { struct vm_struct *area; if (!addr) return; if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", addr)) return; area = find_vm_area(addr); if (unlikely(!area)) { WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr); return; } debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); kasan_poison_vmalloc(area->addr, get_vm_area_size(area)); vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { int i; for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); __free_pages(page, 0); } if (!(area->flags & VM_MAP_PUT_PAGES)) atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); kvfree(area->pages); } kfree(area); return; } static inline void __vfree_deferred(const void *addr) { /* * Use raw_cpu_ptr() because this can be called from preemptible * context. Preemption is absolutely fine here, because the llist_add() * implementation is lockless, so it works even if we are adding to * another cpu's list. schedule_work() should be fine with this too. */ struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); if (llist_add((struct llist_node *)addr, &p->list)) schedule_work(&p->wq); } /** * vfree_atomic - release memory allocated by vmalloc() * @addr: memory base address * * This one is just like vfree() but can be called in any atomic context * except NMIs. */ void vfree_atomic(const void *addr) { BUG_ON(in_nmi()); kmemleak_free(addr); if (!addr) return; __vfree_deferred(addr); } static void __vfree(const void *addr) { if (unlikely(in_interrupt())) __vfree_deferred(addr); else __vunmap(addr, 1); } /** * vfree - Release memory allocated by vmalloc() * @addr: Memory base address * * Free the virtually continuous memory area starting at @addr, as obtained * from one of the vmalloc() family of APIs. This will usually also free the * physical memory underlying the virtual allocation, but that memory is * reference counted, so it will not be freed until the last user goes away. * * If @addr is NULL, no operation is performed. * * Context: * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-depenedent would be a really bad idea). */ void vfree(const void *addr) { BUG_ON(in_nmi()); kmemleak_free(addr); might_sleep_if(!in_interrupt()); if (!addr) return; __vfree(addr); } EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context. */ void vunmap(const void *addr) { BUG_ON(in_interrupt()); might_sleep(); if (addr) __vunmap(addr, 0); } EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual space. * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself * (which must be kmalloc or vmalloc memory) and one reference per pages in it * are transferred from the caller to vmap(), and will be freed / dropped when * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; unsigned long size; /* In bytes */ might_sleep(); if (count > totalram_pages()) return NULL; size = (unsigned long)count << PAGE_SHIFT; area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL; if (map_kernel_range((unsigned long)area->addr, size, pgprot_nx(prot), pages) < 0) { vunmap(area->addr); return NULL; } if (flags & VM_MAP_PUT_PAGES) { area->pages = pages; area->nr_pages = count; } return area->addr; } EXPORT_SYMBOL(vmap); #ifdef CONFIG_VMAP_PFN struct vmap_pfn_data { unsigned long *pfns; pgprot_t prot; unsigned int idx; }; static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) { struct vmap_pfn_data *data = private; if (WARN_ON_ONCE(pfn_valid(data->pfns[data->idx]))) return -EINVAL; *pte = pte_mkspecial(pfn_pte(data->pfns[data->idx++], data->prot)); return 0; } /** * vmap_pfn - map an array of PFNs into virtually contiguous space * @pfns: array of PFNs * @count: number of pages to map * @prot: page protection for the mapping * * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns * the start address of the mapping. */ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) { struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; struct vm_struct *area; area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, __builtin_return_address(0)); if (!area) return NULL; if (apply_to_page_range(&init_mm, (unsigned long)area->addr, count * PAGE_SIZE, vmap_pfn_apply, &data)) { free_vm_area(area); return NULL; } flush_cache_vmap((unsigned long)area->addr, (unsigned long)area->addr + count * PAGE_SIZE); return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, int node) { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; unsigned int nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; unsigned int array_size = nr_pages * sizeof(struct page *), i; struct page **pages; gfp_mask |= __GFP_NOWARN; if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, 1, nested_gfp, node, area->caller); } else { pages = kmalloc_node(array_size, nested_gfp, node); } if (!pages) { remove_vm_area(area->addr); kfree(area); return NULL; } area->pages = pages; area->nr_pages = nr_pages; for (i = 0; i < area->nr_pages; i++) { struct page *page; if (node == NUMA_NO_NODE) page = alloc_page(gfp_mask); else page = alloc_pages_node(node, gfp_mask, 0); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vfree() */ area->nr_pages = i; atomic_long_add(area->nr_pages, &nr_vmalloc_pages); goto fail; } area->pages[i] = page; if (gfpflags_allow_blocking(gfp_mask)) cond_resched(); } atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area), prot, pages) < 0) goto fail; return area->addr; fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); __vfree(area->addr); return NULL; } /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @start: vm area range start * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. * * Return: the address of the area or %NULL on failure */ void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { struct vm_struct *area; void *addr; unsigned long real_size = size; size = PAGE_ALIGN(size); if (!size || (size >> PAGE_SHIFT) > totalram_pages()) goto fail; area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) goto fail; addr = __vmalloc_area_node(area, gfp_mask, prot, node); if (!addr) return NULL; /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. * Now, it is fully initialized, so remove this flag here. */ clear_vm_uninitialized_flag(area); kmemleak_vmalloc(area, size, gfp_mask); return addr; fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure: %lu bytes", real_size); return NULL; } /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted * with mm people. * * Return: pointer to the allocated memory or %NULL on error */ void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* * This is only for performance analysis of vmalloc and stress purpose. * It is required by vmalloc test module, therefore do not use it other * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE EXPORT_SYMBOL_GPL(__vmalloc_node); #endif void *__vmalloc(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc); /** * vmalloc - allocate virtually contiguous memory * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc(unsigned long size) { return __vmalloc_node(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc); /** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc(unsigned long size) { return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_user(unsigned long size) { return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_user); /** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_node(unsigned long size, int node) { return __vmalloc_node(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node); /** * vzalloc_node - allocate memory on a specific node with zero fill * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_node(unsigned long size, int node) { return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_node); #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else /* * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ #define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32(unsigned long size) { return __vmalloc_node(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_user(unsigned long size) { return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_user); /* * small helper routine , copy contents to buf from addr. * If the page is not present, fill zero. */ static int aligned_vread(char *buf, char *addr, unsigned long count) { struct page *p; int copied = 0; while (count) { unsigned long offset, length; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > count) length = count; p = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need * lock. But adding lock here means that we need to add * overhead of vmalloc()/vfree() calles for this _debug_ * interface, rarely used. Instead of that, we'll use * kmap() and get small overhead in this access function. */ if (p) { /* * we can expect USER0 is not used (see vread/vwrite's * function description) */ void *map = kmap_atomic(p); memcpy(buf, map + offset, length); kunmap_atomic(map); } else memset(buf, 0, length); addr += length; buf += length; copied += length; count -= length; } return copied; } static int aligned_vwrite(char *buf, char *addr, unsigned long count) { struct page *p; int copied = 0; while (count) { unsigned long offset, length; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > count) length = count; p = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need * lock. But adding lock here means that we need to add * overhead of vmalloc()/vfree() calles for this _debug_ * interface, rarely used. Instead of that, we'll use * kmap() and get small overhead in this access function. */ if (p) { /* * we can expect USER0 is not used (see vread/vwrite's * function description) */ void *map = kmap_atomic(p); memcpy(map + offset, buf, length); kunmap_atomic(map); } addr += length; buf += length; copied += length; count -= length; } return copied; } /** * vread() - read vmalloc area in a safe way. * @buf: buffer for reading data * @addr: vm address. * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range * of [addr...addr+count) includes some valid address, data is copied to * proper area of @buf. If there are memory holes, they'll be zero-filled. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any information, as /dev/kmem. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ long vread(char *buf, char *addr, unsigned long count) { struct vmap_area *va; struct vm_struct *vm; char *vaddr, *buf_start = buf; unsigned long buflen = count; unsigned long n; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; spin_lock(&vmap_area_lock); list_for_each_entry(va, &vmap_area_list, list) { if (!count) break; if (!va->vm) continue; vm = va->vm; vaddr = (char *) vm->addr; if (addr >= vaddr + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) goto finished; *buf = '\0'; buf++; addr++; count--; } n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; if (!(vm->flags & VM_IOREMAP)) aligned_vread(buf, addr, n); else /* IOREMAP area is treated as memory hole */ memset(buf, 0, n); buf += n; addr += n; count -= n; } finished: spin_unlock(&vmap_area_lock); if (buf == buf_start) return 0; /* zero-fill memory holes */ if (buf != buf_start + buflen) memset(buf, 0, buflen - (buf - buf_start)); return buflen; } /** * vwrite() - write vmalloc area in a safe way. * @buf: buffer for source data * @addr: vm address. * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from a buffer to the given addr. If specified range of * [addr...addr+count) includes some valid address, data is copied from * proper area of @buf. If there are memory holes, no copy to hole. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vwrite() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any information, as /dev/kmem. * * Return: number of bytes for which addr and buf should be * increased (same number as @count) or %0 if [addr...addr+count) * doesn't include any intersection with valid vmalloc area */ long vwrite(char *buf, char *addr, unsigned long count) { struct vmap_area *va; struct vm_struct *vm; char *vaddr; unsigned long n, buflen; int copied = 0; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; buflen = count; spin_lock(&vmap_area_lock); list_for_each_entry(va, &vmap_area_list, list) { if (!count) break; if (!va->vm) continue; vm = va->vm; vaddr = (char *) vm->addr; if (addr >= vaddr + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) goto finished; buf++; addr++; count--; } n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; if (!(vm->flags & VM_IOREMAP)) { aligned_vwrite(buf, addr, n); copied++; } buf += n; addr += n; count -= n; } finished: spin_unlock(&vmap_area_lock); if (!copied) return 0; return buflen; } /** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure * * This function checks that @kaddr is a valid vmalloc'ed area, * and that it is big enough to cover the range starting at * @uaddr in @vma. Will return failure if that criteria isn't * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size) { struct vm_struct *area; unsigned long off; unsigned long end_index; if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) return -EINVAL; size = PAGE_ALIGN(size); if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) return -EINVAL; if (check_add_overflow(size, off, &end_index) || end_index > get_vm_area_size(area)) return -EINVAL; kaddr += off; do { struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; kaddr += PAGE_SIZE; size -= PAGE_SIZE; } while (size > 0); vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; return 0; } EXPORT_SYMBOL(remap_vmalloc_range_partial); /** * remap_vmalloc_range - map vmalloc pages to userspace * @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map * * Returns: 0 for success, -Exxx on failure * * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP static struct vmap_area *node_to_va(struct rb_node *n) { return rb_entry_safe(n, struct vmap_area, rb_node); } /** * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to * @addr: target address * * Returns: vmap_area if it is found. If there is no such area * the first highest(reverse order) vmap_area is returned * i.e. va->va_start < addr && va->va_end < addr or NULL * if there are no any areas before @addr. */ static struct vmap_area * pvm_find_va_enclose_addr(unsigned long addr) { struct vmap_area *va, *tmp; struct rb_node *n; n = free_vmap_area_root.rb_node; va = NULL; while (n) { tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_start <= addr) { va = tmp; if (tmp->va_end >= addr) break; n = n->rb_right; } else { n = n->rb_left; } } return va; } /** * pvm_determine_end_from_reverse - find the highest aligned address * of free block below VMALLOC_END * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. * * Returns: determined end address within vmap_area */ static unsigned long pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align) { unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); unsigned long addr; if (likely(*va)) { list_for_each_entry_from_reverse((*va), &free_vmap_area_list, list) { addr = min((*va)->va_end & ~(align - 1), vmalloc_end); if ((*va)->va_start < addr) return addr; } } return 0; } /** * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator * @offsets: array containing offset of each area * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to * be scattered pretty far, distance between two areas easily going up * to gigabytes. To avoid interacting with regular vmallocs, these * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans free blocks from the end looking * for matching base. While scanning, if any of the areas do not fit the * base address is pulled down to fit the area. Scanning is repeated till * all the areas fit and then all necessary data structures are inserted * and the result is returned. */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; enum fit_type type; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { start = offsets[area]; end = start + sizes[area]; /* is everything aligned properly? */ BUG_ON(!IS_ALIGNED(offsets[area], align)); BUG_ON(!IS_ALIGNED(sizes[area], align)); /* detect the area with the highest address */ if (start > offsets[last_area]) last_area = area; for (area2 = area + 1; area2 < nr_vms; area2++) { unsigned long start2 = offsets[area2]; unsigned long end2 = start2 + sizes[area2]; BUG_ON(start2 < end && start < end2); } } last_end = offsets[last_area] + sizes[last_area]; if (vmalloc_end - vmalloc_start < last_end) { WARN_ON(true); return NULL; } vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL); vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL); if (!vas || !vms) goto err_free2; for (area = 0; area < nr_vms; area++) { vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL); vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free; } retry: spin_lock(&free_vmap_area_lock); /* start scanning - we scan from the top, begin with the last area */ area = term_area = last_area; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(vmalloc_end); base = pvm_determine_end_from_reverse(&va, align) - end; while (true) { /* * base might have underflowed, add last_end before * comparing. */ if (base + last_end < vmalloc_start + last_end) goto overflow; /* * Fitting base has not been found. */ if (va == NULL) goto overflow; /* * If required width exceeds current VA block, move * base downwards and then recheck. */ if (base + end > va->va_end) { base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * If this VA does not fit, move base downwards and recheck. */ if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * This area fits, move on to the previous one. If * the previous one is the terminal one, we're done. */ area = (area + nr_vms - 1) % nr_vms; if (area == term_area) break; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(base + end); } /* we've found a fitting base, insert all va's */ for (area = 0; area < nr_vms; area++) { int ret; start = base + offsets[area]; size = sizes[area]; va = pvm_find_va_enclose_addr(start); if (WARN_ON_ONCE(va == NULL)) /* It is a BUG(), but trigger recovery instead. */ goto recovery; type = classify_va_fit_type(va, start, size); if (WARN_ON_ONCE(type == NOTHING_FIT)) /* It is a BUG(), but trigger recovery instead. */ goto recovery; ret = adjust_va_to_fit_type(va, start, size, type); if (unlikely(ret)) goto recovery; /* Allocated area. */ va = vas[area]; va->va_start = start; va->va_end = start + size; } spin_unlock(&free_vmap_area_lock); /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) goto err_free_shadow; kasan_unpoison_vmalloc((void *)vas[area]->va_start, sizes[area]); } /* insert all vm's */ spin_lock(&vmap_area_lock); for (area = 0; area < nr_vms; area++) { insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list); setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); } spin_unlock(&vmap_area_lock); kfree(vas); return vms; recovery: /* * Remove previously allocated areas. There is no * need in removing these areas from the busy tree, * because they are inserted only on the final step * and when pcpu_get_vm_areas() is success. */ while (area--) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); vas[area] = NULL; } overflow: spin_unlock(&free_vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); purged = true; /* Before "retry", check if we recover. */ for (area = 0; area < nr_vms; area++) { if (vas[area]) continue; vas[area] = kmem_cache_zalloc( vmap_area_cachep, GFP_KERNEL); if (!vas[area]) goto err_free; } goto retry; } err_free: for (area = 0; area < nr_vms; area++) { if (vas[area]) kmem_cache_free(vmap_area_cachep, vas[area]); kfree(vms[area]); } err_free2: kfree(vas); kfree(vms); return NULL; err_free_shadow: spin_lock(&free_vmap_area_lock); /* * We release all the vmalloc shadows, even the ones for regions that * hadn't been successfully added. This relies on kasan_release_vmalloc * being able to tolerate this case. */ for (area = 0; area < nr_vms; area++) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); vas[area] = NULL; kfree(vms[area]); } spin_unlock(&free_vmap_area_lock); kfree(vas); kfree(vms); return NULL; } /** * pcpu_free_vm_areas - free vmalloc areas for percpu allocator * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() * @nr_vms: the number of allocated areas * * Free vm_structs and the array allocated by pcpu_get_vm_areas(). */ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { int i; for (i = 0; i < nr_vms; i++) free_vm_area(vms[i]); kfree(vms); } #endif /* CONFIG_SMP */ #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) __acquires(&vmap_purge_lock) __acquires(&vmap_area_lock) { mutex_lock(&vmap_purge_lock); spin_lock(&vmap_area_lock); return seq_list_start(&vmap_area_list, *pos); } static void *s_next(struct seq_file *m, void *p, loff_t *pos) { return seq_list_next(p, &vmap_area_list, pos); } static void s_stop(struct seq_file *m, void *p) __releases(&vmap_area_lock) __releases(&vmap_purge_lock) { spin_unlock(&vmap_area_lock); mutex_unlock(&vmap_purge_lock); } static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { unsigned int nr, *counters = m->private; if (!counters) return; if (v->flags & VM_UNINITIALIZED) return; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr++) counters[page_to_nid(v->pages[nr])]++; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } } static void show_purge_info(struct seq_file *m) { struct llist_node *head; struct vmap_area *va; head = READ_ONCE(vmap_purge_list.first); if (head == NULL) return; llist_for_each_entry(va, head, purge_list) { seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); } } static int s_show(struct seq_file *m, void *p) { struct vmap_area *va; struct vm_struct *v; va = list_entry(p, struct vmap_area, list); /* * s_show can encounter race with remove_vm_area, !vm on behalf * of vmap area is being tear down or vm_map_ram allocation. */ if (!va->vm) { seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); return 0; } v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); if (v->caller) seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%pa", &v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) seq_puts(m, " user"); if (v->flags & VM_DMA_COHERENT) seq_puts(m, " dma-coherent"); if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); /* * As a final step, dump "unpurged" areas. Note, * that entire "/proc/vmallocinfo" output will not * be address sorted, because the purge list is not * sorted. */ if (list_is_last(&va->list, &vmap_area_list)) show_purge_info(m); return 0; } static const struct seq_operations vmalloc_op = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show, }; static int __init proc_vmalloc_init(void) { if (IS_ENABLED(CONFIG_NUMA)) proc_create_seq_private("vmallocinfo", 0400, NULL, &vmalloc_op, nr_node_ids * sizeof(unsigned int), NULL); else proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op); return 0; } module_init(proc_vmalloc_init); #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | // SPDX-License-Identifier: GPL-2.0-only /* * A generic implementation of binary search for the Linux kernel * * Copyright (C) 2008-2009 Ksplice, Inc. * Author: Tim Abbott <tabbott@ksplice.com> */ #include <linux/export.h> #include <linux/bsearch.h> #include <linux/kprobes.h> /* * bsearch - binary search an array of elements * @key: pointer to item being searched for * @base: pointer to first element to search * @num: number of elements * @size: size of each element * @cmp: pointer to comparison function * * This function does a binary search on the given array. The * contents of the array should already be in ascending sorted order * under the provided comparison function. * * Note that the key need not have the same type as the elements in * the array, e.g. key could be a string and the comparison function * could compare the string with the struct's name field. However, if * the key and elements in the array are of the same type, you can use * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { return __inline_bsearch(key, base, num, size, cmp); } EXPORT_SYMBOL(bsearch); NOKPROBE_SYMBOL(bsearch); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * fs/kernfs/kernfs-internal.h - kernfs internal header file * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de> */ #ifndef __KERNFS_INTERNAL_H #define __KERNFS_INTERNAL_H #include <linux/lockdep.h> #include <linux/fs.h> #include <linux/mutex.h> #include <linux/xattr.h> #include <linux/kernfs.h> #include <linux/fs_context.h> struct kernfs_iattrs { kuid_t ia_uid; kgid_t ia_gid; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; struct simple_xattrs xattrs; atomic_t nr_user_xattrs; atomic_t user_xattr_size; }; /* +1 to avoid triggering overflow warning when negating it */ #define KN_DEACTIVATED_BIAS (INT_MIN + 1) /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */ /** * kernfs_root - find out the kernfs_root a kernfs_node belongs to * @kn: kernfs_node of interest * * Return the kernfs_root @kn belongs to. */ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) { /* if parent exists, it's always a dir; otherwise, @sd is a dir */ if (kn->parent) kn = kn->parent; return kn->dir.root; } /* * mount.c */ struct kernfs_super_info { struct super_block *sb; /* * The root associated with this super_block. Each super_block is * identified by the root and ns it's associated with. */ struct kernfs_root *root; /* * Each sb is associated with one namespace tag, currently the * network namespace of the task which mounted this kernfs * instance. If multiple tags become necessary, make the following * an array and compare kernfs_node tag against every entry. */ const void *ns; /* anchored at kernfs_root->supers, protected by kernfs_mutex */ struct list_head node; }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) return NULL; return d_inode(dentry)->i_private; } extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c */ extern const struct xattr_handler *kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); int kernfs_iop_permission(struct inode *inode, int mask); int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr); int kernfs_iop_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); /* * dir.c */ extern struct mutex kernfs_mutex; extern const struct dentry_operations kernfs_dops; extern const struct file_operations kernfs_dir_fops; extern const struct inode_operations kernfs_dir_iops; struct kernfs_node *kernfs_get_active(struct kernfs_node *kn); void kernfs_put_active(struct kernfs_node *kn); int kernfs_add_one(struct kernfs_node *kn); struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags); /* * file.c */ extern const struct file_operations kernfs_file_fops; void kernfs_drain_open_files(struct kernfs_node *kn); /* * symlink.c */ extern const struct inode_operations kernfs_symlink_iops; #endif /* __KERNFS_INTERNAL_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr ) __field( void *, location ) __field( unsigned short, protocol ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->protocol = ntohs(skb->protocol); ), TP_printk("skbaddr=%p protocol=%u location=%p", __entry->skbaddr, __entry->protocol, __entry->location) ); TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) ), TP_fast_assign( __entry->skbaddr = skb; ), TP_printk("skbaddr=%p", __entry->skbaddr) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support four policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_PREFERRED, .flags = MPOL_F_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /** * numa_map_to_online_node - Find closest online node * @node: Node id to start the search * * Lookup the next closest node by distance if @nid is not online. */ int numa_map_to_online_node(int node) { int min_dist = INT_MAX, dist, n, min_node; if (node == NUMA_NO_NODE || node_online(node)) return node; min_node = node; for_each_online_node(n) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_map_to_online_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (!nodes) pol->flags |= MPOL_F_LOCAL; /* local allocation */ else if (nodes_empty(*nodes)) return -EINVAL; /* no allowed nodes */ else pol->v.preferred_node = first_node(*nodes); return 0; } static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. But, we need to * handle an empty nodemask with MPOL_PREFERRED here. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ if (pol == NULL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) nodes = NULL; /* explicit local allocation */ else { if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; } if (nodes) ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); else ret = mpol_ops[pol->mode].create(pol, NULL); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; pr_debug("setting mode %d flags %d nodes[0] %lx\n", mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); mode = MPOL_PREFERRED; } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *p) { if (!atomic_dec_and_test(&p->refcnt)) return; kmem_cache_free(policy_cache, p); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->v.nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) { int node = first_node(pol->w.user_nodemask); if (node_isset(node, *nodes)) { pol->v.preferred_node = node; pol->flags &= ~MPOL_F_LOCAL; } else pol->flags |= MPOL_F_LOCAL; } else if (pol->flags & MPOL_F_RELATIVE_NODES) { mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); pol->v.preferred_node = first_node(tmp); } else if (!(pol->flags & MPOL_F_LOCAL)) { pol->v.preferred_node = node_remap(pol->v.preferred_node, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; mmap_write_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) mpol_rebind_policy(vma->vm_policy, new); mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_interleave, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; }; /* * Check if the page's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_pages_required(struct page *page, struct queue_pages *qp) { int nid = page_to_nid(page); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } /* * queue_pages_pmd() has four possible return values: * 0 - pages are placed on the right node or queued successfully. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing page was already on a node that does not follow the * policy. */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) __releases(ptl) { int ret = 0; struct page *page; struct queue_pages *qp = walk->private; unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) { ret = -EIO; goto unlock; } page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); __split_huge_pmd(walk->vma, pmd, addr, false, NULL); ret = 2; goto out; } if (!queue_pages_required(page, qp)) goto unlock; flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_page_add(page, qp->pagelist, flags)) { ret = 1; goto unlock; } } else ret = -EIO; unlock: spin_unlock(ptl); out: return ret; } /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: * 0 - pages are placed on the right node or queued successfully. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already * on a node that does not follow the policy. */ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct page *page; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; int ret; bool has_unmovable = false; pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); if (ret != 2) return ret; } /* THP was split, fall through to pte walk */ if (pmd_trans_unstable(pmd)) return 0; mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); if (!page) continue; /* * vm_normal_page() filters out zero pages, but there might * still be PageReserved pages to skip, perhaps in a VDSO. */ if (PageReserved(page)) continue; if (!queue_pages_required(page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { /* MPOL_MF_STRICT must be specified if we get here */ if (!vma_migratable(vma)) { has_unmovable = true; break; } /* * Do not abort immediately since there may be * temporary off LRU pages in the range. Still * need migrate other LRU pages. */ if (migrate_page_add(page, qp->pagelist, flags)) has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); if (has_unmovable) return 1; return addr != end ? -EIO : 0; } static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { int ret = 0; #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = (qp->flags & MPOL_MF_VALID); struct page *page; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(pte); if (!pte_present(entry)) goto unlock; page = pte_page(entry); if (!queue_pages_required(page, qp)) goto unlock; if (flags == MPOL_MF_STRICT) { /* * STRICT alone means only detecting misplaced page and no * need to further check other vma. */ ret = -EIO; goto unlock; } if (!vma_migratable(walk->vma)) { /* * Must be STRICT with MOVE*, otherwise .test_walk() have * stopped walking current vma. * Detecting misplaced page but allow migrating pages which * have been queued. */ ret = 1; goto unlock; } /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate page but allow migrating pages * which have been queued. */ ret = 1; } unlock: spin_unlock(ptl); #else BUG(); #endif return ret; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { int nr_updated; nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); return nr_updated; } #else static unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA((vma->vm_start > start) || (vma->vm_end < end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!vma->vm_next || vma->vm_end < vma->vm_next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; if (endvma > end) endvma = end; if (flags & MPOL_MF_LAZY) { /* Similar to task_numa_work, skip inaccessible VMAs */ if (!is_vm_hugetlb_page(vma) && vma_is_accessible(vma) && !(vma->vm_flags & VM_MIXEDMAP)) change_prot_numa(vma, start, endvma); return 1; } /* queue pages from current vma */ if (flags & MPOL_MF_VALID) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_pages_hugetlb, .pmd_entry = queue_pages_pte_range, .test_walk = queue_pages_test_walk, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are on a set of nodes (determined by * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private. * * queue_pages_range() has three possible return values: * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or * memory range specified by nodemask and maxnode points outside * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n", vma->vm_start, vma->vm_end, vma->vm_pgoff, vma->vm_ops, vma->vm_file, vma->vm_ops ? vma->vm_ops->set_policy : NULL); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Step 2: apply policy to a range and do splits. */ static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct mempolicy *new_pol) { struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; pgoff_t pgoff; unsigned long vmstart; unsigned long vmend; vma = find_vma(mm, start); VM_BUG_ON(!vma); prev = vma->vm_prev; if (start > vma->vm_start) prev = vma; for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) { vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); if (mpol_equal(vma_policy(vma), new_pol)) continue; pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, new_pol, vma->vm_userfaultfd_ctx); if (prev) { vma = prev; goto replace; } if (vma->vm_start != vmstart) { err = split_vma(vma->vm_mm, vma, vmstart, 1); if (err) goto out; } if (vma->vm_end != vmend) { err = split_vma(vma->vm_mm, vma, vmend, 0); if (err) goto out; } replace: err = vma_replace_policy(vma, new_pol); if (err) goto out; } out: return err; } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { mpol_put(new); goto out; } task_lock(current); old = current->mempolicy; current->mempolicy = new; if (new && new->mode == MPOL_INTERLEAVE) current->il_prev = MAX_NUMNODES-1; task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) { nodes_clear(*nodes); if (p == &default_policy) return; switch (p->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: *nodes = p->v.nodes; break; case MPOL_PREFERRED: if (!(p->flags & MPOL_F_LOCAL)) node_set(p->v.preferred_node, *nodes); /* else return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int err; int locked = 1; err = get_user_pages_locked(addr & PAGE_MASK, 1, 0, &p, &locked); if (err > 0) { err = page_to_nid(p); put_page(p); } if (locked) mmap_read_unlock(mm); return err; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = find_vma_intersection(mm, addr, addr+1); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } if (vma->vm_ops && vma->vm_ops->get_policy) pol = vma->vm_ops->get_policy(vma, addr); else pol = vma->vm_policy; } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, lookup_node() * wil drop the mmap_lock, so after calling * lookup_node() only "pol" remains valid, "vma" * is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->v.nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION /* * page migration, thp tail pages can be passed. */ static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { struct page *head = compound_head(page); /* * Avoid migrating a page that is shared with others. */ if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) { if (!isolate_lru_page(head)) { list_add_tail(&head->lru, pagelist); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_lru(head), thp_nr_pages(head)); } else if (flags & MPOL_MF_STRICT) { /* * Non-movable page may reach here. And, there may be * temporary off LRU pages or non-LRU movable pages. * Treat them as unmovable pages since they can't be * isolated, so they can't be moved at the moment. It * should return -EIO for this case too. */ return -EIO; } } return 0; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, }; nodes_clear(nmask); node_set(source, nmask); /* * This does not "check" the range but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. */ VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); } return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { int busy = 0; int err; nodemask_t tmp; err = migrate_prep(); if (err) return err; mmap_read_lock(mm); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s,d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) busy += err; if (err < 0) break; } mmap_read_unlock(mm); if (err < 0) return err; return busy; } /* * Allocate a new page for page migration based on vma policy. * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ static struct page *new_page(struct page *page, unsigned long start) { struct vm_area_struct *vma; unsigned long address; vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) break; vma = vma->vm_next; } if (PageHuge(page)) { return alloc_huge_page_vma(page_hstate(compound_head(page)), vma, address); } else if (PageTransHuge(page)) { struct page *thp; thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, HPAGE_PMD_ORDER); if (!thp) return NULL; prep_transhuge_page(thp); return thp; } /* * if !vma, alloc_page_vma() will use task or system default policy */ return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, vma, address); } #else static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { return -EIO; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct page *new_page(struct page *page, unsigned long start) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; int err; int ret; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = (len + PAGE_SIZE - 1) & PAGE_MASK; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); if (flags & MPOL_MF_LAZY) new->flags |= MPOL_F_MOF; /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", start, start + len, mode, mode_flags, nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { err = migrate_prep(); if (err) goto mpol_out; } { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; ret = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { err = ret; goto up_out; } err = mbind_range(mm, start, end, new); if (!err) { int nr_failed = 0; if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_page, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; } else { up_out: if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); } mmap_write_unlock(mm); mpol_out: mpol_put(new); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long k; unsigned long t; unsigned long nlongs; unsigned long endmask; --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; nlongs = BITS_TO_LONGS(maxnode); if ((maxnode % BITS_PER_LONG) == 0) endmask = ~0UL; else endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; /* * When the user specified more nodes than supported just check * if the non supported part is all zero. * * If maxnode have more longs than MAX_NUMNODES, check * the bits in that area first. And then go through to * check the rest bits which equal or bigger than MAX_NUMNODES. * Otherwise, just check bits [MAX_NUMNODES, maxnode). */ if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { if (get_user(t, nmask + k)) return -EFAULT; if (k == nlongs - 1) { if (t & endmask) return -EINVAL; } else if (t) return -EINVAL; } nlongs = BITS_TO_LONGS(MAX_NUMNODES); endmask = ~0UL; } if (maxnode > MAX_NUMNODES && MAX_NUMNODES % BITS_PER_LONG != 0) { unsigned long valid_mask = endmask; valid_mask &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); if (get_user(t, nmask + nlongs - 1)) return -EFAULT; if (t & valid_mask) return -EINVAL; } if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long))) return -EFAULT; nodes_addr(*nodes)[nlongs-1] &= endmask; return 0; } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; } return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { nodemask_t nodes; int err; unsigned short mode_flags; start = untagged_addr(start); mode_flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if (mode >= MPOL_MAX) return -EINVAL; if ((mode_flags & MPOL_F_STATIC_NODES) && (mode_flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, mode, mode_flags, &nodes, flags); } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { int err; nodemask_t nodes; unsigned short flags; flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)mode >= MPOL_MAX) return -EINVAL; if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(mode, flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, addr, compat_ulong_t, flags) { long err; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) nm = compat_alloc_user_space(alloc_size); err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags); if (!err && nmask) { unsigned long copy_size; copy_size = min_t(unsigned long, sizeof(bm), alloc_size); err = copy_from_user(bm, nm, copy_size); /* ensure entire bitmap is zeroed */ err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); err |= compat_put_bitmap(nmask, bm, nr_bits); } return err; } COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { if (compat_get_bitmap(bm, nmask, nr_bits)) return -EFAULT; nm = compat_alloc_user_space(alloc_size); if (copy_to_user(nm, bm, alloc_size)) return -EFAULT; } return kernel_set_mempolicy(mode, nm, nr_bits+1); } COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) return -EFAULT; nm = compat_alloc_user_space(alloc_size); if (copy_to_user(nm, nodes_addr(bm), alloc_size)) return -EFAULT; } return kernel_mbind(start, len, mode, nm, nr_bits+1, flags); } COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, compat_ulong_t, maxnode, const compat_ulong_t __user *, old_nodes, const compat_ulong_t __user *, new_nodes) { unsigned long __user *old = NULL; unsigned long __user *new = NULL; nodemask_t tmp_mask; unsigned long nr_bits; unsigned long size; nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES); size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (old_nodes) { if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits)) return -EFAULT; old = compat_alloc_user_space(new_nodes ? size * 2 : size); if (new_nodes) new = old + size / sizeof(unsigned long); if (copy_to_user(old, nodes_addr(tmp_mask), size)) return -EFAULT; } if (new_nodes) { if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits)) return -EFAULT; if (new == NULL) new = compat_alloc_user_space(size); if (copy_to_user(new, nodes_addr(tmp_mask), size)) return -EFAULT; } return kernel_migrate_pages(pid, nr_bits + 1, old, new); } #endif /* CONFIG_COMPAT */ bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = NULL; if (vma) { if (vma->vm_ops && vma->vm_ops->get_policy) { pol = vma->vm_ops->get_policy(vma, addr); } else if (vma->vm_policy) { pol = vma->vm_policy; /* * shmem_alloc_page() passes MPOL_F_SHARED policy with * a pseudo vma whose vma->vm_ops=NULL. Take a reference * count on these policies which will be dropped by * mpol_cond_put() later */ if (mpol_needs_cond_ref(pol)) mpol_get(pol); } } return pol; } /* * get_vma_policy(@vma, @addr) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); if (!pol) pol = get_task_policy(current); return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pol = vma->vm_ops->get_policy(vma, vma->vm_start); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->v.nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->v.nodes is intersect with node_states[N_MEMORY]. * so if the following test faile, it implies * policy->v.nodes has movable memory only. */ if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation */ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) { /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && apply_policy_zone(policy, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) return &policy->v.nodes; return NULL; } /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) nd = policy->v.preferred_node; else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); } return nd; } /* Do dynamic interleaving for a process */ static unsigned interleave_nodes(struct mempolicy *policy) { unsigned next; struct task_struct *me = current; next = next_node_in(me->il_prev, policy->v.nodes); if (next < MAX_NUMNODES) me->il_prev = next; return next; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (in_interrupt()) return node; policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) return node; switch (policy->mode) { case MPOL_PREFERRED: /* * handled MPOL_F_LOCAL above */ return policy->v.preferred_node; case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_BIND: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes); return z->zone ? zone_to_nid(z->zone) : node; } default: BUG(); } } /* * Do static interleaving for a VMA with known offset @n. Returns the n'th * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the * number of present nodes. */ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) { unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; int i; int nid; if (!nnodes) return numa_node_id(); target = (unsigned int)n % nnodes; nid = first_node(pol->v.nodes); for (i = 0; i < target; i++) nid = next_node(nid, pol->v.nodes); return nid; } /* Determine a node number for interleave */ static inline unsigned interleave_nid(struct mempolicy *pol, struct vm_area_struct *vma, unsigned long addr, int shift) { if (vma) { unsigned long off; /* * for small pages, there is no difference between * shift and PAGE_SHIFT, so the bit-shift is safe. * for huge pages, since vm_pgoff is in units of small * pages, we need to shift off the always 0 bits to get * a useful offset. */ BUG_ON(shift < PAGE_SHIFT); off = vma->vm_pgoff >> (shift - PAGE_SHIFT); off += (addr - vma->vm_start) >> shift; return offset_il_node(pol, off); } else return interleave_nodes(pol); } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * * Must be protected by read_mems_allowed_begin() */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { int nid; *mpol = get_vma_policy(vma, addr); *nodemask = NULL; /* assume !MPOL_BIND */ if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { nid = interleave_nid(*mpol, vma, addr, huge_page_shift(hstate_vma(vma))); } else { nid = policy_node(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) *nodemask = &(*mpol)->v.nodes; } return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; int nid; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: if (mempolicy->flags & MPOL_F_LOCAL) nid = numa_node_id(); else nid = mempolicy->v.preferred_node; init_nodemask_of_node(mask, nid); break; case MPOL_BIND: case MPOL_INTERLEAVE: *mask = mempolicy->v.nodes; break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_nodemask_intersects * * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default * policy. Otherwise, check for intersection between mask and the policy * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' * policy, always return true since it may allocate elsewhere on fallback. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_nodemask_intersects(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (!mempolicy) goto out; switch (mempolicy->mode) { case MPOL_PREFERRED: /* * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to * allocate from, they may fallback to other nodes when oom. * Thus, it's possible for tsk to have allocated memory from * nodes in mask. */ break; case MPOL_BIND: case MPOL_INTERLEAVE: ret = nodes_intersects(mempolicy->v.nodes, *mask); break; default: BUG(); } out: task_unlock(tsk); return ret; } /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, unsigned nid) { struct page *page; page = __alloc_pages(gfp, order, nid); /* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */ if (!static_branch_likely(&vm_numa_stat_key)) return page; if (page && page_to_nid(page) == nid) { preempt_disable(); __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } return page; } /** * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. * %GFP_KERNEL kernel allocations, * %GFP_HIGHMEM highmem/user allocations, * %GFP_FS allocation should not call back into a file system. * %GFP_ATOMIC don't sleep. * * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. * When VMA is not NULL caller must read-lock the mmap_lock of the * mm_struct of the VMA to prevent it from going away. Should be used for * all allocations for pages that will be mapped into user space. Returns * NULL when no page can be allocated. */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; int preferred_nid; nodemask_t *nmask; pol = get_vma_policy(vma, addr); if (pol->mode == MPOL_INTERLEAVE) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); goto out; } if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { int hpage_node = node; /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) hpage_node = pol->v.preferred_node; nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node(hpage_node, gfp | __GFP_THISNODE | __GFP_NORETRY, order); /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ if (!page && (gfp & __GFP_DIRECT_RECLAIM)) page = __alloc_pages_nodemask(gfp, order, hpage_node, nmask); goto out; } } nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); mpol_cond_put(pol); out: return page; } EXPORT_SYMBOL(alloc_pages_vma); /** * alloc_pages_current - Allocate pages. * * @gfp: * %GFP_USER user allocation, * %GFP_KERNEL kernel allocation, * %GFP_HIGHMEM highmem allocation, * %GFP_FS don't call back into a file system. * %GFP_ATOMIC don't sleep. * @order: Power of two of allocation size in pages. 0 is a single page. * * Allocate a page from the kernel page pool. When not in * interrupt context and apply the current process NUMA policy. * Returns NULL when no page can be allocated. */ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; struct page *page; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (pol->mode == MPOL_INTERLEAVE) page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, policy_node(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); return page; } EXPORT_SYMBOL(alloc_pages_current); int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: /* a's ->flags is the same as b's */ if (a->flags & MPOL_F_LOCAL) return true; return a->v.preferred_node == b->v.preferred_node; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node * sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); pr_debug("inserting %lx-%lx: %d\n", new->start, new->end, new->policy ? new->policy->mode : 0); } /* Find shared policy intersecting idx */ struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current page node is valid in policy * * @page: page to be checked * @vma: vm area where page mapped * @addr: virtual address where page mapped * * Lookup current policy node id for vma,addr and "compare to" page's * node id. * * Returns: * -1 - not misplaced, page is in the right node * node - node id where the page should be * * Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. */ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; struct zoneref *z; int curnid = page_to_nid(page); unsigned long pgoff; int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); int polnid = NUMA_NO_NODE; int ret = -1; pol = get_vma_policy(vma, addr); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: pgoff = vma->vm_pgoff; pgoff += (addr - vma->vm_start) >> PAGE_SHIFT; polnid = offset_il_node(pol, pgoff); break; case MPOL_PREFERRED: if (pol->flags & MPOL_F_LOCAL) polnid = numa_node_id(); else polnid = pol->v.preferred_node; break; case MPOL_BIND: /* * allows binding to multiple nodes. * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->v.nodes)) goto out; z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->v.nodes); polnid = zone_to_nid(z->zone); break; default: BUG(); } /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, unsigned long start, unsigned long end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct vm_area_struct pvma; struct mempolicy *new; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy */ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(new)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_new; /* Create pseudo-vma that contains just the policy */ vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ put_new: mpol_put(new); /* drop initial ref */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *npol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n", vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); if (!new) return -ENOMEM; } err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *p) { struct sp_node *n; struct rb_node *next; if (!p->root.rb_node) return; write_lock(&p->lock); next = rb_first(&p->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(p, n); } write_unlock(&p->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ /* assumes fs == KERNEL_DS */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .v = { .preferred_node = nid, }, }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ /* * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_LOCAL] = "local", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * On success, returns 0, else 1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) new->v.nodes = nodes; else if (nodelist) new->v.preferred_node = first_node(nodes); else new->flags |= MPOL_F_LOCAL; /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the * longest flag, "relative", and to display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: break; case MPOL_PREFERRED: if (flags & MPOL_F_LOCAL) mode = MPOL_LOCAL; else node_set(pol->v.preferred_node, nodes); break; case MPOL_BIND: case MPOL_INTERLEAVE: nodes = pol->v.nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Currently, the only defined flags are mutually exclusive */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * * Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls. * Doug Evans (dje@spiff.uucp), August 07, 1992 * * Deadlock detection added. * FIXME: one thing isn't handled yet: * - mandatory locks (requires lots of changes elsewhere) * Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994. * * Miscellaneous edits, and a total rewrite of posix_lock_file() code. * Kai Petzke (wpp@marie.physik.tu-berlin.de), 1994 * * Converted file_lock_table to a linked list from an array, which eliminates * the limits on how many active file locks are open. * Chad Page (pageone@netcom.com), November 27, 1994 * * Removed dependency on file descriptors. dup()'ed file descriptors now * get the same locks as the original file descriptors, and a close() on * any file descriptor removes ALL the locks on the file for the current * process. Since locks still depend on the process id, locks are inherited * after an exec() but not after a fork(). This agrees with POSIX, and both * BSD and SVR4 practice. * Andy Walker (andy@lysaker.kvaerner.no), February 14, 1995 * * Scrapped free list which is redundant now that we allocate locks * dynamically with kmalloc()/kfree(). * Andy Walker (andy@lysaker.kvaerner.no), February 21, 1995 * * Implemented two lock personalities - FL_FLOCK and FL_POSIX. * * FL_POSIX locks are created with calls to fcntl() and lockf() through the * fcntl() system call. They have the semantics described above. * * FL_FLOCK locks are created with calls to flock(), through the flock() * system call, which is new. Old C libraries implement flock() via fcntl() * and will continue to use the old, broken implementation. * * FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated * with a file pointer (filp). As a result they can be shared by a parent * process and its children after a fork(). They are removed when the last * file descriptor referring to the file pointer is closed (unless explicitly * unlocked). * * FL_FLOCK locks never deadlock, an existing lock is always removed before * upgrading from shared to exclusive (or vice versa). When this happens * any processes blocked by the current lock are woken up and allowed to * run before the new lock is applied. * Andy Walker (andy@lysaker.kvaerner.no), June 09, 1995 * * Removed some race conditions in flock_lock_file(), marked other possible * races. Just grep for FIXME to see them. * Dmitry Gorodchanin (pgmdsg@ibi.com), February 09, 1996. * * Addressed Dmitry's concerns. Deadlock checking no longer recursive. * Lock allocation changed to GFP_ATOMIC as we can't afford to sleep * once we've checked for blocking and deadlocking. * Andy Walker (andy@lysaker.kvaerner.no), April 03, 1996. * * Initial implementation of mandatory locks. SunOS turned out to be * a rotten model, so I implemented the "obvious" semantics. * See 'Documentation/filesystems/mandatory-locking.rst' for details. * Andy Walker (andy@lysaker.kvaerner.no), April 06, 1996. * * Don't allow mandatory locks on mmap()'ed files. Added simple functions to * check if a file has mandatory locks, used by mmap(), open() and creat() to * see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference * Manual, Section 2. * Andy Walker (andy@lysaker.kvaerner.no), April 09, 1996. * * Tidied up block list handling. Added '/proc/locks' interface. * Andy Walker (andy@lysaker.kvaerner.no), April 24, 1996. * * Fixed deadlock condition for pathological code that mixes calls to * flock() and fcntl(). * Andy Walker (andy@lysaker.kvaerner.no), April 29, 1996. * * Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use * for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to * guarantee sensible behaviour in the case where file system modules might * be compiled with different options than the kernel itself. * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996. * * Added a couple of missing wake_up() calls. Thanks to Thomas Meckel * (Thomas.Meckel@mni.fh-giessen.de) for spotting this. * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996. * * Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK * locks. Changed process synchronisation to avoid dereferencing locks that * have already been freed. * Andy Walker (andy@lysaker.kvaerner.no), Sep 21, 1996. * * Made the block list a circular list to minimise searching in the list. * Andy Walker (andy@lysaker.kvaerner.no), Sep 25, 1996. * * Made mandatory locking a mount option. Default is not to allow mandatory * locking. * Andy Walker (andy@lysaker.kvaerner.no), Oct 04, 1996. * * Some adaptations for NFS support. * Olaf Kirch (okir@monad.swb.de), Dec 1996, * * Fixed /proc/locks interface so that we can't overrun the buffer we are handed. * Andy Walker (andy@lysaker.kvaerner.no), May 12, 1997. * * Use slab allocator instead of kmalloc/kfree. * Use generic list implementation from <linux/list.h>. * Sped up posix_locks_deadlock by only considering blocked locks. * Matthew Wilcox <willy@debian.org>, March, 2000. * * Leases and LOCK_MAND * Matthew Wilcox <willy@debian.org>, June, 2000. * Stephen Rothwell <sfr@canb.auug.org.au>, June, 2000. * * Locking conflicts and dependencies: * If multiple threads attempt to lock the same byte (or flock the same file) * only one can be granted the lock, and other must wait their turn. * The first lock has been "applied" or "granted", the others are "waiting" * and are "blocked" by the "applied" lock.. * * Waiting and applied locks are all kept in trees whose properties are: * * - the root of a tree may be an applied or waiting lock. * - every other node in the tree is a waiting lock that * conflicts with every ancestor of that node. * * Every such tree begins life as a waiting singleton which obviously * satisfies the above properties. * * The only ways we modify trees preserve these properties: * * 1. We may add a new leaf node, but only after first verifying that it * conflicts with all of its ancestors. * 2. We may remove the root of a tree, creating a new singleton * tree from the root and N new trees rooted in the immediate * children. * 3. If the root of a tree is not currently an applied lock, we may * apply it (if possible). * 4. We may upgrade the root of the tree (either extend its range, * or upgrade its entire range from read to write). * * When an applied lock is modified in a way that reduces or downgrades any * part of its range, we remove all its children (2 above). This particularly * happens when a lock is unlocked. * * For each of those child trees we "wake up" the thread which is * waiting for the lock so it can continue handling as follows: if the * root of the tree applies, we do so (3). If it doesn't, it must * conflict with some applied lock. We remove (wake up) all of its children * (2), and add it is a new leaf to the tree rooted in the applied * lock (1). We then repeat the process recursively with those * children. * */ #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> #include <linux/uaccess.h> #define IS_POSIX(fl) (fl->fl_flags & FL_POSIX) #define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK) #define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) #define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) #define IS_REMOTELCK(fl) (fl->fl_pid <= 0) static bool lease_breaking(struct file_lock *fl) { return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); } static int target_leasetype(struct file_lock *fl) { if (fl->fl_flags & FL_UNLOCK_PENDING) return F_UNLCK; if (fl->fl_flags & FL_DOWNGRADE_PENDING) return F_RDLCK; return fl->fl_type; } int leases_enable = 1; int lease_break_time = 45; /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock. * Global serialization is done using file_rwsem. * * Note that alterations to the list also require that the relevant flc_lock is * held. */ struct file_lock_list_struct { spinlock_t lock; struct hlist_head hlist; }; static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. * It is protected by blocked_lock_lock. * * We hash locks by lockowner in order to optimize searching for the lock a * particular lockowner is waiting on. * * FIXME: make this value scale via some heuristic? We generally will want more * buckets when we have more lockowners holding locks, but that's a little * difficult to determine without knowing what the workload will look like. */ #define BLOCKED_HASH_BITS 7 static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); /* * This lock protects the blocked_hash. Generally, if you're accessing it, you * want to be holding this lock. * * In addition, it also protects the fl->fl_blocked_requests list, and the * fl->fl_blocker pointer for file_lock structures that are acting as lock * requests (in contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the * flc_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *ctx; /* paired with cmpxchg() below */ ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); if (!ctx) goto out; spin_lock_init(&ctx->flc_lock); INIT_LIST_HEAD(&ctx->flc_flock); INIT_LIST_HEAD(&ctx->flc_posix); INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); return ctx; } static void locks_dump_ctx_list(struct list_head *list, char *list_type) { struct file_lock *fl; list_for_each_entry(fl, list, fl_list) { pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); } } static void locks_check_ctx_lists(struct inode *inode) { struct file_lock_context *ctx = inode->i_flctx; if (unlikely(!list_empty(&ctx->flc_flock) || !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_lease))) { pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); } } static void locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { struct file_lock *fl; struct inode *inode = locks_inode(filp); list_for_each_entry(fl, list, fl_list) if (fl->fl_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); } void locks_free_lock_context(struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); INIT_LIST_HEAD(&fl->fl_list); INIT_LIST_HEAD(&fl->fl_blocked_requests); INIT_LIST_HEAD(&fl->fl_blocked_member); init_waitqueue_head(&fl->fl_wait); } /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(fl); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); void locks_release_private(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); BUG_ON(!list_empty(&fl->fl_list)); BUG_ON(!list_empty(&fl->fl_blocked_requests)); BUG_ON(!list_empty(&fl->fl_blocked_member)); BUG_ON(!hlist_unhashed(&fl->fl_link)); if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); fl->fl_ops = NULL; } if (fl->fl_lmops) { if (fl->fl_lmops->lm_put_owner) { fl->fl_lmops->lm_put_owner(fl->fl_owner); fl->fl_owner = NULL; } fl->fl_lmops = NULL; } } EXPORT_SYMBOL_GPL(locks_release_private); /** * locks_owner_has_blockers - Check for blocking lock requests * @flctx: file lock context * @owner: lock owner * * Return values: * %true: @owner has at least one blocker * %false: @owner has no blockers */ bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { struct file_lock *fl; spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_owner != owner) continue; if (!list_empty(&fl->fl_blocked_requests)) { spin_unlock(&flctx->flc_lock); return true; } } spin_unlock(&flctx->flc_lock); return false; } EXPORT_SYMBOL_GPL(locks_owner_has_blockers); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } EXPORT_SYMBOL(locks_free_lock); static void locks_dispose_list(struct list_head *dispose) { struct file_lock *fl; while (!list_empty(dispose)) { fl = list_first_entry(dispose, struct file_lock, fl_list); list_del_init(&fl->fl_list); locks_free_lock(fl); } } void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); locks_init_lock_heads(fl); } EXPORT_SYMBOL(locks_init_lock); /* * Initialize a new lock from an existing file_lock structure. */ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { new->fl_owner = fl->fl_owner; new->fl_pid = fl->fl_pid; new->fl_file = NULL; new->fl_flags = fl->fl_flags; new->fl_type = fl->fl_type; new->fl_start = fl->fl_start; new->fl_end = fl->fl_end; new->fl_lmops = fl->fl_lmops; new->fl_ops = NULL; if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) fl->fl_lmops->lm_get_owner(fl->fl_owner); } } EXPORT_SYMBOL(locks_copy_conflock); void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { /* "new" must be a freshly-initialized lock */ WARN_ON_ONCE(new->fl_ops); locks_copy_conflock(new, fl); new->fl_file = fl->fl_file; new->fl_ops = fl->fl_ops; if (fl->fl_ops) { if (fl->fl_ops->fl_copy_lock) fl->fl_ops->fl_copy_lock(new, fl); } } EXPORT_SYMBOL(locks_copy_lock); static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) { struct file_lock *f; /* * As ctx->flc_lock is held, new requests cannot be added to * ->fl_blocked_requests, so we don't need a lock to check if it * is empty. */ if (list_empty(&fl->fl_blocked_requests)) return; spin_lock(&blocked_lock_lock); list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests); list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member) f->fl_blocker = new; spin_unlock(&blocked_lock_lock); } static inline int flock_translate_cmd(int cmd) { if (cmd & LOCK_MAND) return cmd & (LOCK_MAND | LOCK_RW); switch (cmd) { case LOCK_SH: return F_RDLCK; case LOCK_EX: return F_WRLCK; case LOCK_UN: return F_UNLCK; } return -EINVAL; } /* Fill in a file_lock structure with an appropriate FLOCK lock. */ static struct file_lock * flock_make_lock(struct file *filp, unsigned int cmd, struct file_lock *fl) { int type = flock_translate_cmd(cmd); if (type < 0) return ERR_PTR(type); if (fl == NULL) { fl = locks_alloc_lock(); if (fl == NULL) return ERR_PTR(-ENOMEM); } else { locks_init_lock(fl); } fl->fl_file = filp; fl->fl_owner = filp; fl->fl_pid = current->tgid; fl->fl_flags = FL_FLOCK; fl->fl_type = type; fl->fl_end = OFFSET_MAX; return fl; } static int assign_type(struct file_lock *fl, long type) { switch (type) { case F_RDLCK: case F_WRLCK: case F_UNLCK: fl->fl_type = type; break; default: return -EINVAL; } return 0; } static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock64 *l) { switch (l->l_whence) { case SEEK_SET: fl->fl_start = 0; break; case SEEK_CUR: fl->fl_start = filp->f_pos; break; case SEEK_END: fl->fl_start = i_size_read(file_inode(filp)); break; default: return -EINVAL; } if (l->l_start > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_start += l->l_start; if (fl->fl_start < 0) return -EINVAL; /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ if (l->l_len > 0) { if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_end = fl->fl_start + l->l_len - 1; } else if (l->l_len < 0) { if (fl->fl_start + l->l_len < 0) return -EINVAL; fl->fl_end = fl->fl_start - 1; fl->fl_start += l->l_len; } else fl->fl_end = OFFSET_MAX; fl->fl_owner = current->files; fl->fl_pid = current->tgid; fl->fl_file = filp; fl->fl_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; return assign_type(fl, l->l_type); } /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX * style lock. */ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock *l) { struct flock64 ll = { .l_type = l->l_type, .l_whence = l->l_whence, .l_start = l->l_start, .l_len = l->l_len, }; return flock64_to_posix_lock(filp, fl, &ll); } /* default lease lock manager operations */ static bool lease_break_callback(struct file_lock *fl) { kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); return false; } static void lease_setup(struct file_lock *fl, void **priv) { struct file *filp = fl->fl_file; struct fasync_struct *fa = *priv; /* * fasync_insert_entry() returns the old entry if any. If there was no * old entry, then it used "priv" and inserted it into the fasync list. * Clear the pointer to indicate that it shouldn't be freed. */ if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa)) *priv = NULL; __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } static const struct lock_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, }; /* * Initialize a lease, use the default lock manager operations */ static int lease_init(struct file *filp, long type, struct file_lock *fl) { if (assign_type(fl, type) != 0) return -EINVAL; fl->fl_owner = filp; fl->fl_pid = current->tgid; fl->fl_file = filp; fl->fl_flags = FL_LEASE; fl->fl_start = 0; fl->fl_end = OFFSET_MAX; fl->fl_ops = NULL; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ static struct file_lock *lease_alloc(struct file *filp, long type) { struct file_lock *fl = locks_alloc_lock(); int error = -ENOMEM; if (fl == NULL) return ERR_PTR(error); error = lease_init(filp, type, fl); if (error) { locks_free_lock(fl); return ERR_PTR(error); } return fl; } /* Check if two locks overlap each other. */ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) { return ((fl1->fl_end >= fl2->fl_start) && (fl2->fl_end >= fl1->fl_start)); } /* * Check whether two locks have the same owner. */ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) { return fl1->fl_owner == fl2->fl_owner; } /* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); percpu_rwsem_assert_held(&file_rwsem); spin_lock(&fll->lock); fl->fl_link_cpu = smp_processor_id(); hlist_add_head(&fl->fl_link, &fll->hlist); spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { struct file_lock_list_struct *fll; percpu_rwsem_assert_held(&file_rwsem); /* * Avoid taking lock if already unhashed. This is safe since this check * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&fl->fl_link)) return; fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu); spin_lock(&fll->lock); hlist_del_init(&fl->fl_link); spin_unlock(&fll->lock); } static unsigned long posix_owner_key(struct file_lock *fl) { return (unsigned long)fl->fl_owner; } static void locks_insert_global_blocked(struct file_lock *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter)); } static void locks_delete_global_blocked(struct file_lock *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_del(&waiter->fl_link); } /* Remove waiter from blocker's block list. * When blocker ends up pointing to itself then the list is empty. * * Must be called with blocked_lock_lock held. */ static void __locks_delete_block(struct file_lock *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->fl_blocked_member); } static void __locks_wake_up_blocks(struct file_lock *blocker) { while (!list_empty(&blocker->fl_blocked_requests)) { struct file_lock *waiter; waiter = list_first_entry(&blocker->fl_blocked_requests, struct file_lock, fl_blocked_member); __locks_delete_block(waiter); if (waiter->fl_lmops && waiter->fl_lmops->lm_notify) waiter->fl_lmops->lm_notify(waiter); else wake_up(&waiter->fl_wait); /* * The setting of fl_blocker to NULL marks the "done" * point in deleting a block. Paired with acquire at the top * of locks_delete_block(). */ smp_store_release(&waiter->fl_blocker, NULL); } } /** * locks_delete_lock - stop waiting for a file lock * @waiter: the lock which was waiting * * lockd/nfsd need to disconnect the lock while working on it. */ int locks_delete_block(struct file_lock *waiter) { int status = -ENOENT; /* * If fl_blocker is NULL, it won't be set again as this thread "owns" * the lock and is the only one that might try to claim the lock. * * We use acquire/release to manage fl_blocker so that we can * optimize away taking the blocked_lock_lock in many cases. * * The smp_load_acquire guarantees two things: * * 1/ that fl_blocked_requests can be tested locklessly. If something * was recently added to that list it must have been in a locked region * *before* the locked region when fl_blocker was set to NULL. * * 2/ that no other thread is accessing 'waiter', so it is safe to free * it. __locks_wake_up_blocks is careful not to touch waiter after * fl_blocker is released. * * If a lockless check of fl_blocker shows it to be NULL, we know that * no new locks can be inserted into its fl_blocked_requests list, and * can avoid doing anything further if the list is empty. */ if (!smp_load_acquire(&waiter->fl_blocker) && list_empty(&waiter->fl_blocked_requests)) return status; spin_lock(&blocked_lock_lock); if (waiter->fl_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_delete_block(waiter); /* * The setting of fl_blocker to NULL marks the "done" point in deleting * a block. Paired with acquire at the top of this function. */ smp_store_release(&waiter->fl_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } EXPORT_SYMBOL(locks_delete_block); /* Insert waiter into blocker's block list. * We use a circular list so that processes can be easily woken up in * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * * Must be called with both the flc_lock and blocked_lock_lock held. The * fl_blocked_requests list itself is protected by the blocked_lock_lock, * but by ensuring that the flc_lock is also held on insertions we can avoid * taking the blocked_lock_lock in some cases when we see that the * fl_blocked_requests list is empty. * * Rather than just adding to the list, we check for conflicts with any existing * waiters, and add beneath any waiter that blocks the new waiter. * Thus wakeups don't happen until needed. */ static void __locks_insert_block(struct file_lock *blocker, struct file_lock *waiter, bool conflict(struct file_lock *, struct file_lock *)) { struct file_lock *fl; BUG_ON(!list_empty(&waiter->fl_blocked_member)); new_blocker: list_for_each_entry(fl, &blocker->fl_blocked_requests, fl_blocked_member) if (conflict(fl, waiter)) { blocker = fl; goto new_blocker; } waiter->fl_blocker = blocker; list_add_tail(&waiter->fl_blocked_member, &blocker->fl_blocked_requests); if (IS_POSIX(blocker) && !IS_OFDLCK(blocker)) locks_insert_global_blocked(waiter); /* The requests in waiter->fl_blocked are known to conflict with * waiter, but might not conflict with blocker, or the requests * and lock which block it. So they all need to be woken. */ __locks_wake_up_blocks(waiter); } /* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock *blocker, struct file_lock *waiter, bool conflict(struct file_lock *, struct file_lock *)) { spin_lock(&blocked_lock_lock); __locks_insert_block(blocker, waiter, conflict); spin_unlock(&blocked_lock_lock); } /* * Wake up processes blocked waiting for blocker. * * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new * blocked requests are only added to the list under the flc_lock, and * the flc_lock is always held here. Note that removal from the * fl_blocked_requests list does not require the flc_lock, so we must * recheck list_empty() after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->fl_blocked_requests)) return; spin_lock(&blocked_lock_lock); __locks_wake_up_blocks(blocker); spin_unlock(&blocked_lock_lock); } static void locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) { list_add_tail(&fl->fl_list, before); locks_insert_global_locks(fl); } static void locks_unlink_lock_ctx(struct file_lock *fl) { locks_delete_global_locks(fl); list_del_init(&fl->fl_list); locks_wake_up_blocks(fl); } static void locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) { locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ static bool locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { if (sys_fl->fl_type == F_WRLCK) return true; if (caller_fl->fl_type == F_WRLCK) return true; return false; } /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific * checking before calling the locks_conflict(). */ static bool posix_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { /* POSIX locks owned by the same process do not conflict with * each other. */ if (posix_same_owner(caller_fl, sys_fl)) return false; /* Check whether they overlap */ if (!locks_overlap(caller_fl, sys_fl)) return false; return locks_conflict(caller_fl, sys_fl); } /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific * checking before calling the locks_conflict(). */ static bool flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { /* FLOCK locks referring to the same filp do not conflict with * each other. */ if (caller_fl->fl_file == sys_fl->fl_file) return false; if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND)) return false; return locks_conflict(caller_fl, sys_fl); } void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; struct inode *inode = locks_inode(filp); void *owner; void (*func)(void); ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; } retry: spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { if (!posix_locks_conflict(fl, cfl)) continue; if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { owner = cfl->fl_lmops->lm_mod_owner; func = cfl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); (*func)(); module_put(owner); goto retry; } locks_copy_conflock(fl, cfl); goto out; } fl->fl_type = F_UNLCK; out: spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); /* * Deadlock detection: * * We attempt to detect deadlocks that are due purely to posix file * locks. * * We assume that a task can be waiting for at most one lock at a time. * So for any acquired lock, the process holding that lock may be * waiting on at most one other lock. That lock in turns may be held by * someone waiting for at most one other lock. Given a requested lock * caller_fl which is about to wait for a conflicting lock block_fl, we * follow this chain of waiters to ensure we are not about to create a * cycle. * * Since we do this before we ever put a process to sleep on a lock, we * are ensured that there is never a cycle; that is what guarantees that * the while() loop in posix_locks_deadlock() eventually completes. * * Note: the above assumption may not be true when handling lock * requests from a broken NFS client. It may also fail in the presence * of tasks (such as posix threads) sharing the same open file table. * To handle those cases, we just bail out after a few iterations. * * For FL_OFDLCK locks, the owner is the filp, not the files_struct. * Because the owner is not even nominally tied to a thread of * execution, the deadlock detection below can't reasonably work well. Just * skip it for those. * * In principle, we could do a more limited deadlock detection on FL_OFDLCK * locks that just checks for the case where two tasks are attempting to * upgrade from read to write locks on the same inode. */ #define MAX_DEADLK_ITERATIONS 10 /* Find a lock that the owner of the given block_fl is blocking on. */ static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl) { struct file_lock *fl; hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) { if (posix_same_owner(fl, block_fl)) { while (fl->fl_blocker) fl = fl->fl_blocker; return fl; } } return NULL; } /* Must be called with the blocked_lock_lock held! */ static int posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { int i = 0; lockdep_assert_held(&blocked_lock_lock); /* * This deadlock detector can't reasonably detect deadlocks with * FL_OFDLCK locks, since they aren't owned by a process, per-se. */ if (IS_OFDLCK(caller_fl)) return 0; while ((block_fl = what_owner_is_waiting_for(block_fl))) { if (i++ > MAX_DEADLK_ITERATIONS) return 0; if (posix_same_owner(caller_fl, block_fl)) return 1; } return 0; } /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks * after any leases, but before any posix locks. * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ static int flock_lock_inode(struct inode *inode, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock *fl; struct file_lock_context *ctx; int error = 0; bool found = false; LIST_HEAD(dispose); ctx = locks_get_lock_context(inode, request->fl_type); if (!ctx) { if (request->fl_type != F_UNLCK) return -ENOMEM; return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0; } if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (request->fl_file != fl->fl_file) continue; if (request->fl_type == fl->fl_type) goto out; found = true; locks_delete_lock_ctx(fl, &dispose); break; } if (request->fl_type == F_UNLCK) { if ((request->fl_flags & FL_EXISTS) && !found) error = -ENOENT; goto out; } find_conflict: list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (!flock_locks_conflict(request, fl)) continue; error = -EAGAIN; if (!(request->fl_flags & FL_SLEEP)) goto out; error = FILE_LOCK_DEFERRED; locks_insert_block(fl, request, flock_locks_conflict); goto out; } if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(new_fl, &ctx->flc_flock); new_fl = NULL; error = 0; out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); trace_flock_lock_inode(inode, request, error); return error; } static int posix_lock_inode(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); void *owner; void (*func)(void); ctx = locks_get_lock_context(inode, request->fl_type); if (!ctx) return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. * * In some cases we can be sure, that no new locks will be needed */ if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK || request->fl_start != 0 || request->fl_end != OFFSET_MAX)) { new_fl = locks_alloc_lock(); new_fl2 = locks_alloc_lock(); } retry: percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->fl_type != F_UNLCK) { list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!posix_locks_conflict(request, fl)) continue; if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable && (*fl->fl_lmops->lm_lock_expirable)(fl)) { owner = fl->fl_lmops->lm_mod_owner; func = fl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); (*func)(); module_put(owner); goto retry; } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; if (!(request->fl_flags & FL_SLEEP)) goto out; /* * Deadlock detection and insertion into the blocked * locks list must be done while holding the same lock! */ error = -EDEADLK; spin_lock(&blocked_lock_lock); /* * Ensure that we don't find any locks blocked on this * request during deadlock detection. */ __locks_wake_up_blocks(request); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(fl, request, posix_locks_conflict); } spin_unlock(&blocked_lock_lock); goto out; } } /* If we're just looking for a conflict, we're done. */ error = 0; if (request->fl_flags & FL_ACCESS) goto out; /* Find the first old lock with the same owner as the new lock */ list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (posix_same_owner(request, fl)) break; } /* Process locks with this owner. */ list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { if (!posix_same_owner(request, fl)) break; /* Detect adjacent or overlapping regions (if same lock type) */ if (request->fl_type == fl->fl_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ if (fl->fl_start - 1 > request->fl_end) break; /* If we come here, the new and old lock are of the * same type and adjacent or overlapping. Make one * lock yielding from the lower start address of both * locks to the higher end address. */ if (fl->fl_start > request->fl_start) fl->fl_start = request->fl_start; else request->fl_start = fl->fl_start; if (fl->fl_end < request->fl_end) fl->fl_end = request->fl_end; else request->fl_end = fl->fl_end; if (added) { locks_delete_lock_ctx(fl, &dispose); continue; } request = fl; added = true; } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) continue; if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) added = true; if (fl->fl_start < request->fl_start) left = fl; /* If the next lock in the list has a higher end * address than the new one, insert the new one here. */ if (fl->fl_end > request->fl_end) { right = fl; break; } if (fl->fl_start >= request->fl_start) { /* The new lock completely replaces an old * one (This may happen several times). */ if (added) { locks_delete_lock_ctx(fl, &dispose); continue; } /* * Replace the old lock with new_fl, and * remove the old one. It's safe to do the * insert here since we know that we won't be * using new_fl later, and that the lock is * just replacing an existing lock. */ error = -ENOLCK; if (!new_fl) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); request = new_fl; new_fl = NULL; locks_insert_lock_ctx(request, &fl->fl_list); locks_delete_lock_ctx(fl, &dispose); added = true; } } } /* * The above code only modifies existing locks in case of merging or * replacing. If new lock(s) need to be inserted all modifications are * done below this, so it's safe yet to bail out. */ error = -ENOLCK; /* "no luck" */ if (right && left == right && !new_fl2) goto out; error = 0; if (!added) { if (request->fl_type == F_UNLCK) { if (request->fl_flags & FL_EXISTS) error = -ENOENT; goto out; } if (!new_fl) { error = -ENOLCK; goto out; } locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(new_fl, &fl->fl_list); fl = new_fl; new_fl = NULL; } if (right) { if (left == right) { /* The new lock breaks the old one in two pieces, * so we have to use the second new lock. */ left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); locks_insert_lock_ctx(left, &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); } if (left) { left->fl_end = request->fl_start - 1; locks_wake_up_blocks(left); } out: trace_posix_lock_inode(inode, request, error); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); /* * Free any unused locks. */ if (new_fl) locks_free_lock(new_fl); if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); return error; } /** * posix_lock_file - Apply a POSIX-style lock to a file * @filp: The file to apply the lock to * @fl: The lock to be applied * @conflock: Place to return a copy of the conflicting lock, if found. * * Add a POSIX style lock to a file. * We merge adjacent & overlapping locks whenever possible. * POSIX locks are sorted by owner task, then by starting address * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return posix_lock_inode(locks_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); /** * posix_lock_inode_wait - Apply a POSIX-style lock to a file * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * * Apply a POSIX style lock request to an inode. */ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, list_empty(&fl->fl_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } #ifdef CONFIG_MANDATORY_FILE_LOCKING /** * locks_mandatory_locked - Check for an active lock * @file: the file to check * * Searches the inode's list of locks to find any POSIX locks which conflict. * This function is called from locks_verify_locked() only. */ int locks_mandatory_locked(struct file *file) { int ret; struct inode *inode = locks_inode(file); struct file_lock_context *ctx; struct file_lock *fl; ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) return 0; /* * Search the lock list for this inode for any POSIX locks. */ spin_lock(&ctx->flc_lock); ret = 0; list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && fl->fl_owner != file) { ret = -EAGAIN; break; } } spin_unlock(&ctx->flc_lock); return ret; } /** * locks_mandatory_area - Check for a conflicting lock * @inode: the file to check * @filp: how the file was opened (if it was) * @start: first byte in the file to check * @end: lastbyte in the file to check * @type: %F_WRLCK for a write lock, else %F_RDLCK * * Searches the inode's list of locks to find any POSIX locks which conflict. */ int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, loff_t end, unsigned char type) { struct file_lock fl; int error; bool sleep = false; locks_init_lock(&fl); fl.fl_pid = current->tgid; fl.fl_file = filp; fl.fl_flags = FL_POSIX | FL_ACCESS; if (filp && !(filp->f_flags & O_NONBLOCK)) sleep = true; fl.fl_type = type; fl.fl_start = start; fl.fl_end = end; for (;;) { if (filp) { fl.fl_owner = filp; fl.fl_flags &= ~FL_SLEEP; error = posix_lock_inode(inode, &fl, NULL); if (!error) break; } if (sleep) fl.fl_flags |= FL_SLEEP; fl.fl_owner = current->files; error = posix_lock_inode(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl.fl_wait, list_empty(&fl.fl_blocked_member)); if (!error) { /* * If we've been sleeping someone might have * changed the permissions behind our back. */ if (__mandatory_lock(inode)) continue; } break; } locks_delete_block(&fl); return error; } EXPORT_SYMBOL(locks_mandatory_area); #endif /* CONFIG_MANDATORY_FILE_LOCKING */ static void lease_clear_pending(struct file_lock *fl, int arg) { switch (arg) { case F_UNLCK: fl->fl_flags &= ~FL_UNLOCK_PENDING; fallthrough; case F_RDLCK: fl->fl_flags &= ~FL_DOWNGRADE_PENDING; } } /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { int error = assign_type(fl, arg); if (error) return error; lease_clear_pending(fl, arg); locks_wake_up_blocks(fl); if (arg == F_UNLCK) { struct file *filp = fl->fl_file; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } locks_delete_lock_ctx(fl, dispose); } return 0; } EXPORT_SYMBOL(lease_modify); static bool past_time(unsigned long then) { if (!then) /* 0 is a special value meaning "this never expires": */ return false; return time_after(jiffies, then); } static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl, *tmp; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) lease_modify(fl, F_UNLCK, dispose); } } static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) { bool rc; if (lease->fl_lmops->lm_breaker_owns_lease && lease->fl_lmops->lm_breaker_owns_lease(lease)) return false; if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) { rc = false; goto trace; } if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) { rc = false; goto trace; } rc = locks_conflict(breaker, lease); trace: trace_leases_conflict(rc, lease, breaker); return rc; } static bool any_leases_conflict(struct inode *inode, struct file_lock *breaker) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) return true; } return false; } /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return * @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR: * break all leases * @type: FL_LEASE: break leases and delegations; FL_DELEG: break * only delegations * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on * a call to open() or truncate(). This function can sleep unless you * specified %O_NONBLOCK to your open(). */ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock_context *ctx; struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); if (!any_leases_conflict(inode, new_fl)) goto out; break_time = 0; if (lease_break_time > 0) { break_time = jiffies + lease_break_time * HZ; if (break_time == 0) break_time++; /* so that 0 means no break time */ } list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { if (fl->fl_flags & FL_UNLOCK_PENDING) continue; fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { if (lease_breaking(fl)) continue; fl->fl_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) locks_delete_lock_ctx(fl, &dispose); } if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; locks_insert_block(fl, new_fl, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, list_empty(&new_fl->fl_blocked_member), break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); if (error >= 0) { /* * Wait for the next conflicting lease that has not been * broken yet */ if (error == 0) time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; error = 0; } out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); free_lock: locks_free_lock(new_fl); return error; } EXPORT_SYMBOL(__break_lease); /** * lease_get_mtime - update modified time of an inode with exclusive lease * @inode: the inode * @time: pointer to a timespec which contains the last modified time * * This is to force NFS clients to flush their caches for files with * exclusive leases. The justification is that if someone has an * exclusive lease, then they could be modifying it. */ void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; struct file_lock *fl; ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); fl = list_first_entry_or_null(&ctx->flc_lease, struct file_lock, fl_list); if (fl && (fl->fl_type == F_WRLCK)) has_lease = true; spin_unlock(&ctx->flc_lock); } if (has_lease) *time = current_time(inode); } EXPORT_SYMBOL(lease_get_mtime); /** * fcntl_getlease - Enquire what lease is currently active * @filp: the file * * The value returned by this function will be one of * (if no lease break is pending): * * %F_RDLCK to indicate a shared lease is held. * * %F_WRLCK to indicate an exclusive lease is held. * * %F_UNLCK to indicate no lease is held. * * (if a lease break is pending): * * %F_RDLCK to indicate an exclusive lease needs to be * changed to a shared lease (or removed). * * %F_UNLCK to indicate the lease needs to be removed. * * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file != filp) continue; type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } return type; } /** * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * * Check to see if there's an existing open fd on this file that would * conflict with the lease we're trying to set. */ static int check_conflicting_open(struct file *filp, const long arg, int flags) { struct inode *inode = locks_inode(filp); int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; if (flags & FL_DELEG) /* We leave these checks to the caller */ return 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; else if (arg != F_WRLCK) return 0; /* * Make sure that only read/write count is from lease requestor. * Note that this will result in denying write leases when i_writecount * is negative, which is what we want. (We shouldn't grant write leases * on files open for execution.) */ if (filp->f_mode & FMODE_WRITE) self_wcount = 1; else if (filp->f_mode & FMODE_READ) self_rcount = 1; if (atomic_read(&inode->i_writecount) != self_wcount || atomic_read(&inode->i_readcount) != self_rcount) return -EAGAIN; return 0; } static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct file_lock *fl, *my_fl = NULL, *lease; struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); lease = *flp; trace_generic_add_lease(inode, lease); /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) return -ENOMEM; /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock * because delegations are an optional optimization, and if * there's some chance of a conflict--we'd rather not * bother, maybe that's a sign this just isn't a good file to * hand out a delegation on. */ if (is_deleg && !inode_trylock(inode)) return -EAGAIN; if (is_deleg && arg == F_WRLCK) { /* Write delegations are not currently supported: */ inode_unlock(inode); WARN_ON_ONCE(1); return -EINVAL; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) goto out; /* * At this point, we know that if there is an exclusive * lease on this file, then we hold it on this filp * (otherwise our open of this file would have blocked). * And if we are trying to acquire an exclusive lease, * then the file is not open by anyone (including us) * except for this filp. */ error = -EAGAIN; list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && fl->fl_owner == lease->fl_owner) { my_fl = fl; continue; } /* * No exclusive leases if someone else has a lease on * this file: */ if (arg == F_WRLCK) goto out; /* * Modifying our existing lease is OK, but no getting a * new lease if someone else is opening for write: */ if (fl->fl_flags & FL_UNLOCK_PENDING) goto out; } if (my_fl != NULL) { lease = my_fl; error = lease->fl_lmops->lm_change(lease, arg, &dispose); if (error) goto out; goto out_setup; } error = -EINVAL; if (!leases_enable) goto out; locks_insert_lock_ctx(lease, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting * open but before the lease was inserted. Check again for a * conflicting open and cancel the lease if there is one. * * We also add a barrier here to ensure that the insertion of the lock * precedes these checks. */ smp_mb(); error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) { locks_unlink_lock_ctx(lease); goto out; } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) *flp = NULL; return error; } static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && fl->fl_owner == owner) { victim = fl; break; } } trace_generic_delete_lease(inode, victim); if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } /** * generic_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @flp: input - file_lock to use, output - file_lock inserted * @priv: private data for lm_setup (may be NULL if lm_setup * doesn't require it) * * The (input) flp->fl_lmops->lm_break function is required * by break_lease(). */ int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct inode *inode = locks_inode(filp); int error; if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = security_file_lock(filp, arg); if (error) return error; switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); case F_RDLCK: case F_WRLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; } return generic_add_lease(filp, arg, flp, priv); default: return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); #if IS_ENABLED(CONFIG_SRCU) /* * Kernel subsystems can register to be notified on any attempt to set * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd * to close files that it may have cached when there is an attempt to set a * conflicting lease. */ static struct srcu_notifier_head lease_notifier_chain; static inline void lease_notifier_chain_init(void) { srcu_init_notifier_head(&lease_notifier_chain); } static inline void setlease_notifier(long arg, struct file_lock *lease) { if (arg != F_UNLCK) srcu_notifier_call_chain(&lease_notifier_chain, arg, lease); } int lease_register_notifier(struct notifier_block *nb) { return srcu_notifier_chain_register(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { srcu_notifier_chain_unregister(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_unregister_notifier); #else /* !IS_ENABLED(CONFIG_SRCU) */ static inline void lease_notifier_chain_init(void) { } static inline void setlease_notifier(long arg, struct file_lock *lease) { } int lease_register_notifier(struct notifier_block *nb) { return 0; } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { } EXPORT_SYMBOL_GPL(lease_unregister_notifier); #endif /* IS_ENABLED(CONFIG_SRCU) */ /** * vfs_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @lease: file_lock to use when adding a lease * @priv: private info for lm_setup when adding a lease (may be * NULL if lm_setup doesn't require it) * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It * may be NULL if the lm_setup operation doesn't require it. */ int vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) { if (lease) setlease_notifier(arg, *lease); if (filp->f_op->setlease) return filp->f_op->setlease(filp, arg, lease, priv); else return generic_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(vfs_setlease); static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) { struct file_lock *fl; struct fasync_struct *new; int error; fl = lease_alloc(filp, arg); if (IS_ERR(fl)) return PTR_ERR(fl); new = fasync_alloc(); if (!new) { locks_free_lock(fl); return -ENOMEM; } new->fa_fd = fd; error = vfs_setlease(filp, arg, &fl, (void **)&new); if (fl) locks_free_lock(fl); if (new) fasync_free(new); return error; } /** * fcntl_setlease - sets a lease on an open file * @fd: open file descriptor * @filp: file pointer * @arg: type of lease to obtain * * Call this fcntl to establish a lease on the file. * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, arg); } /** * flock_lock_inode_wait - Apply a FLOCK-style lock to a file * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a FLOCK style lock request to an inode. */ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, list_empty(&fl->fl_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /** * locks_lock_inode_wait - Apply a lock to an inode * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a POSIX or FLOCK style lock request to an inode. */ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int res = 0; switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: res = posix_lock_inode_wait(inode, fl); break; case FL_FLOCK: res = flock_lock_inode_wait(inode, fl); break; default: BUG(); } return res; } EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. * @fd: the file descriptor to lock. * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. * The @cmd can be one of: * * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. * - %LOCK_MAND -- a 'mandatory' flock. * This exists to emulate Windows Share Modes. * * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other * processes read and write access respectively. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { struct fd f = fdget(fd); struct file_lock *lock; int can_sleep, unlock; int error; error = -EBADF; if (!f.file) goto out; can_sleep = !(cmd & LOCK_NB); cmd &= ~LOCK_NB; unlock = (cmd == LOCK_UN); if (!unlock && !(cmd & LOCK_MAND) && !(f.file->f_mode & (FMODE_READ|FMODE_WRITE))) goto out_putf; lock = flock_make_lock(f.file, cmd, NULL); if (IS_ERR(lock)) { error = PTR_ERR(lock); goto out_putf; } if (can_sleep) lock->fl_flags |= FL_SLEEP; error = security_file_lock(f.file, lock->fl_type); if (error) goto out_free; if (f.file->f_op->flock) error = f.file->f_op->flock(f.file, (can_sleep) ? F_SETLKW : F_SETLK, lock); else error = locks_lock_file_wait(f.file, lock); out_free: locks_free_lock(lock); out_putf: fdput(f); out: return error; } /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for * @fl: The byte-range in the file to test; also used to hold result * * On entry, @fl does not contain a lock, but identifies a range (fl_start, fl_end) * in the file (c.flc_file), and an owner (c.flc_owner) for whom existing locks * should be ignored. c.flc_type and c.flc_flags are ignored. * Both fl_lmops and fl_ops in @fl must be NULL. * Returns -ERRNO on failure. Indicates presence of conflicting lock by * setting fl->fl_type to something other than F_UNLCK. * * If vfs_test_lock() does find a lock and return it, the caller must * use locks_free_lock() or locks_release_private() on the returned lock. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { WARN_ON_ONCE(fl->fl_ops || fl->fl_lmops); WARN_ON_ONCE(filp != fl->fl_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_test_lock); /** * locks_translate_pid - translate a file_lock's fl_pid number into a namespace * @fl: The file_lock who's fl_pid should be translated * @ns: The namespace into which the pid should be translated * * Used to tranlate a fl_pid into a namespace virtual pid number */ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns) { pid_t vnr; struct pid *pid; if (IS_OFDLCK(fl)) return -1; if (IS_REMOTELCK(fl)) return fl->fl_pid; /* * If the flock owner process is dead and its pid has been already * freed, the translation below won't work, but we still want to show * flock owner pid number in init pidns. */ if (ns == &init_pid_ns) return (pid_t)fl->fl_pid; rcu_read_lock(); pid = find_pid_ns(fl->fl_pid, &init_pid_ns); vnr = pid_nr_ns(pid, ns); rcu_read_unlock(); return vnr; } static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via * legacy 32bit flock. */ if (fl->fl_start > OFFT_OFFSET_MAX) return -EOVERFLOW; if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX) return -EOVERFLOW; #endif flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->fl_type; return 0; } #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->fl_type; } #endif /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_GETLK; fl->fl_flags |= FL_OFDLCK; fl->fl_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->fl_type; if (fl->fl_type != F_UNLCK) { error = posix_lock_to_flock(flock, fl); if (error) goto out; } out: locks_free_lock(fl); return error; } /** * vfs_lock_file - file byte range lock * @filp: The file to apply the lock to * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.) * @fl: The lock to be applied * @conf: Place to return a copy of the conflicting lock, if found. * * A caller that doesn't care about the conflicting lock may pass NULL * as the final argument. * * If the filesystem defines a private ->lock() method, then @conf will * be left unchanged; so a caller that cares should initialize it to * some acceptable default. * * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) * lm_grant is set. Callers expecting ->lock() to return asynchronously * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if) * the request is for a blocking lock. When ->lock() does return asynchronously, * it must return FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock * request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine * with the result. If the request timed out the callback routine will return a * nonzero return code and the file system should release the lock. The file * system is also responsible to keep a corresponding posix lock when it * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); } EXPORT_SYMBOL_GPL(vfs_lock_file); static int do_lock_file_wait(struct file *filp, unsigned int cmd, struct file_lock *fl) { int error; error = security_file_lock(filp, fl->fl_type); if (error) return error; for (;;) { error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, list_empty(&fl->fl_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { switch (fl->fl_type) { case F_RDLCK: if (!(fl->fl_file->f_mode & FMODE_READ)) return -EBADF; break; case F_WRLCK: if (!(fl->fl_file->f_mode & FMODE_WRITE)) return -EBADF; } return 0; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { error = -EAGAIN; goto out; } error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; fallthrough; case F_SETLKW: file_lock->fl_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->fl_type != F_UNLCK && !(file_lock->fl_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } #if BITS_PER_LONG == 32 /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock64_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_GETLK64; fl->fl_flags |= FL_OFDLCK; fl->fl_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->fl_type; if (fl->fl_type != F_UNLCK) posix_lock_to_flock64(flock, fl); out: locks_free_lock(fl); return error; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { error = -EAGAIN; goto out; } error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK64; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; fallthrough; case F_SETLKW64: file_lock->fl_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->fl_type != F_UNLCK && !(file_lock->fl_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: locks_free_lock(file_lock); return error; } #endif /* BITS_PER_LONG == 32 */ /* * This function is called when the file is being removed * from the task's fd array. POSIX locks belonging to this task * are deleted at this time. */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; struct inode *inode = locks_inode(filp); struct file_lock lock; struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; locks_init_lock(&lock); lock.fl_type = F_UNLCK; lock.fl_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; lock.fl_owner = owner; lock.fl_pid = current->tgid; lock.fl_file = filp; lock.fl_ops = NULL; lock.fl_lmops = NULL; error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); trace_locks_remove_posix(inode, &lock, error); } EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; struct inode *inode = locks_inode(filp); if (list_empty(&flctx->flc_flock)) return; flock_make_lock(filp, LOCK_UN, &fl); fl.fl_flags |= FL_CLOSE; if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); else flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl); } /* The i_flctx must be valid when calling into here */ static void locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { struct file_lock *fl, *tmp; LIST_HEAD(dispose); if (list_empty(&ctx->flc_lease)) return; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; ctx = locks_inode_context(locks_inode(filp)); if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp, ctx); /* remove any leases */ locks_remove_lease(filp, ctx); spin_lock(&ctx->flc_lock); locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE"); spin_unlock(&ctx->flc_lock); } /** * vfs_cancel_lock - file byte range unblock lock * @filp: The file to apply the unblock to * @fl: The lock to be unblocked * * Used by lock managers to cancel blocked requests */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_cancel_lock); /** * vfs_inode_has_locks - are any file locks held on @inode? * @inode: inode to check for locks * * Return true if there are any FL_POSIX or FL_FLOCK locks currently * set on @inode. */ bool vfs_inode_has_locks(struct inode *inode) { struct file_lock_context *ctx; bool ret; ctx = locks_inode_context(inode); if (!ctx) return false; spin_lock(&ctx->flc_lock); ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); spin_unlock(&ctx->flc_lock); return ret; } EXPORT_SYMBOL_GPL(vfs_inode_has_locks); #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> struct locks_iterator { int li_cpu; loff_t li_pos; }; static void lock_get_status(struct seq_file *f, struct file_lock *fl, loff_t id, char *pfx) { struct inode *inode = NULL; unsigned int fl_pid; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); fl_pid = locks_translate_pid(fl, proc_pidns); /* * If lock owner is dead (and pid is freed) or not visible in current * pidns, zero is shown as a pid value. Check lock info from * init_pid_ns to get saved lock pid value. */ if (fl->fl_file != NULL) inode = locks_inode(fl->fl_file); seq_printf(f, "%lld:%s ", id, pfx); if (IS_POSIX(fl)) { if (fl->fl_flags & FL_ACCESS) seq_puts(f, "ACCESS"); else if (IS_OFDLCK(fl)) seq_puts(f, "OFDLCK"); else seq_puts(f, "POSIX "); seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : mandatory_lock(inode) ? "MANDATORY" : "ADVISORY "); } else if (IS_FLOCK(fl)) { if (fl->fl_type & LOCK_MAND) { seq_puts(f, "FLOCK MSNFS "); } else { seq_puts(f, "FLOCK ADVISORY "); } } else if (IS_LEASE(fl)) { if (fl->fl_flags & FL_DELEG) seq_puts(f, "DELEG "); else seq_puts(f, "LEASE "); if (lease_breaking(fl)) seq_puts(f, "BREAKING "); else if (fl->fl_file) seq_puts(f, "ACTIVE "); else seq_puts(f, "BREAKER "); } else { seq_puts(f, "UNKNOWN UNKNOWN "); } if (fl->fl_type & LOCK_MAND) { seq_printf(f, "%s ", (fl->fl_type & LOCK_READ) ? (fl->fl_type & LOCK_WRITE) ? "RW " : "READ " : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE "); } else { int type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type; seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : (type == F_RDLCK) ? "READ" : "UNLCK"); } if (inode) { /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%lu ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { seq_printf(f, "%d <none>:0 ", fl_pid); } if (IS_POSIX(fl)) { if (fl->fl_end == OFFSET_MAX) seq_printf(f, "%Ld EOF\n", fl->fl_start); else seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end); } else { seq_puts(f, "0 EOF\n"); } } static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock *fl, *bfl; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); fl = hlist_entry(v, struct file_lock, fl_link); if (locks_translate_pid(fl, proc_pidns) == 0) return 0; lock_get_status(f, fl, iter->li_pos, ""); list_for_each_entry(bfl, &fl->fl_blocked_requests, fl_blocked_member) lock_get_status(f, bfl, iter->li_pos, " ->"); return 0; } static void __show_fd_locks(struct seq_file *f, struct list_head *head, int *id, struct file *filp, struct files_struct *files) { struct file_lock *fl; list_for_each_entry(fl, head, fl_list) { if (filp != fl->fl_file) continue; if (fl->fl_owner != files && fl->fl_owner != filp) continue; (*id)++; seq_puts(f, "lock:\t"); lock_get_status(f, fl, *id, ""); } } void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; int id = 0; ctx = locks_inode_context(inode); if (!ctx) return; spin_lock(&ctx->flc_lock); __show_fd_locks(f, &ctx->flc_flock, &id, filp, files); __show_fd_locks(f, &ctx->flc_posix, &id, filp, files); __show_fd_locks(f, &ctx->flc_lease, &id, filp, files); spin_unlock(&ctx->flc_lock); } static void *locks_start(struct seq_file *f, loff_t *pos) __acquires(&blocked_lock_lock) { struct locks_iterator *iter = f->private; iter->li_pos = *pos + 1; percpu_down_write(&file_rwsem); spin_lock(&blocked_lock_lock); return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { struct locks_iterator *iter = f->private; ++iter->li_pos; return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) __releases(&blocked_lock_lock) { spin_unlock(&blocked_lock_lock); percpu_up_write(&file_rwsem); } static const struct seq_operations locks_seq_operations = { .start = locks_start, .next = locks_next, .stop = locks_stop, .show = locks_show, }; static int __init proc_locks_init(void) { proc_create_seq_private("locks", 0, NULL, &locks_seq_operations, sizeof(struct locks_iterator), NULL); return 0; } fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) { int i; flctx_cache = kmem_cache_create("file_lock_ctx", sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); spin_lock_init(&fll->lock); INIT_HLIST_HEAD(&fll->hlist); } lease_notifier_chain_init(); return 0; } core_initcall(filelock_init); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_BIT_H #define _LINUX_WAIT_BIT_H /* * Linux wait-bit related types and methods: */ #include <linux/wait.h> struct wait_bit_key { void *flags; int bit_nr; unsigned long timeout; }; struct wait_bit_queue_entry { struct wait_bit_key key; struct wait_queue_entry wq_entry; }; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); void wake_up_bit(void *word, int bit); int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); struct wait_queue_head *bit_waitqueue(void *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue_entry name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ .wq_entry = { \ .private = current, \ .func = wake_bit_function, \ .entry = \ LIST_HEAD_INIT((name).wq_entry.entry), \ }, \ } extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit. * For instance, if one were to have waiters on a bitflag, one would * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, mode); } /** * wait_on_bit_io - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), but calls * io_schedule() instead of schedule() for the actual waiting. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, mode); } /** * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), except also takes a * timeout parameter. * * Returned value will be zero if the bit was cleared before the * @timeout elapsed, or non-zero if the @timeout elapsed or process * received a signal and the mode permitted wakeup on that signal. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, mode, timeout); } /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared, and allow the waiting action to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } /** * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit * when one intends to set it, for instance, trying to lock bitflags. * For instance, if one were to have waiters trying to set bitflag * and waiting for it to clear before setting it, one would call * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); } /** * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to atomically set it. This is similar * to wait_on_bit(), but calls io_schedule() instead of schedule() * for the actual waiting. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); } /** * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to set it, and allow the waiting action * to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, action, mode); } extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); extern void wake_up_var(void *var); extern wait_queue_head_t *__var_waitqueue(void *p); #define ___wait_var_event(var, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_head *__wq_head = __var_waitqueue(var); \ struct wait_bit_queue_entry __wbq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_var_entry(&__wbq_entry, var, \ exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(__wq_head, \ &__wbq_entry.wq_entry, \ state); \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(__wq_head, &__wbq_entry.wq_entry); \ __out: __ret; \ }) #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event(var, condition); \ } while (0) #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_killable(var, condition); \ __ret; \ }) #define __wait_var_event_timeout(var, condition, timeout) \ ___wait_var_event(var, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_var_event_timeout(var, condition, timeout); \ __ret; \ }) #define __wait_var_event_interruptible(var, condition) \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_interruptible(var, condition); \ __ret; \ }) /** * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * * @bit: the bit of the word being waited on * @word: the word being waited on, a kernel virtual address * * You can use this helper if bitflags are manipulated atomically rather than * non-atomically under a lock. */ static inline void clear_and_wake_up_bit(int bit, void *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ smp_mb__after_atomic(); wake_up_bit(word, bit); } #endif /* _LINUX_WAIT_BIT_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 | #ifdef CONFIG_PREEMPTIRQ_TRACEPOINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM preemptirq #if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PREEMPTIRQ_H #include <linux/ktime.h> #include <linux/tracepoint.h> #include <linux/string.h> #include <asm/sections.h> DECLARE_EVENT_CLASS(preemptirq_template, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip), TP_STRUCT__entry( __field(s32, caller_offs) __field(s32, parent_offs) ), TP_fast_assign( __entry->caller_offs = (s32)(ip - (unsigned long)_stext); __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext); ), TP_printk("caller=%pS parent=%pS", (void *)((unsigned long)(_stext) + __entry->caller_offs), (void *)((unsigned long)(_stext) + __entry->parent_offs)) ); #ifdef CONFIG_TRACE_IRQFLAGS DEFINE_EVENT(preemptirq_template, irq_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, irq_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #endif #ifdef CONFIG_TRACE_PREEMPT_TOGGLE DEFINE_EVENT(preemptirq_template, preempt_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, preempt_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif #endif /* _TRACE_PREEMPTIRQ_H */ #include <trace/define_trace.h> #else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */ #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> #ifdef CONFIG_SET_FS /* * Force the uaccess routines to be wired up for actual userspace access, * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone * using force_uaccess_end below. */ static inline mm_segment_t force_uaccess_begin(void) { mm_segment_t fs = get_fs(); set_fs(USER_DS); return fs; } static inline void force_uaccess_end(mm_segment_t oldfs) { set_fs(oldfs); } #else /* CONFIG_SET_FS */ typedef struct { /* empty dummy */ } mm_segment_t; #ifndef TASK_SIZE_MAX #define TASK_SIZE_MAX TASK_SIZE #endif #define uaccess_kernel() (false) #define user_addr_max() (TASK_SIZE_MAX) static inline mm_segment_t force_uaccess_begin(void) { return (mm_segment_t) { }; } static inline void force_uaccess_end(mm_segment_t oldfs) { } #endif /* CONFIG_SET_FS */ /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } #ifdef INLINE_COPY_FROM_USER static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } #else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (likely(check_copy_size(to, n, false))) n = _copy_from_user(to, from, n); return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (likely(check_copy_size(from, n, true))) n = _copy_to_user(to, from, n); return n; } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(to, n) && access_ok(from, n)) n = raw_copy_in_user(to, from, n); return n; } #endif #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM x86_fpu #if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FPU_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(x86_fpu, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu), TP_STRUCT__entry( __field(struct fpu *, fpu) __field(bool, load_fpu) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, __entry->load_fpu, __entry->xfeatures, __entry->xcomp_bv ) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_dropped, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_src, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH asm/trace/ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE fpu #endif /* _TRACE_FPU_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> #include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writtable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ /* * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify * which does not support FS_ERROR. */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ /* * Valid fsnotify group priorities. Events are send in order from highest * priority to lowest priority. We default to the lowest priority. */ #define FS_PRIO_0 0 /* normal notifiers, no permissions */ #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ #define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* Hash table of events for merge */ struct hlist_head *merge_hash; /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* * These helpers are used to prevent deadlock when reclaiming inodes with * evictable marks of the same group that is allocating a new mark. */ static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); if (group->flags & FSNOTIFY_GROUP_NOFS) group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { if (group->flags & FSNOTIFY_GROUP_NOFS) memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); if (group->flags & FSNOTIFY_GROUP_NOFS) WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, FSNOTIFY_EVENT_ERROR, }; struct fs_error_report { int error; struct inode *inode; struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_DENTRY: return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: return NULL; } } static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_DENTRY: /* Non const is needed for dget() */ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; default: return NULL; } } static inline struct super_block *fsnotify_data_sb(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return ((struct inode *)data)->i_sb; case FSNOTIFY_EVENT_DENTRY: return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: return NULL; } } static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_ERROR: return (struct fs_error_report *) data; default: return NULL; } } /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not * the other way around, because an event can match different watched objects * of the same object type. * For example, both parent and child are watching an object of type inode. */ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_INODE, FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_COUNT }; /* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { iter_info->report_mask |= (1U << iter_type); } static inline struct fsnotify_mark *fsnotify_iter_mark( struct fsnotify_iter_info *iter_info, int iter_type) { if (fsnotify_iter_should_report_type(iter_info, iter_type)) return iter_info->marks[iter_type]; return NULL; } static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, struct fsnotify_mark **markp) { while (type < FSNOTIFY_ITER_TYPE_COUNT) { *markp = fsnotify_iter_mark(iter, type); if (*markp) break; type++; } return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) #define fsnotify_foreach_iter_mark_type(iter, mark, type) \ for (type = 0; \ type = fsnotify_iter_step(iter, type, &mark), \ type < FSNOTIFY_ITER_TYPE_COUNT; \ type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached * to. fsnotify_connp_t * is how we refer from connector back to object. */ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { /* Object pointer [lock] */ fsnotify_connp_t *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ __u32 ignore_mask; /* General fsnotify mark flags */ #define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 /* inotify mark flags */ #define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)); static inline int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *)) { return fsnotify_insert_event(group, event, merge, NULL); } /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) { return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list); } extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* * Canonical "ignore mask" including event flags. * * Note the subtle semantic difference from the legacy ->ignored_mask. * ->ignored_mask traditionally only meant which events should be ignored, * while ->ignore_mask also includes flags regarding the type of objects on * which events should be ignored. */ static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) { __u32 ignore_mask = mark->ignore_mask; /* The event flags in ignore mask take effect */ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return ignore_mask; /* * Legacy behavior: * - Always ignore events on dir * - Ignore events on child if parent is watching children */ ignore_mask |= FS_ISDIR; ignore_mask &= ~FS_EVENT_ON_CHILD; ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; return ignore_mask; } /* Legacy ignored_mask - only event types to ignore */ static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) { return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; } /* * Check if mask (or ignore mask) should be applied depending if victim is a * directory and whether it is reported to a watching parent. */ static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, int iter_type) { /* Should mask be applied to a directory? */ if (is_dir && !(mask & FS_ISDIR)) return false; /* Should mask be applied to a child? */ if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && !(mask & FS_EVENT_ON_CHILD)) return false; return true; } /* * Effective ignore mask taking into account if event victim is a * directory and whether it is reported to a watching parent. */ static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, bool is_dir, int iter_type) { __u32 ignore_mask = fsnotify_ignored_events(mark); if (!ignore_mask) return 0; /* For non-dir and non-child, no need to consult the event flags */ if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) return ignore_mask; ignore_mask = fsnotify_ignore_mask(mark); if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) return 0; return ignore_mask & ALL_FSNOTIFY_EVENTS; } /* Get mask for calculating object interest taking ignore mask into account */ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) { __u32 mask = mark->mask; if (!fsnotify_ignored_events(mark)) return mask; /* Interest in FS_MODIFY may be needed for clearing ignore mask */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mask |= FS_MODIFY; /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. */ return mask | mark->ignore_mask; } /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group); /* Get cached fsid of filesystem containing object */ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* Clear all of the marks of a group attached to a given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } #else static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 | // SPDX-License-Identifier: GPL-2.0-only /* * NSA Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux hook function implementations. * * Authors: Stephen Smalley, <sds@tycho.nsa.gov> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com> * Eric Paris <eparis@redhat.com> * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * <dgoeddel@trustedcs.com> * Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2007 Hitachi Software Engineering Co., Ltd. * Yuichi Nakamura <ynakam@hitachisoft.jp> * Copyright (C) 2016 Mellanox Technologies */ #include <linux/init.h> #include <linux/kd.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/tracehook.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/lsm_hooks.h> #include <linux/xattr.h> #include <linux/capability.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/swap.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/dcache.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ #include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/structs.h> #include <linux/quota.h> #include <linux/un.h> /* for Unix socket types */ #include <net/af_unix.h> /* for Unix socket types */ #include <linux/parser.h> #include <linux/nfs_mount.h> #include <net/ipv6.h> #include <linux/hugetlb.h> #include <linux/personality.h> #include <linux/audit.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/posix-timers.h> #include <linux/syslog.h> #include <linux/user_namespace.h> #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> #include <linux/bpf.h> #include <linux/kernfs.h> #include <linux/stringhash.h> /* for hashlen_string() */ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> #include "avc.h" #include "objsec.h" #include "netif.h" #include "netnode.h" #include "netport.h" #include "ibpkey.h" #include "xfrm.h" #include "netlabel.h" #include "audit.h" #include "avc_ss.h" struct selinux_state selinux_state; /* SECMARK reference count */ static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static int selinux_enforcing_boot __initdata; static int __init enforcing_setup(char *str) { unsigned long enforcing; if (!kstrtoul(str, 0, &enforcing)) selinux_enforcing_boot = enforcing ? 1 : 0; return 1; } __setup("enforcing=", enforcing_setup); #else #define selinux_enforcing_boot 1 #endif int selinux_enabled_boot __initdata = 1; #ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM static int __init selinux_enabled_setup(char *str) { unsigned long enabled; if (!kstrtoul(str, 0, &enabled)) selinux_enabled_boot = enabled ? 1 : 0; return 1; } __setup("selinux=", selinux_enabled_setup); #endif static unsigned int selinux_checkreqprot_boot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE; static int __init checkreqprot_setup(char *str) { unsigned long checkreqprot; if (!kstrtoul(str, 0, &checkreqprot)) { selinux_checkreqprot_boot = checkreqprot ? 1 : 0; if (checkreqprot) pr_warn("SELinux: checkreqprot set to 1 via kernel parameter. This is deprecated and will be rejected in a future kernel release.\n"); } return 1; } __setup("checkreqprot=", checkreqprot_setup); /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * * Description: * This function checks the SECMARK reference counter to see if any SECMARK * targets are currently configured, if the reference counter is greater than * zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is * enabled, false (0) if SECMARK is disabled. If the always_check_network * policy capability is enabled, SECMARK is always considered enabled. * */ static int selinux_secmark_enabled(void) { return (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } /** * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled * * Description: * This function checks if NetLabel or labeled IPSEC is enabled. Returns true * (1) if any are enabled or false (0) if neither are enabled. If the * always_check_network policy capability is enabled, peer labeling * is always considered enabled. * */ static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_netif_flush(); sel_netnode_flush(); sel_netport_flush(); synchronize_net(); } return 0; } static int selinux_lsm_notifier_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_ib_pkey_flush(); call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); } return 0; } /* * initialise the security for the init task */ static void cred_init_security(void) { struct cred *cred = (struct cred *) current->real_cred; struct task_security_struct *tsec; tsec = selinux_cred(cred); tsec->osid = tsec->sid = SECINITSID_KERNEL; } /* * get the security ID of a set of credentials */ static inline u32 cred_sid(const struct cred *cred) { const struct task_security_struct *tsec; tsec = selinux_cred(cred); return tsec->sid; } /* * get the objective security ID of a task */ static inline u32 task_sid(const struct task_struct *task) { u32 sid; rcu_read_lock(); sid = cred_sid(__task_cred(task)); rcu_read_unlock(); return sid; } static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* * Try reloading inode security labels that have been marked as invalid. The * @may_sleep parameter indicates when sleeping and thus reloading labels is * allowed; when set to false, returns -ECHILD when the label is * invalid. The @dentry parameter should be set to a dentry of the inode. */ static int __inode_security_revalidate(struct inode *inode, struct dentry *dentry, bool may_sleep) { struct inode_security_struct *isec = selinux_inode(inode); might_sleep_if(may_sleep); if (selinux_initialized(&selinux_state) && isec->initialized != LABEL_INITIALIZED) { if (!may_sleep) return -ECHILD; /* * Try reloading the inode security label. This will fail if * @opt_dentry is NULL and no dentry for this inode can be * found; in that case, continue using the old label. */ inode_doinit_with_dentry(inode, dentry); } return 0; } static struct inode_security_struct *inode_security_novalidate(struct inode *inode) { return selinux_inode(inode); } static struct inode_security_struct *inode_security_rcu(struct inode *inode, bool rcu) { int error; error = __inode_security_revalidate(inode, NULL, !rcu); if (error) return ERR_PTR(error); return selinux_inode(inode); } /* * Get the security label of an inode. */ static struct inode_security_struct *inode_security(struct inode *inode) { __inode_security_revalidate(inode, NULL, true); return selinux_inode(inode); } static struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); return selinux_inode(inode); } /* * Get the security label of a dentry's backing inode. */ static struct inode_security_struct *backing_inode_security(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); __inode_security_revalidate(inode, dentry, true); return selinux_inode(inode); } static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); struct superblock_security_struct *sbsec; if (!isec) return; sbsec = inode->i_sb->s_security; /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste * time taking a lock doing nothing. * * The list_del_init() function can be safely called more than once. * It should not be possible for this function to be called with * concurrent list_add(), but for better safety against future changes * in the code, we use list_empty_careful() here. */ if (!list_empty_careful(&isec->list)) { spin_lock(&sbsec->isec_lock); list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } } static void superblock_free_security(struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; sb->s_security = NULL; kfree(sbsec); } struct selinux_mnt_opts { const char *fscontext, *context, *rootcontext, *defcontext; }; static void selinux_free_mnt_opts(void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; kfree(opts->fscontext); kfree(opts->context); kfree(opts->rootcontext); kfree(opts->defcontext); kfree(opts); } enum { Opt_error = -1, Opt_context = 0, Opt_defcontext = 1, Opt_fscontext = 2, Opt_rootcontext = 3, Opt_seclabel = 4, }; #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg} static struct { const char *name; int len; int opt; bool has_arg; } tokens[] = { A(context, true), A(fscontext, true), A(defcontext, true), A(rootcontext, true), A(seclabel, false), }; #undef A static int match_opt_prefix(char *s, int l, char **arg) { int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; if (len > l || memcmp(s, tokens[i].name, len)) continue; if (tokens[i].has_arg) { if (len == l || s[len] != '=') continue; *arg = s + len + 1; } else if (len != l) continue; return tokens[i].opt; } return Opt_error; } #define SEL_MOUNT_FAIL_MSG "SELinux: duplicate or incompatible mount options\n" static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(&selinux_state, tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(&selinux_state, tsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(&selinux_state, tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, NULL); return rc; } static int selinux_is_genfs_special_handling(struct super_block *sb) { /* Special handling. Genfs but also in-core setxattr handler */ return !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs") || (selinux_policycap_cgroupseclabel() && (!strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2"))); } static int selinux_is_sblabel_mnt(struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; /* * IMPORTANT: Double-check logic in this function when adding a new * SECURITY_FS_USE_* definition! */ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); switch (sbsec->behavior) { case SECURITY_FS_USE_XATTR: case SECURITY_FS_USE_TRANS: case SECURITY_FS_USE_TASK: case SECURITY_FS_USE_NATIVE: return 1; case SECURITY_FS_USE_GENFS: return selinux_is_genfs_special_handling(sb); /* Never allow relabeling on context mounts */ case SECURITY_FS_USE_MNTPOINT: case SECURITY_FS_USE_NONE: default: return 0; } } static int sb_finish_set_opts(struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); int rc = 0; if (sbsec->behavior == SECURITY_FS_USE_XATTR) { /* Make sure that the xattr handler exists and that no error other than -ENODATA is returned by getxattr on the root directory. -ENODATA is ok, as this may be the first boot of the SELinux kernel before we have assigned xattr values to the filesystem. */ if (!(root_inode->i_opflags & IOP_XATTR)) { pr_warn("SELinux: (dev %s, type %s) has no " "xattr support\n", sb->s_id, sb->s_type->name); rc = -EOPNOTSUPP; goto out; } rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) pr_warn("SELinux: (dev %s, type " "%s) has no security xattr handler\n", sb->s_id, sb->s_type->name); else pr_warn("SELinux: (dev %s, type " "%s) getxattr errno %d\n", sb->s_id, sb->s_type->name, -rc); goto out; } } sbsec->flags |= SE_SBINITIALIZED; /* * Explicitly set or clear SBLABEL_MNT. It's not sufficient to simply * leave the flag untouched because sb_clone_mnt_opts might be handing * us a superblock that needs the flag to be cleared. */ if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; else sbsec->flags &= ~SBLABEL_MNT; /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); /* Initialize any other inodes associated with the superblock, e.g. inodes created prior to initial policy load or inodes created during get_sb by a pseudo filesystem that directly populates itself. */ spin_lock(&sbsec->isec_lock); while (!list_empty(&sbsec->isec_head)) { struct inode_security_struct *isec = list_first_entry(&sbsec->isec_head, struct inode_security_struct, list); struct inode *inode = isec->inode; list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { if (!IS_PRIVATE(inode)) inode_doinit_with_dentry(inode, NULL); iput(inode); } spin_lock(&sbsec->isec_lock); } spin_unlock(&sbsec->isec_lock); out: return rc; } static int bad_option(struct superblock_security_struct *sbsec, char flag, u32 old_sid, u32 new_sid) { char mnt_flags = sbsec->flags & SE_MNTMASK; /* check if the old mount command had the same options */ if (sbsec->flags & SE_SBINITIALIZED) if (!(sbsec->flags & flag) || (old_sid != new_sid)) return 1; /* check if we were passed the same options twice, * aka someone passed context=a,context=b */ if (!(sbsec->flags & SE_SBINITIALIZED)) if (mnt_flags & flag) return 1; return 0; } static int parse_sid(struct super_block *sb, const char *s, u32 *sid) { int rc = security_context_str_to_sid(&selinux_state, s, sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid" "(%s) failed for (dev %s, type %s) errno=%d\n", s, sb->s_id, sb->s_type->name, rc); return rc; } /* * Allow filesystems with binary mount data to explicitly set mount point * labeling information. */ static int selinux_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = sb->s_security; struct dentry *root = sbsec->sb->s_root; struct selinux_mnt_opts *opts = mnt_opts; struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; int rc = 0; mutex_lock(&sbsec->lock); if (!selinux_initialized(&selinux_state)) { if (!opts) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ goto out; } rc = -EINVAL; pr_warn("SELinux: Unable to set superblock options " "before the security server is initialized\n"); goto out; } if (kern_flags && !set_kern_flags) { /* Specifying internal flags without providing a place to * place the results is not allowed */ rc = -EINVAL; goto out; } /* * Binary mount data FS will come through this function twice. Once * from an explicit call and once from the generic calls from the vfs. * Since the generic VFS calls will not contain any security mount data * we need to skip the double mount verification. * * This does open a hole in which we will not notice if the first * mount using this sb set explict options and a second mount using * this sb does not set any security options. (The first options * will be used for both mounts) */ if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA) && !opts) goto out; root_isec = backing_inode_security_novalidate(root); /* * parse the mount options, check if they are valid sids. * also check if someone is trying to mount the same sb more * than once with different security options. */ if (opts) { if (opts->fscontext) { rc = parse_sid(sb, opts->fscontext, &fscontext_sid); if (rc) goto out; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, fscontext_sid)) goto out_double_mount; sbsec->flags |= FSCONTEXT_MNT; } if (opts->context) { rc = parse_sid(sb, opts->context, &context_sid); if (rc) goto out; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, context_sid)) goto out_double_mount; sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext) { rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid); if (rc) goto out; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, rootcontext_sid)) goto out_double_mount; sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext) { rc = parse_sid(sb, opts->defcontext, &defcontext_sid); if (rc) goto out; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, defcontext_sid)) goto out_double_mount; sbsec->flags |= DEFCONTEXT_MNT; } } if (sbsec->flags & SE_SBINITIALIZED) { /* previously mounted with options, but not on this attempt? */ if ((sbsec->flags & SE_MNTMASK) && !opts) goto out_double_mount; rc = 0; goto out; } if (strcmp(sb->s_type->name, "proc") == 0) sbsec->flags |= SE_SBPROC | SE_SBGENFS; if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "bpf") || !strcmp(sb->s_type->name, "pstore")) sbsec->flags |= SE_SBGENFS; if (!strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2")) sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR; if (!sbsec->behavior) { /* * Determine the labeling behavior to use for this * filesystem type. */ rc = security_fs_use(&selinux_state, sb); if (rc) { pr_warn("%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); goto out; } } /* * If this is a user namespace mount and the filesystem type is not * explicitly whitelisted, then no contexts are allowed on the command * line and security labels must be ignored. */ if (sb->s_user_ns != &init_user_ns && strcmp(sb->s_type->name, "tmpfs") && strcmp(sb->s_type->name, "ramfs") && strcmp(sb->s_type->name, "devpts")) { if (context_sid || fscontext_sid || rootcontext_sid || defcontext_sid) { rc = -EACCES; goto out; } if (sbsec->behavior == SECURITY_FS_USE_XATTR) { sbsec->behavior = SECURITY_FS_USE_MNTPOINT; rc = security_transition_sid(&selinux_state, current_sid(), current_sid(), SECCLASS_FILE, NULL, &sbsec->mntpoint_sid); if (rc) goto out; } goto out_set_opts; } /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; sbsec->sid = fscontext_sid; } /* * Switch to using mount point labeling behavior. * sets the label used on all file below the mountpoint, and will set * the superblock context if not already set. */ if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) { sbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (context_sid) { if (!fscontext_sid) { rc = may_context_mount_sb_relabel(context_sid, sbsec, cred); if (rc) goto out; sbsec->sid = context_sid; } else { rc = may_context_mount_inode_relabel(context_sid, sbsec, cred); if (rc) goto out; } if (!rootcontext_sid) rootcontext_sid = context_sid; sbsec->mntpoint_sid = context_sid; sbsec->behavior = SECURITY_FS_USE_MNTPOINT; } if (rootcontext_sid) { rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, cred); if (rc) goto out; root_isec->sid = rootcontext_sid; root_isec->initialized = LABEL_INITIALIZED; } if (defcontext_sid) { if (sbsec->behavior != SECURITY_FS_USE_XATTR && sbsec->behavior != SECURITY_FS_USE_NATIVE) { rc = -EINVAL; pr_warn("SELinux: defcontext option is " "invalid for this filesystem type\n"); goto out; } if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, sbsec, cred); if (rc) goto out; } sbsec->def_sid = defcontext_sid; } out_set_opts: rc = sb_finish_set_opts(sb); out: mutex_unlock(&sbsec->lock); return rc; out_double_mount: rc = -EINVAL; pr_warn("SELinux: mount invalid. Same superblock, different " "security settings for (dev %s, type %s)\n", sb->s_id, sb->s_type->name); goto out; } static int selinux_cmp_sb_context(const struct super_block *oldsb, const struct super_block *newsb) { struct superblock_security_struct *old = oldsb->s_security; struct superblock_security_struct *new = newsb->s_security; char oldflags = old->flags & SE_MNTMASK; char newflags = new->flags & SE_MNTMASK; if (oldflags != newflags) goto mismatch; if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid) goto mismatch; if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid) goto mismatch; if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid) goto mismatch; if (oldflags & ROOTCONTEXT_MNT) { struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root); struct inode_security_struct *newroot = backing_inode_security(newsb->s_root); if (oldroot->sid != newroot->sid) goto mismatch; } return 0; mismatch: pr_warn("SELinux: mount invalid. Same superblock, " "different security settings for (dev %s, " "type %s)\n", newsb->s_id, newsb->s_type->name); return -EBUSY; } static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { int rc = 0; const struct superblock_security_struct *oldsbsec = oldsb->s_security; struct superblock_security_struct *newsbsec = newsb->s_security; int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT); int set_context = (oldsbsec->flags & CONTEXT_MNT); int set_rootcontext = (oldsbsec->flags & ROOTCONTEXT_MNT); /* * if the parent was able to be mounted it clearly had no special lsm * mount options. thus we can safely deal with this superblock later */ if (!selinux_initialized(&selinux_state)) return 0; /* * Specifying internal flags without providing a place to * place the results is not allowed. */ if (kern_flags && !set_kern_flags) return -EINVAL; /* how can we clone if the old one wasn't set up?? */ BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED)); /* if fs is reusing a sb, make sure that the contexts match */ if (newsbsec->flags & SE_SBINITIALIZED) { if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; return selinux_cmp_sb_context(oldsb, newsb); } mutex_lock(&newsbsec->lock); newsbsec->flags = oldsbsec->flags; newsbsec->sid = oldsbsec->sid; newsbsec->def_sid = oldsbsec->def_sid; newsbsec->behavior = oldsbsec->behavior; if (newsbsec->behavior == SECURITY_FS_USE_NATIVE && !(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) { rc = security_fs_use(&selinux_state, newsb); if (rc) goto out; } if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) { newsbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (set_context) { u32 sid = oldsbsec->mntpoint_sid; if (!set_fscontext) newsbsec->sid = sid; if (!set_rootcontext) { struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = sid; } newsbsec->mntpoint_sid = sid; } if (set_rootcontext) { const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root); struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = oldisec->sid; } sb_finish_set_opts(newsb); out: mutex_unlock(&newsbsec->lock); return rc; } static int selinux_add_opt(int token, const char *s, void **mnt_opts) { struct selinux_mnt_opts *opts = *mnt_opts; bool is_alloc_opts = false; if (token == Opt_seclabel) /* eaten and completely ignored */ return 0; if (!s) return -ENOMEM; if (!opts) { opts = kzalloc(sizeof(struct selinux_mnt_opts), GFP_KERNEL); if (!opts) return -ENOMEM; *mnt_opts = opts; is_alloc_opts = true; } switch (token) { case Opt_context: if (opts->context || opts->defcontext) goto Einval; opts->context = s; break; case Opt_fscontext: if (opts->fscontext) goto Einval; opts->fscontext = s; break; case Opt_rootcontext: if (opts->rootcontext) goto Einval; opts->rootcontext = s; break; case Opt_defcontext: if (opts->context || opts->defcontext) goto Einval; opts->defcontext = s; break; } return 0; Einval: if (is_alloc_opts) { kfree(opts); *mnt_opts = NULL; } pr_warn(SEL_MOUNT_FAIL_MSG); return -EINVAL; } static int selinux_add_mnt_opt(const char *option, const char *val, int len, void **mnt_opts) { int token = Opt_error; int rc, i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { if (strcmp(option, tokens[i].name) == 0) { token = tokens[i].opt; break; } } if (token == Opt_error) return -EINVAL; if (token != Opt_seclabel) { val = kmemdup_nul(val, len, GFP_KERNEL); if (!val) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, val, mnt_opts); if (unlikely(rc)) { kfree(val); goto free_opt; } return rc; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; u32 len; int rc; rc = security_sid_to_context(&selinux_state, sid, &context, &len); if (!rc) { bool has_comma = context && strchr(context, ','); seq_putc(m, '='); if (has_comma) seq_putc(m, '\"'); seq_escape(m, context, "\"\n\\"); if (has_comma) seq_putc(m, '\"'); } kfree(context); return rc; } static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!selinux_initialized(&selinux_state)) return 0; if (sbsec->flags & FSCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, FSCONTEXT_STR); rc = show_sid(m, sbsec->sid); if (rc) return rc; } if (sbsec->flags & CONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, CONTEXT_STR); rc = show_sid(m, sbsec->mntpoint_sid); if (rc) return rc; } if (sbsec->flags & DEFCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, DEFCONTEXT_STR); rc = show_sid(m, sbsec->def_sid); if (rc) return rc; } if (sbsec->flags & ROOTCONTEXT_MNT) { struct dentry *root = sbsec->sb->s_root; struct inode_security_struct *isec = backing_inode_security(root); seq_putc(m, ','); seq_puts(m, ROOTCONTEXT_STR); rc = show_sid(m, isec->sid); if (rc) return rc; } if (sbsec->flags & SBLABEL_MNT) { seq_putc(m, ','); seq_puts(m, SECLABEL_STR); } return 0; } static inline u16 inode_mode_to_security_class(umode_t mode) { switch (mode & S_IFMT) { case S_IFSOCK: return SECCLASS_SOCK_FILE; case S_IFLNK: return SECCLASS_LNK_FILE; case S_IFREG: return SECCLASS_FILE; case S_IFBLK: return SECCLASS_BLK_FILE; case S_IFDIR: return SECCLASS_DIR; case S_IFCHR: return SECCLASS_CHR_FILE; case S_IFIFO: return SECCLASS_FIFO_FILE; } return SECCLASS_FILE; } static inline int default_protocol_stream(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP); } static inline int default_protocol_dgram(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP); } static inline u16 socket_type_to_security_class(int family, int type, int protocol) { int extsockclass = selinux_policycap_extsockclass(); switch (family) { case PF_UNIX: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: return SECCLASS_UNIX_STREAM_SOCKET; case SOCK_DGRAM: case SOCK_RAW: return SECCLASS_UNIX_DGRAM_SOCKET; } break; case PF_INET: case PF_INET6: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: if (default_protocol_stream(protocol)) return SECCLASS_TCP_SOCKET; else if (extsockclass && protocol == IPPROTO_SCTP) return SECCLASS_SCTP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DGRAM: if (default_protocol_dgram(protocol)) return SECCLASS_UDP_SOCKET; else if (extsockclass && (protocol == IPPROTO_ICMP || protocol == IPPROTO_ICMPV6)) return SECCLASS_ICMP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DCCP: return SECCLASS_DCCP_SOCKET; default: return SECCLASS_RAWIP_SOCKET; } break; case PF_NETLINK: switch (protocol) { case NETLINK_ROUTE: return SECCLASS_NETLINK_ROUTE_SOCKET; case NETLINK_SOCK_DIAG: return SECCLASS_NETLINK_TCPDIAG_SOCKET; case NETLINK_NFLOG: return SECCLASS_NETLINK_NFLOG_SOCKET; case NETLINK_XFRM: return SECCLASS_NETLINK_XFRM_SOCKET; case NETLINK_SELINUX: return SECCLASS_NETLINK_SELINUX_SOCKET; case NETLINK_ISCSI: return SECCLASS_NETLINK_ISCSI_SOCKET; case NETLINK_AUDIT: return SECCLASS_NETLINK_AUDIT_SOCKET; case NETLINK_FIB_LOOKUP: return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET; case NETLINK_CONNECTOR: return SECCLASS_NETLINK_CONNECTOR_SOCKET; case NETLINK_NETFILTER: return SECCLASS_NETLINK_NETFILTER_SOCKET; case NETLINK_DNRTMSG: return SECCLASS_NETLINK_DNRT_SOCKET; case NETLINK_KOBJECT_UEVENT: return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET; case NETLINK_GENERIC: return SECCLASS_NETLINK_GENERIC_SOCKET; case NETLINK_SCSITRANSPORT: return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET; case NETLINK_RDMA: return SECCLASS_NETLINK_RDMA_SOCKET; case NETLINK_CRYPTO: return SECCLASS_NETLINK_CRYPTO_SOCKET; default: return SECCLASS_NETLINK_SOCKET; } case PF_PACKET: return SECCLASS_PACKET_SOCKET; case PF_KEY: return SECCLASS_KEY_SOCKET; case PF_APPLETALK: return SECCLASS_APPLETALK_SOCKET; } if (extsockclass) { switch (family) { case PF_AX25: return SECCLASS_AX25_SOCKET; case PF_IPX: return SECCLASS_IPX_SOCKET; case PF_NETROM: return SECCLASS_NETROM_SOCKET; case PF_ATMPVC: return SECCLASS_ATMPVC_SOCKET; case PF_X25: return SECCLASS_X25_SOCKET; case PF_ROSE: return SECCLASS_ROSE_SOCKET; case PF_DECnet: return SECCLASS_DECNET_SOCKET; case PF_ATMSVC: return SECCLASS_ATMSVC_SOCKET; case PF_RDS: return SECCLASS_RDS_SOCKET; case PF_IRDA: return SECCLASS_IRDA_SOCKET; case PF_PPPOX: return SECCLASS_PPPOX_SOCKET; case PF_LLC: return SECCLASS_LLC_SOCKET; case PF_CAN: return SECCLASS_CAN_SOCKET; case PF_TIPC: return SECCLASS_TIPC_SOCKET; case PF_BLUETOOTH: return SECCLASS_BLUETOOTH_SOCKET; case PF_IUCV: return SECCLASS_IUCV_SOCKET; case PF_RXRPC: return SECCLASS_RXRPC_SOCKET; case PF_ISDN: return SECCLASS_ISDN_SOCKET; case PF_PHONET: return SECCLASS_PHONET_SOCKET; case PF_IEEE802154: return SECCLASS_IEEE802154_SOCKET; case PF_CAIF: return SECCLASS_CAIF_SOCKET; case PF_ALG: return SECCLASS_ALG_SOCKET; case PF_NFC: return SECCLASS_NFC_SOCKET; case PF_VSOCK: return SECCLASS_VSOCK_SOCKET; case PF_KCM: return SECCLASS_KCM_SOCKET; case PF_QIPCRTR: return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; #if PF_MAX > 45 #error New address family defined, please update this function. #endif } } return SECCLASS_SOCKET; } static int selinux_genfs_get_sid(struct dentry *dentry, u16 tclass, u16 flags, u32 *sid) { int rc; struct super_block *sb = dentry->d_sb; char *buffer, *path; buffer = (char *)__get_free_page(GFP_KERNEL); if (!buffer) return -ENOMEM; path = dentry_path_raw(dentry, buffer, PAGE_SIZE); if (IS_ERR(path)) rc = PTR_ERR(path); else { if (flags & SE_SBPROC) { /* each process gets a /proc/PID/ entry. Strip off the * PID part to get a valid selinux labeling. * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */ while (path[1] >= '0' && path[1] <= '9') { path[1] = '/'; path++; } } rc = security_genfs_sid(&selinux_state, sb->s_type->name, path, tclass, sid); if (rc == -ENOENT) { /* No match in policy, mark as unlabeled. */ *sid = SECINITSID_UNLABELED; rc = 0; } } free_page((unsigned long)buffer); return rc; } static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry, u32 def_sid, u32 *sid) { #define INITCONTEXTLEN 255 char *context; unsigned int len; int rc; len = INITCONTEXTLEN; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { kfree(context); /* Need a larger buffer. Query for the right size. */ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0) return rc; len = rc; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); } if (rc < 0) { kfree(context); if (rc != -ENODATA) { pr_warn("SELinux: %s: getxattr returned %d for dev=%s ino=%ld\n", __func__, -rc, inode->i_sb->s_id, inode->i_ino); return rc; } *sid = def_sid; return 0; } rc = security_context_to_sid_default(&selinux_state, context, rc, sid, def_sid, GFP_NOFS); if (rc) { char *dev = inode->i_sb->s_id; unsigned long ino = inode->i_ino; if (rc == -EINVAL) { pr_notice_ratelimited("SELinux: inode=%lu on dev=%s was found to have an invalid context=%s. This indicates you may need to relabel the inode or the filesystem in question.\n", ino, dev, context); } else { pr_warn("SELinux: %s: context_to_sid(%s) returned %d for dev=%s ino=%ld\n", __func__, context, -rc, dev, ino); } } kfree(context); return 0; } /* The inode's security attributes must be initialized before first use. */ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry) { struct superblock_security_struct *sbsec = NULL; struct inode_security_struct *isec = selinux_inode(inode); u32 task_sid, sid = 0; u16 sclass; struct dentry *dentry; int rc = 0; if (isec->initialized == LABEL_INITIALIZED) return 0; spin_lock(&isec->lock); if (isec->initialized == LABEL_INITIALIZED) goto out_unlock; if (isec->sclass == SECCLASS_FILE) isec->sclass = inode_mode_to_security_class(inode->i_mode); sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SE_SBINITIALIZED)) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ spin_lock(&sbsec->isec_lock); if (list_empty(&isec->list)) list_add(&isec->list, &sbsec->isec_head); spin_unlock(&sbsec->isec_lock); goto out_unlock; } sclass = isec->sclass; task_sid = isec->task_sid; sid = isec->sid; isec->initialized = LABEL_PENDING; spin_unlock(&isec->lock); switch (sbsec->behavior) { case SECURITY_FS_USE_NATIVE: break; case SECURITY_FS_USE_XATTR: if (!(inode->i_opflags & IOP_XATTR)) { sid = sbsec->def_sid; break; } /* Need a dentry, since the xattr API requires one. Life would be simpler if we could just pass the inode. */ if (opt_dentry) { /* Called from d_instantiate or d_splice_alias. */ dentry = dget(opt_dentry); } else { /* * Called from selinux_complete_init, try to find a dentry. * Some filesystems really want a connected one, so try * that first. We could split SECURITY_FS_USE_XATTR in * two, depending upon that... */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } if (!dentry) { /* * this is can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as these * will get fixed up the next time we go through * inode_doinit with a dentry, before these inodes could * be used again by userspace. */ goto out_invalid; } rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid, &sid); dput(dentry); if (rc) goto out; break; case SECURITY_FS_USE_TASK: sid = task_sid; break; case SECURITY_FS_USE_TRANS: /* Default to the fs SID. */ sid = sbsec->sid; /* Try to obtain a transition SID. */ rc = security_transition_sid(&selinux_state, task_sid, sid, sclass, NULL, &sid); if (rc) goto out; break; case SECURITY_FS_USE_MNTPOINT: sid = sbsec->mntpoint_sid; break; default: /* Default to the fs superblock SID. */ sid = sbsec->sid; if ((sbsec->flags & SE_SBGENFS) && (!S_ISLNK(inode->i_mode) || selinux_policycap_genfs_seclabel_symlinks())) { /* We must have a dentry to determine the label on * procfs inodes */ if (opt_dentry) { /* Called from d_instantiate or * d_splice_alias. */ dentry = dget(opt_dentry); } else { /* Called from selinux_complete_init, try to * find a dentry. Some filesystems really want * a connected one, so try that first. */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } /* * This can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as * these will get fixed up the next time we go through * inode_doinit() with a dentry, before these inodes * could be used again by userspace. */ if (!dentry) goto out_invalid; rc = selinux_genfs_get_sid(dentry, sclass, sbsec->flags, &sid); if (rc) { dput(dentry); goto out; } if ((sbsec->flags & SE_SBGENFS_XATTR) && (inode->i_opflags & IOP_XATTR)) { rc = inode_doinit_use_xattr(inode, dentry, sid, &sid); if (rc) { dput(dentry); goto out; } } dput(dentry); } break; } out: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { if (rc) { isec->initialized = LABEL_INVALID; goto out_unlock; } isec->initialized = LABEL_INITIALIZED; isec->sid = sid; } out_unlock: spin_unlock(&isec->lock); return rc; out_invalid: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { isec->initialized = LABEL_INVALID; isec->sid = sid; } spin_unlock(&isec->lock); return 0; } /* Convert a Linux signal to an access vector. */ static inline u32 signal_to_av(int sig) { u32 perm = 0; switch (sig) { case SIGCHLD: /* Commonly granted from child to parent. */ perm = PROCESS__SIGCHLD; break; case SIGKILL: /* Cannot be caught or ignored */ perm = PROCESS__SIGKILL; break; case SIGSTOP: /* Cannot be caught or ignored */ perm = PROCESS__SIGSTOP; break; default: /* All other signals. */ perm = PROCESS__SIGNAL; break; } return perm; } #if CAP_LAST_CAP > 63 #error Fix SELinux to handle capabilities > 63. #endif /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; u16 sclass; u32 sid = cred_sid(cred); u32 av = CAP_TO_MASK(cap); int rc; ad.type = LSM_AUDIT_DATA_CAP; ad.u.cap = cap; switch (CAP_TO_INDEX(cap)) { case 0: sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS; break; case 1: sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS; break; default: pr_err("SELinux: out of range capability %d\n", cap); BUG(); return -EINVAL; } rc = avc_has_perm_noaudit(&selinux_state, sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(&selinux_state, sid, sid, sclass, av, &avd, rc, &ad, 0); if (rc2) return rc2; } return rc; } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; validate_creds(cred); if (unlikely(IS_PRIVATE(inode))) return 0; sid = cred_sid(cred); isec = selinux_inode(inode); return avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ static inline int dentry_has_perm(const struct cred *cred, struct dentry *dentry, u32 av) { struct inode *inode = d_backing_inode(dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; __inode_security_revalidate(inode, dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, const struct path *path, u32 av) { struct inode *inode = d_backing_inode(path->dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; __inode_security_revalidate(inode, path->dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ static inline int file_path_has_perm(const struct cred *cred, struct file *file, u32 av) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return inode_has_perm(cred, file_inode(file), av, &ad); } #ifdef CONFIG_BPF_SYSCALL static int bpf_fd_pass(struct file *file, u32 sid); #endif /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to check a particular permission to the file. Access to the descriptor is implicitly granted if it has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ static int file_has_perm(const struct cred *cred, struct file *file, u32 av) { struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct common_audit_data ad; u32 sid = cred_sid(cred); int rc; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; if (sid != fsec->sid) { rc = avc_has_perm(&selinux_state, sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, cred_sid(cred)); if (rc) return rc; #endif /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) rc = inode_has_perm(cred, inode, av, &ad); out: return rc; } /* * Determine the label for an inode that might be unioned. */ static int selinux_determine_inode_label(const struct task_security_struct *tsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) { const struct superblock_security_struct *sbsec = dir->i_sb->s_security; if ((sbsec->flags & SE_SBINITIALIZED) && (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && tsec->create_sid) { *_new_isid = tsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); return security_transition_sid(&selinux_state, tsec->sid, dsec->sid, tclass, name, _new_isid); } return 0; } /* Check whether a task can create a file. */ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; struct common_audit_data ad; int rc; dsec = inode_security(dir); sbsec = dir->i_sb->s_security; sid = tsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; rc = avc_has_perm(&selinux_state, sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; return avc_has_perm(&selinux_state, newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } #define MAY_LINK 0 #define MAY_UNLINK 1 #define MAY_RMDIR 2 /* Check whether a task can link, unlink, or rmdir a file/directory. */ static int may_link(struct inode *dir, struct dentry *dentry, int kind) { struct inode_security_struct *dsec, *isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int rc; dsec = inode_security(dir); isec = backing_inode_security(dentry); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); rc = avc_has_perm(&selinux_state, sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; switch (kind) { case MAY_LINK: av = FILE__LINK; break; case MAY_UNLINK: av = FILE__UNLINK; break; case MAY_RMDIR: av = DIR__RMDIR; break; default: pr_warn("SELinux: %s: unrecognized kind %d\n", __func__, kind); return 0; } rc = avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, av, &ad); return rc; } static inline int may_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; old_dsec = inode_security(old_dir); old_isec = backing_inode_security(old_dentry); old_is_dir = d_is_dir(old_dentry); new_dsec = inode_security(new_dir); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = old_dentry; rc = avc_has_perm(&selinux_state, sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { rc = avc_has_perm(&selinux_state, sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; } ad.u.dentry = new_dentry; av = DIR__ADD_NAME | DIR__SEARCH; if (d_is_positive(new_dentry)) av |= DIR__REMOVE_NAME; rc = avc_has_perm(&selinux_state, sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (d_is_positive(new_dentry)) { new_isec = backing_inode_security(new_dentry); new_is_dir = d_is_dir(new_dentry); rc = avc_has_perm(&selinux_state, sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) return rc; } return 0; } /* Check whether a task can perform a filesystem operation. */ static int superblock_has_perm(const struct cred *cred, struct super_block *sb, u32 perms, struct common_audit_data *ad) { struct superblock_security_struct *sbsec; u32 sid = cred_sid(cred); sbsec = sb->s_security; return avc_has_perm(&selinux_state, sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ static inline u32 file_mask_to_av(int mode, int mask) { u32 av = 0; if (!S_ISDIR(mode)) { if (mask & MAY_EXEC) av |= FILE__EXECUTE; if (mask & MAY_READ) av |= FILE__READ; if (mask & MAY_APPEND) av |= FILE__APPEND; else if (mask & MAY_WRITE) av |= FILE__WRITE; } else { if (mask & MAY_EXEC) av |= DIR__SEARCH; if (mask & MAY_WRITE) av |= DIR__WRITE; if (mask & MAY_READ) av |= DIR__READ; } return av; } /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(struct file *file) { u32 av = 0; if (file->f_mode & FMODE_READ) av |= FILE__READ; if (file->f_mode & FMODE_WRITE) { if (file->f_flags & O_APPEND) av |= FILE__APPEND; else av |= FILE__WRITE; } if (!av) { /* * Special file opened with flags 3 for ioctl-only use. */ av = FILE__IOCTL; } return av; } /* * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) { u32 av = file_to_av(file); struct inode *inode = file_inode(file); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC) av |= FILE__OPEN; return av; } /* Hook functions begin here. */ static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(&selinux_state, current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } static int selinux_binder_transaction(const struct cred *from, const struct cred *to) { u32 mysid = current_sid(); u32 fromsid = cred_sid(from); u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { rc = avc_has_perm(&selinux_state, mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL); if (rc) return rc; } return avc_has_perm(&selinux_state, fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } static int selinux_binder_transfer_binder(const struct cred *from, const struct cred *to) { return avc_has_perm(&selinux_state, cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } static int selinux_binder_transfer_file(const struct cred *from, const struct cred *to, struct file *file) { u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; struct common_audit_data ad; int rc; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; if (sid != fsec->sid) { rc = avc_has_perm(&selinux_state, sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, sid); if (rc) return rc; #endif if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; isec = backing_inode_security(dentry); return avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, file_to_av(file), &ad); } static int selinux_ptrace_access_check(struct task_struct *child, unsigned int mode) { u32 sid = current_sid(); u32 csid = task_sid(child); if (mode & PTRACE_MODE_READ) return avc_has_perm(&selinux_state, sid, csid, SECCLASS_FILE, FILE__READ, NULL); return avc_has_perm(&selinux_state, sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(&selinux_state, task_sid(parent), current_sid(), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return avc_has_perm(&selinux_state, current_sid(), task_sid(target), SECCLASS_PROCESS, PROCESS__GETCAP, NULL); } static int selinux_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return avc_has_perm(&selinux_state, cred_sid(old), cred_sid(new), SECCLASS_PROCESS, PROCESS__SETCAP, NULL); } /* * (This comment used to live with the selinux_task_setuid hook, * which was removed). * * Since setuid only affects the current process, and since the SELinux * controls are not based on the Linux identity attributes, SELinux does not * need to control this operation. However, SELinux does control the use of * the CAP_SETUID and CAP_SETGID capabilities using the capable hook. */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb) { const struct cred *cred = current_cred(); int rc = 0; if (!sb) return 0; switch (cmds) { case Q_SYNC: case Q_QUOTAON: case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: case Q_XQUOTAOFF: case Q_XQUOTAON: case Q_XSETQLIM: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: case Q_XGETQUOTA: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETNEXTQUOTA: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ break; } return rc; } static int selinux_quota_on(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) { switch (type) { case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL); case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, NULL); } /* All other syslog types */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL); } /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { int rc, cap_sys_admin = 0; rc = cred_has_capability(current_cred(), CAP_SYS_ADMIN, CAP_OPT_NOAUDIT, true); if (rc == 0) cap_sys_admin = 1; return cap_sys_admin; } /* binprm security operations */ static u32 ptrace_parent_sid(void) { u32 sid = 0; struct task_struct *tracer; rcu_read_lock(); tracer = ptrace_parent(current); if (tracer) sid = task_sid(tracer); rcu_read_unlock(); return sid; } static int check_nnp_nosuid(const struct linux_binprm *bprm, const struct task_security_struct *old_tsec, const struct task_security_struct *new_tsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); int rc; u32 av; if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ if (new_tsec->sid == old_tsec->sid) return 0; /* No change in credentials */ /* * If the policy enables the nnp_nosuid_transition policy capability, * then we permit transitions under NNP or nosuid if the * policy allows the corresponding permission between * the old and new contexts. */ if (selinux_policycap_nnp_nosuid_transition()) { av = 0; if (nnp) av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; } /* * We also permit NNP or nosuid transitions to bounded SIDs, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ rc = security_bounded_transition(&selinux_state, old_tsec->sid, new_tsec->sid); if (!rc) return 0; /* * On failure, preserve the errno values for NNP vs nosuid. * NNP: Operation not permitted for caller. * nosuid: Permission denied to file. */ if (nnp) return -EPERM; return -EACCES; } static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { const struct task_security_struct *old_tsec; struct task_security_struct *new_tsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); int rc; /* SELinux context only depends on initial program or script and not * the script interpreter */ old_tsec = selinux_cred(current_cred()); new_tsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ new_tsec->sid = old_tsec->sid; new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ new_tsec->create_sid = 0; new_tsec->keycreate_sid = 0; new_tsec->sockcreate_sid = 0; if (old_tsec->exec_sid) { new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ new_tsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ rc = security_transition_sid(&selinux_state, old_tsec->sid, isec->sid, SECCLASS_PROCESS, NULL, &new_tsec->sid); if (rc) return rc; /* * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) new_tsec->sid = old_tsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; if (new_tsec->sid == old_tsec->sid) { rc = avc_has_perm(&selinux_state, old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; rc = avc_has_perm(&selinux_state, new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) return -EPERM; } /* Make sure that anyone attempting to ptrace over a task that * changes its SID has the appropriate permit */ if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { rc = avc_has_perm(&selinux_state, ptsid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) return -EPERM; } } /* Clear any possibly unsafe personality bits on exec: */ bprm->per_clear |= PER_CLEAR_ON_SETID; /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; } return 0; } static int match_file(const void *p, struct file *file, unsigned fd) { return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0; } /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) { struct file *file, *devnull = NULL; struct tty_struct *tty; int drop_tty = 0; unsigned n; tty = get_current_tty(); if (tty) { spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; /* Revalidate access to controlling tty. Use file_path_has_perm on the tty path directly rather than using file_has_perm, as this particular open file may belong to another process and we are only interested in the inode-based check here. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); } /* Reset controlling tty. */ if (drop_tty) no_tty(); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, cred); if (!n) /* none found? */ return; devnull = dentry_open(&selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); if (devnull) fput(devnull); } /* * Prepare a process for imminent new credential changes due to exec */ static void selinux_bprm_committing_creds(struct linux_binprm *bprm) { struct task_security_struct *new_tsec; struct rlimit *rlim, *initrlim; int rc, i; new_tsec = selinux_cred(bprm->cred); if (new_tsec->sid == new_tsec->osid) return; /* Close files for which the new task SID is not authorized. */ flush_unauthorized_files(bprm->cred, current->files); /* Always clear parent death signal on SID transitions. */ current->pdeath_signal = 0; /* Check whether the new SID can inherit resource limits from the old * SID. If not, reset all soft limits to the lower of the current * task's hard limit and the init task's soft limit. * * Note that the setting of hard limits (even to lower them) can be * controlled by the setrlimit check. The inclusion of the init task's * soft limit into the computation is to avoid resetting soft limits * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ rc = avc_has_perm(&selinux_state, new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ task_lock(current); for (i = 0; i < RLIM_NLIMITS; i++) { rlim = current->signal->rlim + i; initrlim = init_task.signal->rlim + i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } task_unlock(current); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(current, rlimit(RLIMIT_CPU)); } } /* * Clean up the process immediately after the installation of new credentials * due to exec */ static void selinux_bprm_committed_creds(struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 osid, sid; int rc; osid = tsec->osid; sid = tsec->sid; if (sid == osid) return; /* Check whether the new SID can inherit signal state from the old SID. * If not, clear itimers to avoid subsequent signal generation and * flush and unblock signals. * * This must occur _after_ the task SID has been updated so that any * kill done after the flush will be checked against the new SID. */ rc = avc_has_perm(&selinux_state, osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { clear_itimer(); spin_lock_irq(¤t->sighand->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); flush_sigqueue(¤t->signal->shared_pending); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); } spin_unlock_irq(¤t->sighand->siglock); } /* Wake up the parent if it is waiting so that it can recheck * wait permission to the new task SID. */ read_lock(&tasklist_lock); __wake_up_parent(current, current->real_parent); read_unlock(&tasklist_lock); } /* superblock security operations */ static int selinux_sb_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec; sbsec = kzalloc(sizeof(struct superblock_security_struct), GFP_KERNEL); if (!sbsec) return -ENOMEM; mutex_init(&sbsec->lock); INIT_LIST_HEAD(&sbsec->isec_head); spin_lock_init(&sbsec->isec_lock); sbsec->sb = sb; sbsec->sid = SECINITSID_UNLABELED; sbsec->def_sid = SECINITSID_FILE; sbsec->mntpoint_sid = SECINITSID_UNLABELED; sb->s_security = sbsec; return 0; } static void selinux_sb_free_security(struct super_block *sb) { superblock_free_security(sb); } static inline int opt_len(const char *s) { bool open_quote = false; int len; char c; for (len = 0; (c = s[len]) != '\0'; len++) { if (c == '"') open_quote = !open_quote; if (c == ',' && !open_quote) break; } return len; } static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) { char *from = options; char *to = options; bool first = true; int rc; while (1) { int len = opt_len(from); int token; char *arg = NULL; token = match_opt_prefix(from, len, &arg); if (token != Opt_error) { char *p, *q; /* strip quotes */ if (arg) { for (p = q = arg; p < from + len; p++) { char c = *p; if (c != '"') *q++ = c; } arg = kmemdup_nul(arg, q - arg, GFP_KERNEL); if (!arg) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, arg, mnt_opts); if (unlikely(rc)) { kfree(arg); goto free_opt; } } else { if (!first) { // copy with preceding comma from--; len++; } if (to != from) memmove(to, from, len); to += len; first = false; } if (!from[len]) break; from += len + 1; } *to = '\0'; return 0; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = sb->s_security; u32 sid; int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!opts) return 0; if (opts->fscontext) { rc = parse_sid(sb, opts->fscontext, &sid); if (rc) return rc; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid)) goto out_bad_option; } if (opts->context) { rc = parse_sid(sb, opts->context, &sid); if (rc) return rc; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid)) goto out_bad_option; } if (opts->rootcontext) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); rc = parse_sid(sb, opts->rootcontext, &sid); if (rc) return rc; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid)) goto out_bad_option; } if (opts->defcontext) { rc = parse_sid(sb, opts->defcontext, &sid); if (rc) return rc; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid)) goto out_bad_option; } return 0; out_bad_option: pr_warn("SELinux: unable to change security options " "during remount (dev %s, type=%s)\n", sb->s_id, sb->s_type->name); return -EINVAL; } static int selinux_sb_kern_mount(struct super_block *sb) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = sb->s_root; return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry->d_sb->s_root; return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { const struct cred *cred = current_cred(); if (flags & MS_REMOUNT) return superblock_has_perm(cred, path->dentry->d_sb, FILESYSTEM__REMOUNT, NULL); else return path_has_perm(cred, path, FILE__MOUNTON); } static int selinux_move_mount(const struct path *from_path, const struct path *to_path) { const struct cred *cred = current_cred(); return path_has_perm(cred, to_path, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { const struct cred *cred = current_cred(); return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { const struct selinux_mnt_opts *src = src_fc->security; struct selinux_mnt_opts *opts; if (!src) return 0; fc->security = kzalloc(sizeof(struct selinux_mnt_opts), GFP_KERNEL); if (!fc->security) return -ENOMEM; opts = fc->security; if (src->fscontext) { opts->fscontext = kstrdup(src->fscontext, GFP_KERNEL); if (!opts->fscontext) return -ENOMEM; } if (src->context) { opts->context = kstrdup(src->context, GFP_KERNEL); if (!opts->context) return -ENOMEM; } if (src->rootcontext) { opts->rootcontext = kstrdup(src->rootcontext, GFP_KERNEL); if (!opts->rootcontext) return -ENOMEM; } if (src->defcontext) { opts->defcontext = kstrdup(src->defcontext, GFP_KERNEL); if (!opts->defcontext) return -ENOMEM; } return 0; } static const struct fs_parameter_spec selinux_fs_parameters[] = { fsparam_string(CONTEXT_STR, Opt_context), fsparam_string(DEFCONTEXT_STR, Opt_defcontext), fsparam_string(FSCONTEXT_STR, Opt_fscontext), fsparam_string(ROOTCONTEXT_STR, Opt_rootcontext), fsparam_flag (SECLABEL_STR, Opt_seclabel), {} }; static int selinux_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; int opt, rc; opt = fs_parse(fc, selinux_fs_parameters, param, &result); if (opt < 0) return opt; rc = selinux_add_opt(opt, param->string, &fc->security); if (!rc) param->string = NULL; return rc; } /* inode security operations */ static int selinux_inode_alloc_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; return 0; } static void selinux_inode_free_security(struct inode *inode) { inode_free_security(inode); } static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, u32 *ctxlen) { u32 newsid; int rc; rc = selinux_determine_inode_label(selinux_cred(current_cred()), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; return security_sid_to_context(&selinux_state, newsid, (char **)ctx, ctxlen); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { u32 newsid; int rc; struct task_security_struct *tsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; tsec = selinux_cred(new); tsec->create_sid = newsid; return 0; } static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; u32 newsid, clen; int rc; char *context; sbsec = dir->i_sb->s_security; newsid = tsec->create_sid; rc = selinux_determine_inode_label(tsec, dir, qstr, inode_mode_to_security_class(inode->i_mode), &newsid); if (rc) return rc; /* Possibly defer initialization to selinux_complete_init. */ if (sbsec->flags & SE_SBINITIALIZED) { struct inode_security_struct *isec = selinux_inode(inode); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; } if (!selinux_initialized(&selinux_state) || !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (name) *name = XATTR_SELINUX_SUFFIX; if (value && len) { rc = security_sid_to_context_force(&selinux_state, newsid, &context, &clen); if (rc) return rc; *value = context; *len = clen; } return 0; } static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { return may_create(dir, dentry, SECCLASS_FILE); } static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { return may_link(dir, old_dentry, MAY_LINK); } static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_UNLINK); } static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name) { return may_create(dir, dentry, SECCLASS_LNK_FILE); } static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask) { return may_create(dir, dentry, SECCLASS_DIR); } static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_RMDIR); } static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return may_create(dir, dentry, inode_mode_to_security_class(mode)); } static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry, struct inode *new_inode, struct dentry *new_dentry) { return may_rename(old_inode, old_dentry, new_inode, new_dentry); } static int selinux_inode_readlink(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { const struct cred *cred = current_cred(); struct common_audit_data ad; struct inode_security_struct *isec; u32 sid; validate_creds(cred); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; sid = cred_sid(cred); isec = inode_security_rcu(inode, rcu); if (IS_ERR(isec)) return PTR_ERR(isec); return avc_has_perm_flags(&selinux_state, sid, isec->sid, isec->sclass, FILE__READ, &ad, rcu ? MAY_NOT_BLOCK : 0); } static noinline int audit_inode_permission(struct inode *inode, u32 perms, u32 audited, u32 denied, int result) { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); int rc; ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; rc = slow_avc_audit(&selinux_state, current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); if (rc) return rc; return 0; } static int selinux_inode_permission(struct inode *inode, int mask) { const struct cred *cred = current_cred(); u32 perms; bool from_access; bool no_block = mask & MAY_NOT_BLOCK; struct inode_security_struct *isec; u32 sid; struct av_decision avd; int rc, rc2; u32 audited, denied; from_access = mask & MAY_ACCESS; mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND); /* No permission to check. Existence test. */ if (!mask) return 0; validate_creds(cred); if (unlikely(IS_PRIVATE(inode))) return 0; perms = file_mask_to_av(inode->i_mode, mask); sid = cred_sid(cred); isec = inode_security_rcu(inode, no_block); if (IS_ERR(isec)) return PTR_ERR(isec); rc = avc_has_perm_noaudit(&selinux_state, sid, isec->sid, isec->sclass, perms, no_block ? AVC_NONBLOCKING : 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; /* fall back to ref-walk if we have to generate audit */ if (no_block) return -ECHILD; rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; return rc; } static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) { const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; __u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE | ATTR_FORCE); if (!ia_valid) return 0; } if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC && (ia_valid & ATTR_SIZE) && !(ia_valid & ATTR_FILE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); } static int selinux_inode_getattr(const struct path *path) { return path_has_perm(current_cred(), path, FILE__GETATTR); } static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } static int selinux_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; struct superblock_security_struct *sbsec; struct common_audit_data ad; u32 newsid, sid = current_sid(); int rc = 0; if (strcmp(name, XATTR_NAME_SELINUX)) { rc = cap_inode_setxattr(dentry, name, value, size, flags); if (rc) return rc; /* Not an attribute we recognize, so just check the ordinary setattr permission. */ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } if (!selinux_initialized(&selinux_state)) return (inode_owner_or_capable(inode) ? 0 : -EPERM); sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!inode_owner_or_capable(inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = backing_inode_security(dentry); rc = avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; rc = security_context_to_sid(&selinux_state, value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (value) { const char *str = value; if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; } else { audit_size = 0; } ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=setxattr invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return rc; } rc = security_context_to_sid_force(&selinux_state, value, size, &newsid); } if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; rc = security_validate_transition(&selinux_state, isec->sid, newsid, sid, isec->sclass); if (rc) return rc; return avc_has_perm(&selinux_state, newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; u32 newsid; int rc; if (strcmp(name, XATTR_NAME_SELINUX)) { /* Not an attribute we recognize, so nothing to do. */ return; } if (!selinux_initialized(&selinux_state)) { /* If we haven't even been initialized, then we can't validate * against a policy, so leave the label as invalid. It may * resolve to a valid label on the next revalidation try if * we've since initialized. */ return; } rc = security_context_to_sid_force(&selinux_state, value, size, &newsid); if (rc) { pr_err("SELinux: unable to map context to SID" "for (%s, %lu), rc=%d\n", inode->i_sb->s_id, inode->i_ino, -rc); return; } isec = backing_inode_security(dentry); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return; } static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct dentry *dentry, const char *name) { if (strcmp(name, XATTR_NAME_SELINUX)) { int rc = cap_inode_removexattr(dentry, name); if (rc) return rc; /* Not an attribute we recognize, so just check the ordinary setattr permission. */ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } if (!selinux_initialized(&selinux_state)) return 0; /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; } static int selinux_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { int ret; u32 perm; struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; /* * Set permission needed based on the type of mark being set. * Performs an additional check for sb watches. */ switch (obj_type) { case FSNOTIFY_OBJ_TYPE_VFSMOUNT: perm = FILE__WATCH_MOUNT; break; case FSNOTIFY_OBJ_TYPE_SB: perm = FILE__WATCH_SB; ret = superblock_has_perm(current_cred(), path->dentry->d_sb, FILESYSTEM__WATCH, &ad); if (ret) return ret; break; case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; default: return -EINVAL; } /* blocking watches require the file:watch_with_perm permission */ if (mask & (ALL_FSNOTIFY_PERM_EVENTS)) perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); } /* * Copy the inode security context value to the user. * * Permission check is handled by selinux_inode_getxattr hook. */ static int selinux_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { u32 size; int error; char *context = NULL; struct inode_security_struct *isec; /* * If we're not initialized yet, then we can't validate contexts, so * just let vfs_getxattr fall back to using the on-disk xattr. */ if (!selinux_initialized(&selinux_state) || strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; /* * If the caller has CAP_MAC_ADMIN, then get the raw context * value even if it is not defined by current policy; otherwise, * use the in-core value under current policy. * Use the non-auditing forms of the permission checks since * getxattr may be called by unprivileged processes commonly * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ isec = inode_security(inode); if (has_cap_mac_admin(false)) error = security_sid_to_context_force(&selinux_state, isec->sid, &context, &size); else error = security_sid_to_context(&selinux_state, isec->sid, &context, &size); if (error) return error; error = size; if (alloc) { *buffer = context; goto out_nofree; } kfree(context); out_nofree: return error; } static int selinux_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct inode_security_struct *isec = inode_security_novalidate(inode); struct superblock_security_struct *sbsec = inode->i_sb->s_security; u32 newsid; int rc; if (strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!value || !size) return -EACCES; rc = security_context_to_sid(&selinux_state, value, size, &newsid, GFP_KERNEL); if (rc) return rc; spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return 0; } static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { const int len = sizeof(XATTR_NAME_SELINUX); if (!selinux_initialized(&selinux_state)) return 0; if (buffer && len <= buffer_size) memcpy(buffer, XATTR_NAME_SELINUX, len); return len; } static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { u32 sid; struct task_security_struct *tsec; struct cred *new_creds = *new; if (new_creds == NULL) { new_creds = prepare_creds(); if (!new_creds) return -ENOMEM; } tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getsecid(d_inode(src), &sid); tsec->create_sid = sid; *new = new_creds; return 0; } static int selinux_inode_copy_up_xattr(const char *name) { /* The copy_up hook above sets the initial context on an inode, but we * don't then want to overwrite it by blindly copying all the lower * xattrs up. Instead, we have to filter out SELinux-related xattrs. */ if (strcmp(name, XATTR_NAME_SELINUX) == 0) return 1; /* Discard */ /* * Any other attribute apart from SELINUX is not claimed, supported * by selinux. */ return -EOPNOTSUPP; } /* kernfs node operations */ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0); if (rc == -ENODATA) return 0; else if (rc < 0) return rc; clen = (u32)rc; context = kmalloc(clen, GFP_KERNEL); if (!context) return -ENOMEM; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen); if (rc < 0) { kfree(context); return rc; } rc = security_context_to_sid(&selinux_state, context, clen, &parent_sid, GFP_KERNEL); kfree(context); if (rc) return rc; if (tsec->create_sid) { newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); struct qstr q; q.name = kn->name; q.hash_len = hashlen_string(kn_dir, kn->name); rc = security_transition_sid(&selinux_state, tsec->sid, parent_sid, secclass, &q, &newsid); if (rc) return rc; } rc = security_sid_to_context_force(&selinux_state, newsid, &context, &clen); if (rc) return rc; rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen, XATTR_CREATE); kfree(context); return rc; } /* file security operations */ static int selinux_revalidate_file_permission(struct file *file, int mask) { const struct cred *cred = current_cred(); struct inode *inode = file_inode(file); /* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */ if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; return file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); } static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file_inode(file); struct file_security_struct *fsec = selinux_file(file); struct inode_security_struct *isec; u32 sid = current_sid(); if (!mask) /* No permission to check. Existence test. */ return 0; isec = inode_security(inode); if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno(&selinux_state)) /* No change since file_open check. */ return 0; return selinux_revalidate_file_permission(file, mask); } static int selinux_file_alloc_security(struct file *file) { struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); fsec->sid = sid; fsec->fown_sid = sid; return 0; } /* * Check whether a task has the ioctl permission and cmd * operation to an inode. */ static int ioctl_has_perm(const struct cred *cred, struct file *file, u32 requested, u16 cmd) { struct common_audit_data ad; struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct inode_security_struct *isec; struct lsm_ioctlop_audit ioctl; u32 ssid = cred_sid(cred); int rc; u8 driver = cmd >> 8; u8 xperm = cmd & 0xff; ad.type = LSM_AUDIT_DATA_IOCTL_OP; ad.u.op = &ioctl; ad.u.op->cmd = cmd; ad.u.op->path = file->f_path; if (ssid != fsec->sid) { rc = avc_has_perm(&selinux_state, ssid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } if (unlikely(IS_PRIVATE(inode))) return 0; isec = inode_security(inode); rc = avc_has_extended_perms(&selinux_state, ssid, isec->sid, isec->sclass, requested, driver, xperm, &ad); out: return rc; } static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int error = 0; switch (cmd) { case FIONREAD: case FIBMAP: case FIGETBSZ: case FS_IOC_GETFLAGS: case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: case FIOASYNC: error = file_has_perm(cred, file, 0); break; case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, CAP_OPT_NONE, true); break; case FIOCLEX: case FIONCLEX: if (!selinux_policycap_ioctl_skip_cloexec()) error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); break; /* default case assumes that the command will go * to the file's ioctl() function. */ default: error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); } return error; } static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { /* * If we are in a 64-bit kernel running 32-bit userspace, we need to * make sure we don't compare 32-bit flags to 64-bit flags. */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; break; case FS_IOC32_SETFLAGS: cmd = FS_IOC_SETFLAGS; break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case FS_IOC32_SETVERSION: cmd = FS_IOC_SETVERSION; break; default: break; } return selinux_file_ioctl(file, cmd, arg); } static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); int rc = 0; if (default_noexec && (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) || (!shared && (prot & PROT_WRITE)))) { /* * We are making executable an anonymous mapping or a * private file mapping that will also be writable. * This has an additional check. */ rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM, NULL); if (rc) goto error; } if (file) { /* read access is always possible with a mapping */ u32 av = FILE__READ; /* write access only matters if the mapping is shared */ if (shared && (prot & PROT_WRITE)) av |= FILE__WRITE; if (prot & PROT_EXEC) av |= FILE__EXECUTE; return file_has_perm(cred, file, av); } error: return rc; } static int selinux_mmap_addr(unsigned long addr) { int rc = 0; if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { u32 sid = current_sid(); rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); } return rc; } static int selinux_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { struct common_audit_data ad; int rc; if (file) { ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; rc = inode_has_perm(current_cred(), file_inode(file), FILE__MAP, &ad); if (rc) return rc; } if (checkreqprot_get(&selinux_state)) prot = reqprot; return file_map_prot_check(file, prot, (flags & MAP_TYPE) == MAP_SHARED); } static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); if (checkreqprot_get(&selinux_state)) prot = reqprot; if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; if (vma->vm_start >= vma->vm_mm->start_brk && vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && ((vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack) || vma_is_stack_for_current(vma))) { rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECSTACK, NULL); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has * had some COW done. Since pages might have been * written, check ability to execute the possibly * modified content. This typically should only * occur for text relocations. */ rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; } return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED); } static int selinux_file_lock(struct file *file, unsigned int cmd) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int err = 0; switch (cmd) { case F_SETFL: if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { err = file_has_perm(cred, file, FILE__WRITE); break; } fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: case F_GETOWN: case F_GETSIG: case F_GETOWNER_UIDS: /* Just check FD__USE permission */ err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: case F_SETLKW: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: case F_SETLKW64: #endif err = file_has_perm(cred, file, FILE__LOCK); break; } return err; } static void selinux_file_set_fowner(struct file *file) { struct file_security_struct *fsec; fsec = selinux_file(file); fsec->fown_sid = current_sid(); } static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; u32 sid = task_sid(tsk); u32 perm; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = container_of(fown, struct file, f_owner); fsec = selinux_file(file); if (!signum) perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */ else perm = signal_to_av(signum); return avc_has_perm(&selinux_state, fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, file_to_av(file)); } static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; fsec = selinux_file(file); isec = inode_security(file_inode(file)); /* * Save inode label and policy sequence number * at open-time so that selinux_file_permission * can determine whether revalidation is necessary. * Task label is already saved in the file security * struct as its SID. */ fsec->isid = isec->sid; fsec->pseqno = avc_policy_seqno(&selinux_state); /* * Since the inode label or policy seqno may have changed * between the selinux_inode_permission check and the saving * of state above, recheck that access is still permitted. * Otherwise, access might never be revalidated against the * new inode label or new policy. * This check is not redundant - do not remove. */ return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ static int selinux_task_alloc(struct task_struct *task, unsigned long clone_flags) { u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; return 0; } /* * transfer the SELinux data to a blank set of creds */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) { *secid = cred_sid(c); } /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(&selinux_state, sid, secid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { tsec->sid = secid; tsec->create_sid = 0; tsec->keycreate_sid = 0; tsec->sockcreate_sid = 0; } return ret; } /* * set the file creation context in a security record to the same as the * objective context of the specified inode */ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, NULL); if (ret == 0) tsec->create_sid = isec->sid; return ret; } static int selinux_kernel_module_request(char *kmod_name) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_KMOD; ad.u.kmod_name = kmod_name; return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, &ad); } static int selinux_kernel_module_from_file(struct file *file) { struct common_audit_data ad; struct inode_security_struct *isec; struct file_security_struct *fsec; u32 sid = current_sid(); int rc; /* init_module */ if (file == NULL) return avc_has_perm(&selinux_state, sid, sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, NULL); /* finit_module */ ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; fsec = selinux_file(file); if (sid != fsec->sid) { rc = avc_has_perm(&selinux_state, sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } isec = inode_security(file_inode(file)); return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, &ad); } static int selinux_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int rc = 0; switch (id) { case READING_MODULE: rc = selinux_kernel_module_from_file(contents ? file : NULL); break; default: break; } return rc; } static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents) { int rc = 0; switch (id) { case LOADING_MODULE: rc = selinux_kernel_module_from_file(NULL); default: break; } return rc; } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETPGID, NULL); } static int selinux_task_getpgid(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETPGID, NULL); } static int selinux_task_getsid(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETSESSION, NULL); } static void selinux_task_getsecid(struct task_struct *p, u32 *secid) { *secid = task_sid(p); } static int selinux_task_setnice(struct task_struct *p, int nice) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getioprio(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { u32 av = 0; if (!flags) return 0; if (flags & LSM_PRLIMIT_WRITE) av |= PROCESS__SETRLIMIT; if (flags & LSM_PRLIMIT_READ) av |= PROCESS__GETRLIMIT; return avc_has_perm(&selinux_state, cred_sid(cred), cred_sid(tcred), SECCLASS_PROCESS, av, NULL); } static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { struct rlimit *old_rlim = p->signal->rlim + resource; /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL); return 0; } static int selinux_task_setscheduler(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getscheduler(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_movememory(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; u32 perm; if (!sig) perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); if (!cred) secid = current_sid(); else secid = cred_sid(cred); return avc_has_perm(&selinux_state, secid, task_sid(p), SECCLASS_PROCESS, perm, NULL); } static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = task_sid(p); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = sid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ihlen, ret = -EINVAL; struct iphdr _iph, *ih; offset = skb_network_offset(skb); ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) goto out; ihlen = ih->ihl * 4; if (ihlen < sizeof(_iph)) goto out; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; ret = 0; if (proto) *proto = ih->protocol; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif default: break; } out: return ret; } #if IS_ENABLED(CONFIG_IPV6) /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv6(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { u8 nexthdr; int ret = -EINVAL, offset; struct ipv6hdr _ipv6h, *ip6; __be16 frag_off; offset = skb_network_offset(skb); ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (ip6 == NULL) goto out; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; ret = 0; nexthdr = ip6->nexthdr; offset += sizeof(_ipv6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) goto out; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif /* includes fragments */ default: break; } out: return ret; } #endif /* IPV6 */ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad, char **_addrp, int src, u8 *proto) { char *addrp; int ret; switch (ad->u.net->family) { case PF_INET: ret = selinux_parse_skb_ipv4(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v4info.saddr : &ad->u.net->v4info.daddr); goto okay; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: ret = selinux_parse_skb_ipv6(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v6info.saddr : &ad->u.net->v6info.daddr); goto okay; #endif /* IPV6 */ default: addrp = NULL; goto okay; } parse_error: pr_warn( "SELinux: failure in selinux_parse_skb()," " unable to parse packet\n"); return ret; okay: if (_addrp) *_addrp = addrp; return 0; } /** * selinux_skb_peerlbl_sid - Determine the peer label of a packet * @skb: the packet * @family: protocol family * @sid: the packet's peer label SID * * Description: * Check the various different forms of network peer labeling and determine * the peer label/SID for the packet; most of the magic actually occurs in * the security server function security_net_peersid_cmp(). The function * returns zero if the value in @sid is valid (although it may be SECSID_NULL) * or -EACCES if @sid is invalid due to inconsistencies with the different * peer labels. * */ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) { int err; u32 xfrm_sid; u32 nlbl_sid; u32 nlbl_type; err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); if (unlikely(err)) return -EACCES; err = security_net_peersid_resolve(&selinux_state, nlbl_sid, nlbl_type, xfrm_sid, sid); if (unlikely(err)) { pr_warn( "SELinux: failure in selinux_skb_peerlbl_sid()," " unable to determine packet's peer label\n"); return -EACCES; } return 0; } /** * selinux_conn_sid - Determine the child socket label for a connection * @sk_sid: the parent socket's SID * @skb_sid: the packet's SID * @conn_sid: the resulting connection SID * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) { int err = 0; if (skb_sid != SECSID_NULL) err = security_sid_mls_copy(&selinux_state, sk_sid, skb_sid, conn_sid); else *conn_sid = sk_sid; return err; } /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, u16 secclass, u32 *socksid) { if (tsec->sockcreate_sid > SECSID_NULL) { *socksid = tsec->sockcreate_sid; return 0; } return security_transition_sid(&selinux_state, tsec->sid, tsec->sid, secclass, NULL, socksid); } static int sock_has_perm(struct sock *sk, u32 perms) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; if (sksec->sid == SECINITSID_KERNEL) return 0; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = sk; return avc_has_perm(&selinux_state, current_sid(), sksec->sid, sksec->sclass, perms, &ad); } static int selinux_socket_create(int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; if (kern) return 0; secclass = socket_type_to_security_class(family, type, protocol); rc = socket_sockcreate_sid(tsec, secclass, &newsid); if (rc) return rc; return avc_has_perm(&selinux_state, tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); u32 sid = SECINITSID_KERNEL; int err = 0; if (!kern) { err = socket_sockcreate_sid(tsec, sclass, &sid); if (err) return err; } isec->sclass = sclass; isec->sid = sid; isec->initialized = LABEL_INITIALIZED; if (sock->sk) { sksec = sock->sk->sk_security; sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) sksec->sctp_assoc_state = SCTP_ASSOC_UNSET; err = selinux_netlbl_socket_post_create(sock->sk, family); } return err; } static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { struct sk_security_struct *sksec_a = socka->sk->sk_security; struct sk_security_struct *sksec_b = sockb->sk->sk_security; sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; return 0; } /* Range of port numbers used to automatically bind. Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; u16 family; int err; err = sock_has_perm(sk, SOCKET__BIND); if (err) goto out; /* If PF_INET or PF_INET6, check name_bind permission for the port. */ family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; u16 family_sa; unsigned short snum; u32 sid, node_perm; /* * sctp_bindx(3) calls via selinux_sctp_bind_connect() * that validates multiple binding addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; family_sa = address->sa_family; switch (family_sa) { case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { if (family == PF_INET6) { /* Length check from inet6_bind_sk() */ if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; /* Family check from __inet6_bind() */ goto err_af; } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) goto err_af; family_sa = AF_INET; } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; case AF_INET6: if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; addr6 = (struct sockaddr_in6 *)address; snum = ntohs(addr6->sin6_port); addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: goto err_af; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sport = htons(snum); ad.u.net->family = family_sa; if (snum) { int low, high; inet_get_local_port_range(sock_net(sk), &low, &high); if (inet_port_requires_bind_service(sock_net(sk), snum) || snum < low || snum > high) { err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) goto out; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, SOCKET__NAME_BIND, &ad); if (err) goto out; } } switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: node_perm = TCP_SOCKET__NODE_BIND; break; case SECCLASS_UDP_SOCKET: node_perm = UDP_SOCKET__NODE_BIND; break; case SECCLASS_DCCP_SOCKET: node_perm = DCCP_SOCKET__NODE_BIND; break; case SECCLASS_SCTP_SOCKET: node_perm = SCTP_SOCKET__NODE_BIND; break; default: node_perm = RAWIP_SOCKET__NODE_BIND; break; } err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, node_perm, &ad); if (err) goto out; } out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; int err; err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* connect(AF_UNSPEC) has special handling, as it is a documented * way to disconnect the socket */ if (address->sa_family == AF_UNSPEC) return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission * for the port. */ if (sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_DCCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) { struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; unsigned short snum; u32 sid, perm; /* sctp_connectx(3) calls via selinux_sctp_bind_connect() * that validates multiple connect addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; snum = ntohs(addr4->sin_port); break; case AF_INET6: addr6 = (struct sockaddr_in6 *)address; if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; snum = ntohs(addr6->sin6_port); break; default: /* Note that SCTP services expect -EINVAL, whereas * others expect -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; else return -EAFNOSUPPORT; } err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) return err; switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: perm = TCP_SOCKET__NAME_CONNECT; break; case SECCLASS_DCCP_SOCKET: perm = DCCP_SOCKET__NAME_CONNECT; break; case SECCLASS_SCTP_SOCKET: perm = SCTP_SOCKET__NAME_CONNECT; break; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); ad.u.net->family = address->sa_family; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, perm, &ad); if (err) return err; } return 0; } /* Supports connect(2), see comments in selinux_socket_connect_helper() */ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { int err; struct sock *sk = sock->sk; err = selinux_socket_connect_helper(sock, address, addrlen); if (err) return err; return selinux_netlbl_socket_connect(sk, address); } static int selinux_socket_listen(struct socket *sock, int backlog) { return sock_has_perm(sock->sk, SOCKET__LISTEN); } static int selinux_socket_accept(struct socket *sock, struct socket *newsock) { int err; struct inode_security_struct *isec; struct inode_security_struct *newisec; u16 sclass; u32 sid; err = sock_has_perm(sock->sk, SOCKET__ACCEPT); if (err) return err; isec = inode_security_novalidate(SOCK_INODE(sock)); spin_lock(&isec->lock); sclass = isec->sclass; sid = isec->sid; spin_unlock(&isec->lock); newisec = inode_security_novalidate(SOCK_INODE(newsock)); newisec->sclass = sclass; newisec->sid = sid; newisec->initialized = LABEL_INITIALIZED; return 0; } static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return sock_has_perm(sock->sk, SOCKET__WRITE); } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return sock_has_perm(sock->sk, SOCKET__READ); } static int selinux_socket_getsockname(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_getpeername(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_setsockopt(struct socket *sock, int level, int optname) { int err; err = sock_has_perm(sock->sk, SOCKET__SETOPT); if (err) return err; return selinux_netlbl_socket_setsockopt(sock, level, optname); } static int selinux_socket_getsockopt(struct socket *sock, int level, int optname) { return sock_has_perm(sock->sk, SOCKET__GETOPT); } static int selinux_socket_shutdown(struct socket *sock, int how) { return sock_has_perm(sock->sk, SOCKET__SHUTDOWN); } static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { struct sk_security_struct *sksec_sock = sock->sk_security; struct sk_security_struct *sksec_other = other->sk_security; struct sk_security_struct *sksec_new = newsk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; int err; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = other; err = avc_has_perm(&selinux_state, sksec_sock->sid, sksec_other->sid, sksec_other->sclass, UNIX_STREAM_SOCKET__CONNECTTO, &ad); if (err) return err; /* server child socket */ sksec_new->peer_sid = sksec_sock->sid; err = security_sid_mls_copy(&selinux_state, sksec_other->sid, sksec_sock->sid, &sksec_new->sid); if (err) return err; /* connecting socket */ sksec_sock->peer_sid = sksec_new->sid; return 0; } static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { struct sk_security_struct *ssec = sock->sk->sk_security; struct sk_security_struct *osec = other->sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = other->sk; return avc_has_perm(&selinux_state, ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO, &ad); } static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex, char *addrp, u16 family, u32 peer_sid, struct common_audit_data *ad) { int err; u32 if_sid; u32 node_sid; err = sel_netif_sid(ns, ifindex, &if_sid); if (err) return err; err = avc_has_perm(&selinux_state, peer_sid, if_sid, SECCLASS_NETIF, NETIF__INGRESS, ad); if (err) return err; err = sel_netnode_sid(addrp, family, &node_sid); if (err) return err; return avc_has_perm(&selinux_state, peer_sid, node_sid, SECCLASS_NODE, NODE__RECVFROM, ad); } static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; struct sk_security_struct *sksec = sk->sk_security; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = skb->skb_iif; ad.u.net->family = family; err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (selinux_secmark_enabled()) { err = avc_has_perm(&selinux_state, sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad); if (err) return err; err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad); return err; } static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; struct sk_security_struct *sksec = sk->sk_security; u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; u8 secmark_active; u8 peerlbl_active; if (family != PF_INET && family != PF_INET6) return 0; /* Handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_sock_rcv_skb_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_sock_rcv_skb_compat(sk, skb, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return 0; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = skb->skb_iif; ad.u.net->family = family; err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (peerlbl_active) { u32 peer_sid; err = selinux_skb_peerlbl_sid(skb, family, &peer_sid); if (err) return err; err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } err = avc_has_perm(&selinux_state, sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } } if (secmark_active) { err = avc_has_perm(&selinux_state, sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } return err; } static int selinux_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { int err = 0; char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = sock->sk->sk_security; u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) peer_sid = sksec->peer_sid; if (peer_sid == SECSID_NULL) return -ENOPROTOOPT; err = security_sid_to_context(&selinux_state, peer_sid, &scontext, &scontext_len); if (err) return err; if (scontext_len > len) { err = -ERANGE; goto out_len; } if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; out_len: if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; } static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { u32 peer_secid = SECSID_NULL; u16 family; struct inode_security_struct *isec; if (skb && skb->protocol == htons(ETH_P_IP)) family = PF_INET; else if (skb && skb->protocol == htons(ETH_P_IPV6)) family = PF_INET6; else if (sock) family = sock->sk->sk_family; else goto out; if (sock && family == PF_UNIX) { isec = inode_security_novalidate(SOCK_INODE(sock)); peer_secid = isec->sid; } else if (skb) selinux_skb_peerlbl_sid(skb, family, &peer_secid); out: *secid = peer_secid; if (peer_secid == SECSID_NULL) return -EINVAL; return 0; } static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *sksec; sksec = kzalloc(sizeof(*sksec), priority); if (!sksec) return -ENOMEM; sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); sk->sk_security = sksec; return 0; } static void selinux_sk_free_security(struct sock *sk) { struct sk_security_struct *sksec = sk->sk_security; sk->sk_security = NULL; selinux_netlbl_sk_security_free(sksec); kfree(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; newsksec->sclass = sksec->sclass; selinux_netlbl_sk_security_reset(newsksec); } static void selinux_sk_getsecid(struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { struct sk_security_struct *sksec = sk->sk_security; *secid = sksec->sid; } } static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); struct sk_security_struct *sksec = sk->sk_security; if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; } /* Called whenever SCTP receives an INIT chunk. This happens when an incoming * connect(2), sctp_connectx(3) or sctp_sendmsg(3) (with no association * already present). */ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb) { struct sk_security_struct *sksec = ep->base.sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; u8 peerlbl_active; u32 peer_sid = SECINITSID_UNLABELED; u32 conn_sid; int err = 0; if (!selinux_policycap_extsockclass()) return 0; peerlbl_active = selinux_peerlbl_enabled(); if (peerlbl_active) { /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ err = selinux_skb_peerlbl_sid(skb, ep->base.sk->sk_family, &peer_sid); if (err) return err; if (peer_sid == SECSID_NULL) peer_sid = SECINITSID_UNLABELED; } if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) { sksec->sctp_assoc_state = SCTP_ASSOC_SET; /* Here as first association on socket. As the peer SID * was allowed by peer recv (and the netif/node checks), * then it is approved by policy and used as the primary * peer SID for getpeercon(3). */ sksec->peer_sid = peer_sid; } else if (sksec->peer_sid != peer_sid) { /* Other association peer SIDs are checked to enforce * consistency among the peer SIDs. */ ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = ep->base.sk; err = avc_has_perm(&selinux_state, sksec->peer_sid, peer_sid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); if (err) return err; } /* Compute the MLS component for the connection and store * the information in ep. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. */ err = selinux_conn_sid(sksec->sid, peer_sid, &conn_sid); if (err) return err; ep->secid = conn_sid; ep->peer_secid = peer_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ return selinux_netlbl_sctp_assoc_request(ep, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting * based on their @optname. */ static int selinux_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { if (walk_size + sizeof(sa_family_t) > addrlen) return -EINVAL; addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; case AF_INET6: len = sizeof(struct sockaddr_in6); break; default: return -EINVAL; } if (walk_size + len > addrlen) return -EINVAL; err = -EINVAL; switch (optname) { /* Bind checks */ case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: err = selinux_socket_bind(sock, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: err = selinux_socket_connect_helper(sock, addr, len); if (err) return err; /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new * primary address is selected. * Note that an SCTP connect(2) call happens before * the SCTP protocol layer and is handled via * selinux_socket_connect(). */ err = selinux_netlbl_socket_connect_locked(sk, addr); break; } if (err) return err; addr_buf += len; walk_size += len; } return 0; } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. */ if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); newsksec->sid = ep->secid; newsksec->peer_sid = ep->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct sk_security_struct *sksec = sk->sk_security; int err; u16 family = req->rsk_ops->family; u32 connsid; u32 peersid; err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; err = selinux_conn_sid(sksec->sid, peersid, &connsid); if (err) return err; req->secid = connsid; req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; /* NOTE: Ideally, we should also get the isec->sid for the new socket in sync, but we don't have the isec available yet. So we will wait until sock_graft to do it, by which time it will have been created and available. */ /* We don't need to take any sort of lock here as we are the only * thread with access to newsksec */ selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family); } static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; u32 tsid; __tsec = selinux_cred(current_cred()); tsid = __tsec->sid; return avc_has_perm(&selinux_state, tsid, sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } static void selinux_secmark_refcount_inc(void) { atomic_inc(&selinux_secmark_refcount); } static void selinux_secmark_refcount_dec(void) { atomic_dec(&selinux_secmark_refcount); } static void selinux_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { flic->flowic_secid = req->secid; } static int selinux_tun_dev_alloc_security(void **security) { struct tun_security_struct *tunsec; tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL); if (!tunsec) return -ENOMEM; tunsec->sid = current_sid(); *security = tunsec; return 0; } static void selinux_tun_dev_free_security(void *security) { kfree(security); } static int selinux_tun_dev_create(void) { u32 sid = current_sid(); /* we aren't taking into account the "sockcreate" SID since the socket * that is being created here is not a socket in the traditional sense, * instead it is a private sock, accessible only to the kernel, and * representing a wide range of network traffic spanning multiple * connections unlike traditional sockets - check the TUN driver to * get a better understanding of why this socket is special */ return avc_has_perm(&selinux_state, sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE, NULL); } static int selinux_tun_dev_attach_queue(void *security) { struct tun_security_struct *tunsec = security; return avc_has_perm(&selinux_state, current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); } static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = security; struct sk_security_struct *sksec = sk->sk_security; /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply * labeling without the support of the TUN user the resulting labeled * traffic from the other end of the connection would almost certainly * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; return 0; } static int selinux_tun_dev_open(void *security) { struct tun_security_struct *tunsec = security; u32 sid = current_sid(); int err; err = avc_has_perm(&selinux_state, sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; err = avc_has_perm(&selinux_state, sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELTO, NULL); if (err) return err; tunsec->sid = sid; return 0; } #ifdef CONFIG_NETFILTER static unsigned int selinux_ip_forward(struct sk_buff *skb, const struct net_device *indev, u16 family) { int err; char *addrp; u32 peer_sid; struct common_audit_data ad; struct lsm_network_audit net = {0,}; u8 secmark_active; u8 netlbl_active; u8 peerlbl_active; if (!selinux_policycap_netpeer()) return NF_ACCEPT; secmark_active = selinux_secmark_enabled(); netlbl_active = netlbl_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0) return NF_DROP; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = indev->ifindex; ad.u.net->family = family; if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0) return NF_DROP; if (peerlbl_active) { err = selinux_inet_sys_rcv_skb(dev_net(indev), indev->ifindex, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 1); return NF_DROP; } } if (secmark_active) if (avc_has_perm(&selinux_state, peer_sid, skb->secmark, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; if (netlbl_active) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH * protection */ if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ipv4_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_forward(skb, state->in, PF_INET); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int selinux_ipv6_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_forward(skb, state->in, PF_INET6); } #endif /* IPV6 */ static unsigned int selinux_ip_output(struct sk_buff *skb, u16 family) { struct sock *sk; u32 sid; if (!netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ sk = skb->sk; if (sk) { struct sk_security_struct *sksec; if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and * not the parent socket. unfortunately, we can't * lookup the request_sock yet as it isn't queued on * the parent socket until after the SYN-ACK is sent. * the "solution" is to simply pass the packet as-is * as any IP option based labeling should be copied * from the initial connection request (in the IP * layer). it is far from ideal, but until we get a * security label in the packet itself this is the * best we can do. */ return NF_ACCEPT; /* standard practice, label using the parent socket */ sksec = sk->sk_security; sid = sksec->sid; } else sid = SECINITSID_KERNEL; if (selinux_netlbl_skbuff_setsid(skb, family, sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_output(skb, PF_INET); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int selinux_ipv6_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_output(skb, PF_INET6); } #endif /* IPV6 */ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, int ifindex, u16 family) { struct sock *sk = skb_to_full_sk(skb); struct sk_security_struct *sksec; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; u8 proto = 0; if (sk == NULL) return NF_ACCEPT; sksec = sk->sk_security; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = ifindex; ad.u.net->family = family; if (selinux_parse_skb(skb, &ad, &addrp, 0, &proto)) return NF_DROP; if (selinux_secmark_enabled()) if (avc_has_perm(&selinux_state, sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) return NF_DROP_ERR(-ECONNREFUSED); return NF_ACCEPT; } static unsigned int selinux_ip_postroute(struct sk_buff *skb, const struct net_device *outdev, u16 family) { u32 secmark_perm; u32 peer_sid; int ifindex = outdev->ifindex; struct sock *sk; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; u8 secmark_active; u8 peerlbl_active; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_ip_postroute_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_ip_postroute_compat(skb, ifindex, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; sk = skb_to_full_sk(skb); #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. * NOTE: if this is a local socket (skb->sk != NULL) that is in the * TCP listening state we cannot wait until the XFRM processing * is done as we will miss out on the SA label if we do; * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && !(sk && sk_listener(sk))) return NF_ACCEPT; #endif if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet * to determine which and if the packet is being forwarded * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) return NF_DROP; } else { secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned * to the connection/request_sock but unfortunately we can't * query the request_sock as it isn't queued on the parent * socket until after the SYN-ACK packet is sent; the only * viable choice is to regenerate the label like we do in * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; struct sk_security_struct *sksec; sksec = sk->sk_security; if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL * and the packet has been through at least one XFRM * transformation then we must be dealing with the "final" * form of labeled IPsec packet; since we've already applied * all of our access controls on this packet we can safely * pass the packet. */ if (skb_sid == SECSID_NULL) { switch (family) { case PF_INET: if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; case PF_INET6: if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; default: return NF_DROP_ERR(-ECONNREFUSED); } } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; } else { /* Locally generated packet, fetch the security label from the * associated socket. */ struct sk_security_struct *sksec = sk->sk_security; peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = ifindex; ad.u.net->family = family; if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL)) return NF_DROP; if (secmark_active) if (avc_has_perm(&selinux_state, peer_sid, skb->secmark, SECCLASS_PACKET, secmark_perm, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (peerlbl_active) { u32 if_sid; u32 node_sid; if (sel_netif_sid(dev_net(outdev), ifindex, &if_sid)) return NF_DROP; if (avc_has_perm(&selinux_state, peer_sid, if_sid, SECCLASS_NETIF, NETIF__EGRESS, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (sel_netnode_sid(addrp, family, &node_sid)) return NF_DROP; if (avc_has_perm(&selinux_state, peer_sid, node_sid, SECCLASS_NODE, NODE__SENDTO, &ad)) return NF_DROP_ERR(-ECONNREFUSED); } return NF_ACCEPT; } static unsigned int selinux_ipv4_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_postroute(skb, state->out, PF_INET); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int selinux_ipv6_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_postroute(skb, state->out, PF_INET6); } #endif /* IPV6 */ #endif /* CONFIG_NETFILTER */ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { int rc = 0; unsigned int msg_len; unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = sk->sk_security; u16 sclass = sksec->sclass; u32 perm; while (data_len >= nlmsg_total_size(0)) { nlh = (struct nlmsghdr *)data; /* NOTE: the nlmsg_len field isn't reliably set by some netlink * users which means we can't reject skb's with bogus * length fields; our solution is to follow what * netlink_rcv_skb() does and simply skip processing at * messages with length fields that are clearly junk */ if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) return 0; rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); if (rc == 0) { rc = sock_has_perm(sk, perm); if (rc) return rc; } else if (rc == -EINVAL) { /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" " message: protocol=%hu nlmsg_type=%hu sclass=%s" " pid=%d comm=%s\n", sk->sk_protocol, nlh->nlmsg_type, secclass_map[sclass - 1].name, task_pid_nr(current), current->comm); if (enforcing_enabled(&selinux_state) && !security_get_allow_unknown(&selinux_state)) return rc; rc = 0; } else if (rc == -ENOENT) { /* -ENOENT is a missing socket/class mapping, ignore */ rc = 0; } else { return rc; } /* move to the next message after applying netlink padding */ msg_len = NLMSG_ALIGN(nlh->nlmsg_len); if (msg_len >= data_len) return 0; data_len -= msg_len; data += msg_len; } return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { isec->sclass = sclass; isec->sid = current_sid(); } static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(ipc_perms); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = ipc_perms->key; return avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; return 0; } /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); return rc; } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { int err; int perms; switch (cmd) { case IPC_INFO: case MSG_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: perms = MSGQ__GETATTR | MSGQ__ASSOCIATE; break; case IPC_SET: perms = MSGQ__SETATTR; break; case IPC_RMID: perms = MSGQ__DESTROY; break; default: return 0; } err = ipc_has_perm(msq, perms); return err; } static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); /* * First time through, need to assign label to the message */ if (msec->sid == SECINITSID_UNLABELED) { /* * Compute new sid based on current process and * message queue this message will be stored in */ rc = security_transition_sid(&selinux_state, sid, isec->sid, SECCLASS_MSG, NULL, &msec->sid); if (rc) return rc; } ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; /* Can this process write to the queue? */ rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ rc = avc_has_perm(&selinux_state, sid, msec->sid, SECCLASS_MSG, MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ rc = avc_has_perm(&selinux_state, msec->sid, isec->sid, SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); return rc; } static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = task_sid(target); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) rc = avc_has_perm(&selinux_state, sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(shp); ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); return rc; } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } /* Note, at this point, shp is locked down */ static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { int perms; int err; switch (cmd) { case IPC_INFO: case SHM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case SHM_STAT: case SHM_STAT_ANY: perms = SHM__GETATTR | SHM__ASSOCIATE; break; case IPC_SET: perms = SHM__SETATTR; break; case SHM_LOCK: case SHM_UNLOCK: perms = SHM__LOCK; break; case IPC_RMID: perms = SHM__DESTROY; break; default: return 0; } err = ipc_has_perm(shp, perms); return err; } static int selinux_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { u32 perms; if (shmflg & SHM_RDONLY) perms = SHM__READ; else perms = SHM__READ | SHM__WRITE; return ipc_has_perm(shp, perms); } /* Semaphore security operations */ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(sma); ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); return rc; } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } /* Note, at this point, sma is locked down */ static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd) { int err; u32 perms; switch (cmd) { case IPC_INFO: case SEM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case GETPID: case GETNCNT: case GETZCNT: perms = SEM__GETATTR; break; case GETVAL: case GETALL: perms = SEM__READ; break; case SETVAL: case SETALL: perms = SEM__WRITE; break; case IPC_RMID: perms = SEM__DESTROY; break; case IPC_SET: perms = SEM__SETATTR; break; case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: perms = SEM__GETATTR | SEM__ASSOCIATE; break; default: return 0; } err = ipc_has_perm(sma, perms); return err; } static int selinux_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { u32 perms; if (alter) perms = SEM__READ | SEM__WRITE; else perms = SEM__READ; return ipc_has_perm(sma, perms); } static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { u32 av = 0; av = 0; if (flag & S_IRUGO) av |= IPC__UNIX_READ; if (flag & S_IWUGO) av |= IPC__UNIX_WRITE; if (av == 0) return 0; return ipc_has_perm(ipcp, av); } static void selinux_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { struct ipc_security_struct *isec = selinux_ipc(ipcp); *secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) { if (inode) inode_doinit_with_dentry(inode, dentry); } static int selinux_getprocattr(struct task_struct *p, char *name, char **value) { const struct task_security_struct *__tsec; u32 sid; int error; unsigned len; rcu_read_lock(); __tsec = selinux_cred(__task_cred(p)); if (current != p) { error = avc_has_perm(&selinux_state, current_sid(), __tsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto bad; } if (!strcmp(name, "current")) sid = __tsec->sid; else if (!strcmp(name, "prev")) sid = __tsec->osid; else if (!strcmp(name, "exec")) sid = __tsec->exec_sid; else if (!strcmp(name, "fscreate")) sid = __tsec->create_sid; else if (!strcmp(name, "keycreate")) sid = __tsec->keycreate_sid; else if (!strcmp(name, "sockcreate")) sid = __tsec->sockcreate_sid; else { error = -EINVAL; goto bad; } rcu_read_unlock(); if (!sid) return 0; error = security_sid_to_context(&selinux_state, sid, value, &len); if (error) return error; return len; bad: rcu_read_unlock(); return error; } static int selinux_setprocattr(const char *name, void *value, size_t size) { struct task_security_struct *tsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; char *str = value; /* * Basic control over ability to set these attributes at all. */ if (!strcmp(name, "exec")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETEXEC, NULL); else if (!strcmp(name, "fscreate")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETFSCREATE, NULL); else if (!strcmp(name, "keycreate")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETKEYCREATE, NULL); else if (!strcmp(name, "sockcreate")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, NULL); else if (!strcmp(name, "current")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETCURRENT, NULL); else error = -EINVAL; if (error) return error; /* Obtain a SID for the context, if one was specified. */ if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; } error = security_context_to_sid(&selinux_state, value, size, &sid, GFP_KERNEL); if (error == -EINVAL && !strcmp(name, "fscreate")) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=fscreate invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return error; } error = security_context_to_sid_force( &selinux_state, value, size, &sid); } if (error) return error; } new = prepare_creds(); if (!new) return -ENOMEM; /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ tsec = selinux_cred(new); if (!strcmp(name, "exec")) { tsec->exec_sid = sid; } else if (!strcmp(name, "fscreate")) { tsec->create_sid = sid; } else if (!strcmp(name, "keycreate")) { if (sid) { error = avc_has_perm(&selinux_state, mysid, sid, SECCLASS_KEY, KEY__CREATE, NULL); if (error) goto abort_change; } tsec->keycreate_sid = sid; } else if (!strcmp(name, "sockcreate")) { tsec->sockcreate_sid = sid; } else if (!strcmp(name, "current")) { error = -EINVAL; if (sid == 0) goto abort_change; /* Only allow single threaded processes to change context */ error = -EPERM; if (!current_is_single_threaded()) { error = security_bounded_transition(&selinux_state, tsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ error = avc_has_perm(&selinux_state, tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = ptrace_parent_sid(); if (ptsid != 0) { error = avc_has_perm(&selinux_state, ptsid, sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (error) goto abort_change; } tsec->sid = sid; } else { error = -EINVAL; goto abort_change; } commit_creds(new); return size; abort_change: abort_creds(new); return error; } static int selinux_ismaclabel(const char *name) { return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return security_sid_to_context(&selinux_state, secid, secdata, seclen); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { return security_context_to_sid(&selinux_state, secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) { kfree(secdata); } static void selinux_inode_invalidate_secctx(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); spin_lock(&isec->lock); isec->initialized = LABEL_INVALID; spin_unlock(&isec->lock); } /* * called with inode->i_mutex locked */ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, ctxlen, 0); /* Do not return error when suppressing label (SBLABEL_MNT not set). */ return rc == -EOPNOTSUPP ? 0 : rc; } /* * called with inode->i_mutex locked */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return __vfs_setxattr_locked(dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0, NULL); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; len = selinux_inode_getsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; return 0; } #ifdef CONFIG_KEYS static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; struct key_security_struct *ksec; ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); if (!ksec) return -ENOMEM; tsec = selinux_cred(cred); if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; k->security = ksec; return 0; } static void selinux_key_free(struct key *k) { struct key_security_struct *ksec = k->security; k->security = NULL; kfree(ksec); } static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; struct key_security_struct *ksec; u32 perm, sid; switch (need_perm) { case KEY_NEED_VIEW: perm = KEY__VIEW; break; case KEY_NEED_READ: perm = KEY__READ; break; case KEY_NEED_WRITE: perm = KEY__WRITE; break; case KEY_NEED_SEARCH: perm = KEY__SEARCH; break; case KEY_NEED_LINK: perm = KEY__LINK; break; case KEY_NEED_SETATTR: perm = KEY__SETATTR; break; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: return 0; default: WARN_ON(1); return -EPERM; } sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); ksec = key->security; return avc_has_perm(&selinux_state, sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { struct key_security_struct *ksec = key->security; char *context = NULL; unsigned len; int rc; rc = security_sid_to_context(&selinux_state, ksec->sid, &context, &len); if (!rc) rc = len; *_buffer = context; return rc; } #ifdef CONFIG_KEY_NOTIFICATIONS static int selinux_watch_key(struct key *key) { struct key_security_struct *ksec = key->security; u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL); } #endif #endif #ifdef CONFIG_SECURITY_INFINIBAND static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibpkey_audit ibpkey; err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBPKEY; ibpkey.subnet_prefix = subnet_prefix; ibpkey.pkey = pkey_val; ad.u.ibpkey = &ibpkey; return avc_has_perm(&selinux_state, sec->sid, sid, SECCLASS_INFINIBAND_PKEY, INFINIBAND_PKEY__ACCESS, &ad); } static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, u8 port_num) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibendport_audit ibendport; err = security_ib_endport_sid(&selinux_state, dev_name, port_num, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; strncpy(ibendport.dev_name, dev_name, sizeof(ibendport.dev_name)); ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(&selinux_state, sec->sid, sid, SECCLASS_INFINIBAND_ENDPORT, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } static int selinux_ib_alloc_security(void **ib_sec) { struct ib_security_struct *sec; sec = kzalloc(sizeof(*sec), GFP_KERNEL); if (!sec) return -ENOMEM; sec->sid = current_sid(); *ib_sec = sec; return 0; } static void selinux_ib_free_security(void *ib_sec) { kfree(ib_sec); } #endif #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, unsigned int size) { u32 sid = current_sid(); int ret; switch (cmd) { case BPF_MAP_CREATE: ret = avc_has_perm(&selinux_state, sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); break; case BPF_PROG_LOAD: ret = avc_has_perm(&selinux_state, sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); break; default: ret = 0; break; } return ret; } static u32 bpf_map_fmode_to_av(fmode_t fmode) { u32 av = 0; if (fmode & FMODE_READ) av |= BPF__MAP_READ; if (fmode & FMODE_WRITE) av |= BPF__MAP_WRITE; return av; } /* This function will check the file pass through unix socket or binder to see * if it is a bpf related object. And apply correspinding checks on the bpf * object based on the type. The bpf maps and programs, not like other files and * socket, are using a shared anonymous inode inside the kernel as their inode. * So checking that inode cannot identify if the process have privilege to * access the bpf object and that's why we have to add this additional check in * selinux_file_receive and selinux_binder_transfer_files. */ static int bpf_fd_pass(struct file *file, u32 sid) { struct bpf_security_struct *bpfsec; struct bpf_prog *prog; struct bpf_map *map; int ret; if (file->f_op == &bpf_map_fops) { map = file->private_data; bpfsec = map->security; ret = avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(file->f_mode), NULL); if (ret) return ret; } else if (file->f_op == &bpf_prog_fops) { prog = file->private_data; bpfsec = prog->aux->security; ret = avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); if (ret) return ret; } return 0; } static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = map->security; return avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(fmode), NULL); } static int selinux_bpf_prog(struct bpf_prog *prog) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = prog->aux->security; return avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); } static int selinux_bpf_map_alloc(struct bpf_map *map) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); map->security = bpfsec; return 0; } static void selinux_bpf_map_free(struct bpf_map *map) { struct bpf_security_struct *bpfsec = map->security; map->security = NULL; kfree(bpfsec); } static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); aux->security = bpfsec; return 0; } static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) { struct bpf_security_struct *bpfsec = aux->security; aux->security = NULL; kfree(bpfsec); } #endif static int selinux_lockdown(enum lockdown_reason what) { struct common_audit_data ad; u32 sid = current_sid(); int invalid_reason = (what <= LOCKDOWN_NONE) || (what == LOCKDOWN_INTEGRITY_MAX) || (what >= LOCKDOWN_CONFIDENTIALITY_MAX); if (WARN(invalid_reason, "Invalid lockdown reason")) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "lockdown_reason=invalid"); return -EINVAL; } ad.type = LSM_AUDIT_DATA_LOCKDOWN; ad.u.reason = what; if (what <= LOCKDOWN_INTEGRITY_MAX) return avc_has_perm(&selinux_state, sid, sid, SECCLASS_LOCKDOWN, LOCKDOWN__INTEGRITY, &ad); else return avc_has_perm(&selinux_state, sid, sid, SECCLASS_LOCKDOWN, LOCKDOWN__CONFIDENTIALITY, &ad); } struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), }; #ifdef CONFIG_PERF_EVENTS static int selinux_perf_event_open(struct perf_event_attr *attr, int type) { u32 requested, sid = current_sid(); if (type == PERF_SECURITY_OPEN) requested = PERF_EVENT__OPEN; else if (type == PERF_SECURITY_CPU) requested = PERF_EVENT__CPU; else if (type == PERF_SECURITY_KERNEL) requested = PERF_EVENT__KERNEL; else if (type == PERF_SECURITY_TRACEPOINT) requested = PERF_EVENT__TRACEPOINT; else return -EINVAL; return avc_has_perm(&selinux_state, sid, sid, SECCLASS_PERF_EVENT, requested, NULL); } static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; perfsec = kzalloc(sizeof(*perfsec), GFP_KERNEL); if (!perfsec) return -ENOMEM; perfsec->sid = current_sid(); event->security = perfsec; return 0; } static void selinux_perf_event_free(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; event->security = NULL; kfree(perfsec); } static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); } static int selinux_perf_event_write(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); } #endif /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, * 2. hooks that both access structures allocated by other hooks, and allocate * structures that can be later accessed by other hooks (mostly "cloning" * hooks), * 3. hooks that only allocate structures that can be later accessed by other * hooks ("allocating" hooks). * * Please follow block comment delimiters in the list to keep this order. * * This ordering is needed for SELinux runtime disable to work at least somewhat * safely. Breaking the ordering rules above might lead to NULL pointer derefs * when disabling SELinux at runtime. */ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder), LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file), LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme), LSM_HOOK_INIT(capget, selinux_capget), LSM_HOOK_INIT(capset, selinux_capset), LSM_HOOK_INIT(capable, selinux_capable), LSM_HOOK_INIT(quotactl, selinux_quotactl), LSM_HOOK_INIT(quota_on, selinux_quota_on), LSM_HOOK_INIT(syslog, selinux_syslog), LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory), LSM_HOOK_INIT(netlink_send, selinux_netlink_send), LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds), LSM_HOOK_INIT(sb_free_security, selinux_sb_free_security), LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts), LSM_HOOK_INIT(sb_remount, selinux_sb_remount), LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount), LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options), LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs), LSM_HOOK_INIT(sb_mount, selinux_mount), LSM_HOOK_INIT(sb_umount, selinux_umount), LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts), LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts), LSM_HOOK_INIT(move_mount, selinux_move_mount), LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security), LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as), LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security), LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security), LSM_HOOK_INIT(inode_create, selinux_inode_create), LSM_HOOK_INIT(inode_link, selinux_inode_link), LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink), LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink), LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir), LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir), LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod), LSM_HOOK_INIT(inode_rename, selinux_inode_rename), LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink), LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link), LSM_HOOK_INIT(inode_permission, selinux_inode_permission), LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr), LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr), LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr), LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr), LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr), LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr), LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), LSM_HOOK_INIT(inode_getsecid, selinux_inode_getsecid), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security), LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), LSM_HOOK_INIT(file_lock, selinux_file_lock), LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl), LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner), LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask), LSM_HOOK_INIT(file_receive, selinux_file_receive), LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data), LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), LSM_HOOK_INIT(task_getsecid, selinux_task_getsecid), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit), LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit), LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler), LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler), LSM_HOOK_INIT(task_movememory, selinux_task_movememory), LSM_HOOK_INIT(task_kill, selinux_task_kill), LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate), LSM_HOOK_INIT(getprocattr, selinux_getprocattr), LSM_HOOK_INIT(setprocattr, selinux_setprocattr), LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel), LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid), LSM_HOOK_INIT(release_secctx, selinux_release_secctx), LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx), LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx), LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send), LSM_HOOK_INIT(socket_create, selinux_socket_create), LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create), LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair), LSM_HOOK_INIT(socket_bind, selinux_socket_bind), LSM_HOOK_INIT(socket_connect, selinux_socket_connect), LSM_HOOK_INIT(socket_listen, selinux_socket_listen), LSM_HOOK_INIT(socket_accept, selinux_socket_accept), LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown), LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb), LSM_HOOK_INIT(socket_getpeersec_stream, selinux_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security), LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security), LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid), LSM_HOOK_INIT(sock_graft, selinux_sock_graft), LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet), LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), LSM_HOOK_INIT(tun_dev_free_security, selinux_tun_dev_free_security), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), LSM_HOOK_INIT(ib_free_security, selinux_ib_free_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete), LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free), LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete), LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup), LSM_HOOK_INIT(xfrm_state_pol_flow_match, selinux_xfrm_state_pol_flow_match), LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_free, selinux_key_free), LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS LSM_HOOK_INIT(watch_key, selinux_watch_key), #endif #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), LSM_HOOK_INIT(perf_event_free, selinux_perf_event_free), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif LSM_HOOK_INIT(locked_down, selinux_lockdown), /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), LSM_HOOK_INIT(sb_add_mnt_opt, selinux_add_mnt_opt), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif /* * PUT "ALLOCATING" HOOKS HERE */ LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc), LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc), LSM_HOOK_INIT(xfrm_state_alloc_acquire, selinux_xfrm_state_alloc_acquire), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, selinux_key_alloc), #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), #endif }; static __init int selinux_init(void) { pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(&selinux_state, selinux_enforcing_boot); checkreqprot_set(&selinux_state, selinux_checkreqprot_boot); selinux_avc_init(&selinux_state.avc); mutex_init(&selinux_state.status_lock); mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); avc_init(); avtab_cache_init(); ebitmap_cache_init(); hashtab_cache_init(); security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), "selinux"); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC LSM notifier callback\n"); if (selinux_enforcing_boot) pr_debug("SELinux: Starting in enforcing mode\n"); else pr_debug("SELinux: Starting in permissive mode\n"); fs_validate_description("selinux", selinux_fs_parameters); return 0; } static void delayed_superblock_init(struct super_block *sb, void *unused) { selinux_set_mnt_opts(sb, NULL, 0, NULL); } void selinux_complete_init(void) { pr_debug("SELinux: Completing initialization.\n"); /* Set up any superblocks initialized prior to the policy load. */ pr_debug("SELinux: Setting up existing superblocks.\n"); iterate_supers(delayed_superblock_init, NULL); } /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled_boot, .blobs = &selinux_blob_sizes, .init = selinux_init, }; #if defined(CONFIG_NETFILTER) static const struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ipv4_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ipv4_forward, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ipv4_output, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = selinux_ipv6_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ipv6_forward, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, }, { .hook = selinux_ipv6_output, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif /* IPV6 */ }; static int __net_init selinux_nf_register(struct net *net) { return nf_register_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static void __net_exit selinux_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, }; static int __init selinux_nf_ip_init(void) { int err; if (!selinux_enabled_boot) return 0; pr_debug("SELinux: Registering netfilter hooks\n"); err = register_pernet_subsys(&selinux_net_ops); if (err) panic("SELinux: register_pernet_subsys: error %d\n", err); return 0; } __initcall(selinux_nf_ip_init); #ifdef CONFIG_SECURITY_SELINUX_DISABLE static void selinux_nf_ip_exit(void) { pr_debug("SELinux: Unregistering netfilter hooks\n"); unregister_pernet_subsys(&selinux_net_ops); } #endif #else /* CONFIG_NETFILTER */ #ifdef CONFIG_SECURITY_SELINUX_DISABLE #define selinux_nf_ip_exit() #endif #endif /* CONFIG_NETFILTER */ #ifdef CONFIG_SECURITY_SELINUX_DISABLE int selinux_disable(struct selinux_state *state) { if (selinux_initialized(state)) { /* Not permitted after initial policy load. */ return -EINVAL; } if (selinux_disabled(state)) { /* Only do this once. */ return -EINVAL; } selinux_mark_disabled(state); pr_info("SELinux: Disabled at runtime.\n"); /* * Unregister netfilter hooks. * Must be done before security_delete_hooks() to avoid breaking * runtime disable. */ selinux_nf_ip_exit(); security_delete_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks)); /* Try to destroy the avc node cache */ avc_disable(); /* Unregister selinuxfs. */ exit_sel_fs(); return 0; } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/writeback.h */ #ifndef WRITEBACK_H #define WRITEBACK_H #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/fs.h> #include <linux/flex_proportions.h> #include <linux/backing-dev-defs.h> #include <linux/blk_types.h> #include <linux/blk-cgroup.h> struct bio; DECLARE_PER_CPU(int, dirty_throttle_leaks); /* * The 1/4 region under the global dirty thresh is for smooth dirty throttling: * * (thresh - thresh/DIRTY_FULL_SCOPE, thresh) * * Further beyond, all dirtier tasks will enter a loop waiting (possibly long * time) for the dirty pages to drop, unless written enough pages. * * The global dirty threshold is normally equal to the global dirty limit, * except when the system suddenly allocates a lot of anonymous memory and * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ #define DIRTY_SCOPE 8 #define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2) struct backing_dev_info; /* * fs/fs-writeback.c */ enum writeback_sync_modes { WB_SYNC_NONE, /* Don't wait on anything */ WB_SYNC_ALL, /* Wait on every mapping */ }; /* * A control structure which tells the writeback code what to do. These are * always on the stack, and hence need no locking. They are always initialised * in a manner such that unspecified fields are set to zero. */ struct writeback_control { long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ /* * For a_ops->writepages(): if start or end are non-zero then this is * a hint that the filesystem need only write out the pages inside that * byterange. The byte at `end' is included in the writeout request. */ loff_t range_start; loff_t range_end; enum writeback_sync_modes sync_mode; unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_background:1; /* A background writeback */ unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */ unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ /* * When writeback IOs are bounced through async layers, only the * initial synchronous phase should be accounted towards inode * cgroup ownership arbitration to avoid confusion. Later stages * can set the following flag to disable the accounting. */ unsigned no_cgroup_owner:1; unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ /* foreign inode detection, see wbc_detach_inode() */ int wb_id; /* current wb id */ int wb_lcand_id; /* last foreign candidate wb id */ int wb_tcand_id; /* this foreign candidate wb id */ size_t wb_bytes; /* bytes written by current wb */ size_t wb_lcand_bytes; /* bytes written by last candidate */ size_t wb_tcand_bytes; /* bytes written by this candidate */ #endif }; static inline int wbc_to_write_flags(struct writeback_control *wbc) { int flags = 0; if (wbc->punt_to_cgroup) flags = REQ_CGROUP_PUNT; if (wbc->sync_mode == WB_SYNC_ALL) flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) flags |= REQ_BACKGROUND; return flags; } static inline struct cgroup_subsys_state * wbc_blkcg_css(struct writeback_control *wbc) { #ifdef CONFIG_CGROUP_WRITEBACK if (wbc->wb) return wbc->wb->blkcg_css; #endif return blkcg_root_css; } /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global * domain, global_wb_domain, that every wb in the system is a member of. * This allows measuring the relative bandwidth of each wb to distribute * dirtyable memory accordingly. */ struct wb_domain { spinlock_t lock; /* * Scale the writeback cache size proportional to the relative * writeout speed. * * We do this by keeping a floating proportion between BDIs, based * on page writeback completions [end_page_writeback()]. Those * devices that write out pages fastest will get the larger share, * while the slower will get a smaller share. * * We use page writeout completions because we are interested in * getting rid of dirty pages. Having them written out is the * primary goal. * * We introduce a concept of time, a period over which we measure * these events, because demand can/will vary over time. The length * of this period itself is measured in page writeback completions. */ struct fprop_global completions; struct timer_list period_timer; /* timer for aging of completions */ unsigned long period_time; /* * The dirtyable memory and dirty threshold could be suddenly * knocked down by a large amount (eg. on the startup of KVM in a * swapless system). This may throw the system into deep dirty * exceeded state and throttle heavy/light dirtiers alike. To * retain good responsiveness, maintain global_dirty_limit for * tracking slowly down to the knocked down dirty threshold. * * Both fields are protected by ->lock. */ unsigned long dirty_limit_tstamp; unsigned long dirty_limit; }; /** * wb_domain_size_changed - memory available to a wb_domain has changed * @dom: wb_domain of interest * * This function should be called when the amount of memory available to * @dom has changed. It resets @dom's dirty limit parameters to prevent * the past values which don't match the current configuration from skewing * dirty throttling. Without this, when memory size of a wb_domain is * greatly reduced, the dirty throttling logic may allow too many pages to * be dirtied leading to consecutive unnecessary OOMs and may get stuck in * that situation. */ static inline void wb_domain_size_changed(struct wb_domain *dom) { spin_lock(&dom->lock); dom->dirty_limit_tstamp = jiffies; dom->dirty_limit = 0; spin_unlock(&dom->lock); } /* * fs/fs-writeback.c */ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(enum wb_reason reason); void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) { might_sleep(); wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/cgroup.h> #include <linux/bio.h> void __inode_attach_wb(struct inode *inode, struct page *page); void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock); void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); /** * inode_attach_wb - associate an inode with its wb * @inode: inode of interest * @page: page being dirtied (may be NULL) * * If @inode doesn't have its wb, associate it with the wb matching the * memcg of @page or, if @page is NULL, %current. May be called w/ or w/o * @inode->i_lock. */ static inline void inode_attach_wb(struct inode *inode, struct page *page) { if (!inode->i_wb) __inode_attach_wb(inode, page); } /** * inode_detach_wb - disassociate an inode from its wb * @inode: inode of interest * * @inode is being freed. Detach from its wb. */ static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } } /** * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite * @wbc: writeback_control of interest * @inode: target inode * * This function is to be used by __filemap_fdatawrite_range(), which is an * alternative entry point into writeback code, and first ensures @inode is * associated with a bdi_writeback and attaches it to @wbc. */ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { spin_lock(&inode->i_lock); inode_attach_wb(inode, NULL); wbc_attach_and_unlock_inode(wbc, inode); } /** * wbc_init_bio - writeback specific initializtion of bio * @wbc: writeback_control for the writeback in progress * @bio: bio to be initialized * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup * writeback context. Must be called after the bio has been associated with * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (wbc->wb) bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline void inode_attach_wb(struct inode *inode, struct page *page) { } static inline void inode_detach_wb(struct inode *inode) { } static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { spin_unlock(&inode->i_lock); } static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { } static inline void wbc_detach_inode(struct writeback_control *wbc) { } static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { } static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { } static inline void cgroup_writeback_umount(void) { } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * mm/page-writeback.c */ #ifdef CONFIG_BLOCK void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); void laptop_mode_sync(struct work_struct *work); void laptop_mode_timer_fn(struct timer_list *t); #else static inline void laptop_sync_completion(void) { } #endif bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom); #endif extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern int dirty_background_ratio; extern unsigned long dirty_background_bytes; extern int vm_dirty_ratio; extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void balance_dirty_pages_ratelimited(struct address_space *mapping); bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, void *data); int generic_writepages(struct address_space *mapping, struct writeback_control *wbc); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); void account_page_redirty(struct page *page); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); #endif /* WRITEBACK_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set. */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS ((slab_flags_t __force)0x00000100U) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC ((slab_flags_t __force)0x00040000U) /* * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * rcu_read_lock() * again: * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * goto again; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * goto again; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU ((slab_flags_t __force)0x00080000U) /* Spread some memory over cpuset */ #define SLAB_MEM_SPREAD ((slab_flags_t __force)0x00100000U) /* Trace allocations and frees */ #define SLAB_TRACE ((slab_flags_t __force)0x00200000U) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS ((slab_flags_t __force)0x00400000U) #else # define SLAB_DEBUG_OBJECTS 0 #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE ((slab_flags_t __force)0x00800000U) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB ((slab_flags_t __force)0x02000000U) #else # define SLAB_FAILSLAB 0 #endif /* Account to memcg */ #ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U) #else # define SLAB_ACCOUNT 0 #endif #ifdef CONFIG_KASAN #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 #endif /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab deactivation flag */ #define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct mem_cgroup; /* * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); bool slab_is_available(void); extern bool usercopy_fallback; struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ kmem_cache_create(#__struct, sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), NULL) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ kmem_cache_create_usercopy(#__struct, \ sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ sizeof_field(struct __struct, __field), NULL) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); #else static inline void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user) { } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) #else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN * aligned pointers. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ #ifdef CONFIG_SLAB /* * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * * WARNING: Its not easy to increase this value since the allocators have * to do various tricks to work around compiler limitations in order to * ensure proper constant folding. */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif #ifdef CONFIG_SLOB /* * SLOB passes all requests larger than one page to the page allocator. * No kmalloc array is necessary since objects of different sizes can * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif NR_KMALLOC_TYPES }; #ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { #ifdef CONFIG_ZONE_DMA /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for both flags. */ if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0)) return KMALLOC_NORMAL; /* * At least one of the flags has to be set. If both are, __GFP_DMA * is more important. */ return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM; #else return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL; #endif } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n */ static __always_inline unsigned int kmalloc_index(size_t size) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (size <= 4 * 1024 * 1024) return 22; if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; if (size <= 64 * 1024 * 1024) return 26; BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *, void *); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); /* * Caller must not use kfree_bulk() on memory not originally allocated * by kmalloc(), because the SLOB allocator cannot handle this. */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) { return kmem_cache_alloc(s, flags); } #endif #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_slab_alignment __malloc; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); ret = kasan_kmalloc(s, ret, size, flags); return ret; } static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } #endif static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); } /** * kmalloc - allocate memory * @size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * %GFP_HIGHUSER * Allocate memory from high memory on behalf of user. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB unsigned int index; #endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB index = kmalloc_index(size); if (!index) return ZERO_SIZE_PTR; return kmem_cache_alloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif } return __kmalloc(size, flags); } static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; return kmem_cache_alloc_node_trace( kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif return __kmalloc_node(size, flags, node); } /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc(bytes, flags); return __kmalloc(bytes, flags); } /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node(bytes, flags, node); return __kmalloc_node(bytes, flags, node); } static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) #else /* CONFIG_NUMA */ #define kmalloc_node_track_caller(size, flags, node) \ kmalloc_track_caller(size, flags) #endif /* CONFIG_NUMA */ /* * Shortcuts */ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) { return kmem_cache_alloc(k, flags | __GFP_ZERO); } /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } /** * kzalloc_node - allocate zeroed memory from a particular memory node. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); #if defined(CONFIG_SMP) && defined(CONFIG_SLAB) int slab_prepare_cpu(unsigned int cpu); int slab_dead_cpu(unsigned int cpu); #else #define slab_prepare_cpu NULL #define slab_dead_cpu NULL #endif #endif /* _LINUX_SLAB_H */ |
syz_mount_image$iso9660(&(0x7f0000000000), &(0x7f0000000100)='./file0\x00', 0x0, 0x3, &(0x7f0000000200)=[{&(0x7f0000010000)="01434430303101004c494e55582020202020202020202020202020202020202020202020202020204344524f4d2020202020202020202020202020202020202020202020202020200000000000000000b7000000000000b70000000000000000000000000000000000000000000000000000000000000000010000010100000100080800180000000000001813000000000000000000001500000000220017", 0x9f, 0x8000}, {&(0x7f0000010600)="ff4344303031", 0x6, 0x8800}, {&(0x7f0000010900)="2200170000000000001700080000000008807809140b2a3a08a2", 0x1a, 0xb800}], 0x0, &(0x7f0000000140))